scsi: cxlflash: Make cxlflash_class constant

Since commit 43a7206b0963 ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the cxlflash_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ricardo B. Marliere <ricardo@marliere.net> Link: https://lore.kernel.org/r/20240302-class_cleanup-scsi-v1-3-b9096b990e27@marliere.net Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
author: Ricardo B. Marliere <ricardo@marliere.net> 2024-03-02 13:47:24 -0300
committer: Martin K. Petersen <martin.petersen@oracle.com> 2024-03-10 18:15:48 -0400
commit: a08f0eb02981ebeccc6c62833e673cc06a29393b (patch)
tree: bc2148af4d4cea3f3ca8054e321f36a7cd08388c /scripts/patch-kernel
parent: ee8dda6a7e9d28260e30ecaf8b5f27d176c8ade0 (diff)
0 files changed, 0 insertions, 0 deletions
diff --git a/.mailmap b/.mailmap
index 10b27ecb61c0..fd6219293057 100644
--- a/.mailmap
+++ b/.mailmap
@@ -108,6 +108,10 @@ Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
+Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
+Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
 Jean Tourrilhes <jt@hpl.hp.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
@@ -230,6 +234,7 @@ Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
 Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
 Shuah Khan <shuah@kernel.org> <shuahkh@osg.samsung.com>
 Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com>
+Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index 2c44b4f1b060..70dcaf2481f4 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -29,4 +29,9 @@ Description:
 		17 - sectors discarded
 		18 - time spent discarding
 
+		Kernel 5.5+ appends two more fields for flush requests:
+
+		19 - flush requests completed successfully
+		20 - time spent flushing
+
 		For more details refer to Documentation/admin-guide/iostats.rst
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index f8c7c7126bb1..ed8c14f161ee 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -15,6 +15,12 @@ Description:
 		 9 - I/Os currently in progress
 		10 - time spent doing I/Os (ms)
 		11 - weighted time spent doing I/Os (ms)
+		12 - discards completed
+		13 - discards merged
+		14 - sectors discarded
+		15 - time spent discarding (ms)
+		16 - flush requests completed
+		17 - time spent flushing (ms)
 		For more details refer Documentation/admin-guide/iostats.rst
 
 
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 06d0931119cc..fc20cde63d1e 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -486,6 +486,8 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
+		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst
index a30aa91b5fbe..594095b54b29 100644
--- a/Documentation/admin-guide/device-mapper/dm-integrity.rst
+++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst
@@ -177,6 +177,11 @@ bitmap_flush_interval:number
 	The bitmap flush interval in milliseconds. The metadata buffers
 	are synchronized when this interval expires.
 
+fix_padding
+	Use a smaller padding of the tag area that is more
+	space-efficient. If this option is not present, large padding is
+	used - that is for compatibility with older kernels.
+
 
 The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
 be changed when reloading the target (load an inactive table and swap the
diff --git a/Documentation/admin-guide/device-mapper/dm-raid.rst b/Documentation/admin-guide/device-mapper/dm-raid.rst
index 2fe255b130fb..f6344675e395 100644
--- a/Documentation/admin-guide/device-mapper/dm-raid.rst
+++ b/Documentation/admin-guide/device-mapper/dm-raid.rst
@@ -417,3 +417,5 @@ Version History
 	deadlock/potential data corruption.  Update superblock when
 	specific devices are requested via rebuild.  Fix RAID leg
 	rebuild errors.
+ 1.15.0 Fix size extensions not being synchronized in case of new MD bitmap
+        pages allocated;  also fix those not occuring after previous reductions
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 49311f3da6f2..0795e3c2643f 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -12,3 +12,5 @@ are configurable at compile, boot or run time.
    spectre
    l1tf
    mds
+   tsx_async_abort
+   multihit.rst
diff --git a/Documentation/admin-guide/hw-vuln/multihit.rst b/Documentation/admin-guide/hw-vuln/multihit.rst
new file mode 100644
index 000000000000..ba9988d8bce5
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/multihit.rst
@@ -0,0 +1,163 @@
+iTLB multihit
+=============
+
+iTLB multihit is an erratum where some processors may incur a machine check
+error, possibly resulting in an unrecoverable CPU lockup, when an
+instruction fetch hits multiple entries in the instruction TLB. This can
+occur when the page size is changed along with either the physical address
+or cache type. A malicious guest running on a virtualized system can
+exploit this erratum to perform a denial of service attack.
+
+
+Affected processors
+-------------------
+
+Variations of this erratum are present on most Intel Core and Xeon processor
+models. The erratum is not present on:
+
+   - non-Intel processors
+
+   - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont)
+
+   - Intel processors that have the PSCHANGE_MC_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR.
+
+
+Related CVEs
+------------
+
+The following CVE entry is related to this issue:
+
+   ==============  =================================================
+   CVE-2018-12207  Machine Check Error Avoidance on Page Size Change
+   ==============  =================================================
+
+
+Problem
+-------
+
+Privileged software, including OS and virtual machine managers (VMM), are in
+charge of memory management. A key component in memory management is the control
+of the page tables. Modern processors use virtual memory, a technique that creates
+the illusion of a very large memory for processors. This virtual space is split
+into pages of a given size. Page tables translate virtual addresses to physical
+addresses.
+
+To reduce latency when performing a virtual to physical address translation,
+processors include a structure, called TLB, that caches recent translations.
+There are separate TLBs for instruction (iTLB) and data (dTLB).
+
+Under this errata, instructions are fetched from a linear address translated
+using a 4 KB translation cached in the iTLB. Privileged software modifies the
+paging structure so that the same linear address using large page size (2 MB, 4
+MB, 1 GB) with a different physical address or memory type.  After the page
+structure modification but before the software invalidates any iTLB entries for
+the linear address, a code fetch that happens on the same linear address may
+cause a machine-check error which can result in a system hang or shutdown.
+
+
+Attack scenarios
+----------------
+
+Attacks against the iTLB multihit erratum can be mounted from malicious
+guests in a virtualized system.
+
+
+iTLB multihit system information
+--------------------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current iTLB
+multihit status of the system:whether the system is vulnerable and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/itlb_multihit
+
+The possible values in this file are:
+
+.. list-table::
+
+     * - Not affected
+       - The processor is not vulnerable.
+     * - KVM: Mitigation: Split huge pages
+       - Software changes mitigate this issue.
+     * - KVM: Vulnerable
+       - The processor is vulnerable, but no mitigation enabled
+
+
+Enumeration of the erratum
+--------------------------------
+
+A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr
+and will be set on CPU's which are mitigated against this issue.
+
+   =======================================   ===========   ===============================
+   IA32_ARCH_CAPABILITIES MSR                Not present   Possibly vulnerable,check model
+   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '0'           Likely vulnerable,check model
+   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '1'           Not vulnerable
+   =======================================   ===========   ===============================
+
+
+Mitigation mechanism
+-------------------------
+
+This erratum can be mitigated by restricting the use of large page sizes to
+non-executable pages.  This forces all iTLB entries to be 4K, and removes
+the possibility of multiple hits.
+
+In order to mitigate the vulnerability, KVM initially marks all huge pages
+as non-executable. If the guest attempts to execute in one of those pages,
+the page is broken down into 4K pages, which are then marked executable.
+
+If EPT is disabled or not available on the host, KVM is in control of TLB
+flushes and the problematic situation cannot happen.  However, the shadow
+EPT paging mechanism used by nested virtualization is vulnerable, because
+the nested guest can trigger multiple iTLB hits by modifying its own
+(non-nested) page tables.  For simplicity, KVM will make large pages
+non-executable in all shadow paging modes.
+
+Mitigation control on the kernel command line and KVM - module parameter
+------------------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism for marking huge pages as
+non-executable can be controlled with a module parameter "nx_huge_pages=".
+The kernel command line allows to control the iTLB multihit mitigations at
+boot time with the option "kvm.nx_huge_pages=".
+
+The valid arguments for these options are:
+
+  ==========  ================================================================
+  force       Mitigation is enabled. In this case, the mitigation implements
+              non-executable huge pages in Linux kernel KVM module. All huge
+              pages in the EPT are marked as non-executable.
+              If a guest attempts to execute in one of those pages, the page is
+              broken down into 4K pages, which are then marked executable.
+
+  off	      Mitigation is disabled.
+
+  auto        Enable mitigation only if the platform is affected and the kernel
+              was not booted with the "mitigations=off" command line parameter.
+	      This is the default option.
+  ==========  ================================================================
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The system is protected by the kernel unconditionally and no further
+   action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   If the guest comes from a trusted source, you may assume that the guest will
+   not attempt to maliciously exploit these errata and no further action is
+   required.
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+   If the guest comes from an untrusted source, the guest host kernel will need
+   to apply iTLB multihit mitigation via the kernel command line or kvm
+   module parameter.
diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
new file mode 100644
index 000000000000..fddbd7579c53
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
@@ -0,0 +1,276 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+TAA - TSX Asynchronous Abort
+======================================
+
+TAA is a hardware vulnerability that allows unprivileged speculative access to
+data which is available in various CPU internal buffers by using asynchronous
+aborts within an Intel TSX transactional region.
+
+Affected processors
+-------------------
+
+This vulnerability only affects Intel processors that support Intel
+Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8)
+is 0 in the IA32_ARCH_CAPABILITIES MSR.  On processors where the MDS_NO bit
+(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations
+also mitigate against TAA.
+
+Whether a processor is affected or not can be read out from the TAA
+vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entry is related to this TAA issue:
+
+   ==============  =====  ===================================================
+   CVE-2019-11135  TAA    TSX Asynchronous Abort (TAA) condition on some
+                          microprocessors utilizing speculative execution may
+                          allow an authenticated user to potentially enable
+                          information disclosure via a side channel with
+                          local access.
+   ==============  =====  ===================================================
+
+Problem
+-------
+
+When performing store, load or L1 refill operations, processors write
+data into temporary microarchitectural structures (buffers). The data in
+those buffers can be forwarded to load operations as an optimization.
+
+Intel TSX is an extension to the x86 instruction set architecture that adds
+hardware transactional memory support to improve performance of multi-threaded
+software. TSX lets the processor expose and exploit concurrency hidden in an
+application due to dynamically avoiding unnecessary synchronization.
+
+TSX supports atomic memory transactions that are either committed (success) or
+aborted. During an abort, operations that happened within the transactional region
+are rolled back. An asynchronous abort takes place, among other options, when a
+different thread accesses a cache line that is also used within the transactional
+region when that access might lead to a data race.
+
+Immediately after an uncompleted asynchronous abort, certain speculatively
+executed loads may read data from those internal buffers and pass it to dependent
+operations. This can be then used to infer the value via a cache side channel
+attack.
+
+Because the buffers are potentially shared between Hyper-Threads cross
+Hyper-Thread attacks are possible.
+
+The victim of a malicious actor does not need to make use of TSX. Only the
+attacker needs to begin a TSX transaction and raise an asynchronous abort
+which in turn potenitally leaks data stored in the buffers.
+
+More detailed technical information is available in the TAA specific x86
+architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`.
+
+
+Attack scenarios
+----------------
+
+Attacks against the TAA vulnerability can be implemented from unprivileged
+applications running on hosts or guests.
+
+As for MDS, the attacker has no control over the memory addresses that can
+be leaked. Only the victim is responsible for bringing data to the CPU. As
+a result, the malicious actor has to sample as much data as possible and
+then postprocess it to try to infer any useful information from it.
+
+A potential attacker only has read access to the data. Also, there is no direct
+privilege escalation by using this technique.
+
+
+.. _tsx_async_abort_sys_info:
+
+TAA system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current TAA status
+of mitigated systems. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+
+The possible values in this file are:
+
+.. list-table::
+
+   * - 'Vulnerable'
+     - The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied.
+   * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+     - The system tries to clear the buffers but the microcode might not support the operation.
+   * - 'Mitigation: Clear CPU buffers'
+     - The microcode has been updated to clear the buffers. TSX is still enabled.
+   * - 'Mitigation: TSX disabled'
+     - TSX is disabled.
+   * - 'Not affected'
+     - The CPU is not affected by this issue.
+
+.. _ucode_needed:
+
+Best effort mitigation mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If the processor is vulnerable, but the availability of the microcode-based
+mitigation mechanism is not advertised via CPUID the kernel selects a best
+effort mitigation mode.  This mode invokes the mitigation instructions
+without a guarantee that they clear the CPU buffers.
+
+This is done to address virtualization scenarios where the host has the
+microcode update applied, but the hypervisor is not yet updated to expose the
+CPUID to the guest. If the host has updated microcode the protection takes
+effect; otherwise a few CPU cycles are wasted pointlessly.
+
+The state in the tsx_async_abort sysfs file reflects this situation
+accordingly.
+
+
+Mitigation mechanism
+--------------------
+
+The kernel detects the affected CPUs and the presence of the microcode which is
+required. If a CPU is affected and the microcode is available, then the kernel
+enables the mitigation by default.
+
+
+The mitigation can be controlled at boot time via a kernel command line option.
+See :ref:`taa_mitigation_control_command_line`.
+
+.. _virt_mechanism:
+
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Affected systems where the host has TAA microcode and TAA is mitigated by
+having disabled TSX previously, are not vulnerable regardless of the status
+of the VMs.
+
+In all other cases, if the host either does not have the TAA microcode or
+the kernel is not mitigated, the system might be vulnerable.
+
+
+.. _taa_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the TAA mitigations at boot time with
+the option "tsx_async_abort=". The valid arguments for this option are:
+
+  ============  =============================================================
+  off		This option disables the TAA mitigation on affected platforms.
+                If the system has TSX enabled (see next parameter) and the CPU
+                is affected, the system is vulnerable.
+
+  full	        TAA mitigation is enabled. If TSX is enabled, on an affected
+                system it will clear CPU buffers on ring transitions. On
+                systems which are MDS-affected and deploy MDS mitigation,
+                TAA is also mitigated. Specifying this option on those
+                systems will have no effect.
+
+  full,nosmt    The same as tsx_async_abort=full, with SMT disabled on
+                vulnerable CPUs that have TSX enabled. This is the complete
+                mitigation. When TSX is disabled, SMT is not disabled because
+                CPU is not vulnerable to cross-thread TAA attacks.
+  ============  =============================================================
+
+Not specifying this option is equivalent to "tsx_async_abort=full".
+
+The kernel command line also allows to control the TSX feature using the
+parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used
+to control the TSX feature and the enumeration of the TSX feature bits (RTM
+and HLE) in CPUID.
+
+The valid options are:
+
+  ============  =============================================================
+  off		Disables TSX on the system.
+
+                Note that this option takes effect only on newer CPUs which are
+                not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1
+                and which get the new IA32_TSX_CTRL MSR through a microcode
+                update. This new MSR allows for the reliable deactivation of
+                the TSX functionality.
+
+  on		Enables TSX.
+
+                Although there are mitigations for all known security
+                vulnerabilities, TSX has been known to be an accelerator for
+                several previous speculation-related CVEs, and so there may be
+                unknown security risks associated with leaving it enabled.
+
+  auto		Disables TSX if X86_BUG_TAA is present, otherwise enables TSX
+                on the system.
+  ============  =============================================================
+
+Not specifying this option is equivalent to "tsx=off".
+
+The following combinations of the "tsx_async_abort" and "tsx" are possible. For
+affected platforms tsx=auto is equivalent to tsx=off and the result will be:
+
+  =========  ==========================   =========================================
+  tsx=on     tsx_async_abort=full         The system will use VERW to clear CPU
+                                          buffers. Cross-thread attacks are still
+					  possible on SMT machines.
+  tsx=on     tsx_async_abort=full,nosmt   As above, cross-thread attacks on SMT
+                                          mitigated.
+  tsx=on     tsx_async_abort=off          The system is vulnerable.
+  tsx=off    tsx_async_abort=full         TSX might be disabled if microcode
+                                          provides a TSX control MSR. If so,
+					  system is not vulnerable.
+  tsx=off    tsx_async_abort=full,nosmt   Ditto
+  tsx=off    tsx_async_abort=off          ditto
+  =========  ==========================   =========================================
+
+
+For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU
+buffers.  For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0)
+"tsx" command line argument has no effect.
+
+For the affected platforms below table indicates the mitigation status for the
+combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO
+and TSX_CTRL_MSR.
+
+  =======  =========  =============  ========================================
+  MDS_NO   MD_CLEAR   TSX_CTRL_MSR   Status
+  =======  =========  =============  ========================================
+    0          0            0        Vulnerable (needs microcode)
+    0          1            0        MDS and TAA mitigated via VERW
+    1          1            0        MDS fixed, TAA vulnerable if TSX enabled
+                                     because MD_CLEAR has no meaning and
+                                     VERW is not guaranteed to clear buffers
+    1          X            1        MDS fixed, TAA can be mitigated by
+                                     VERW or TSX_CTRL_MSR
+  =======  =========  =============  ========================================
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If all user space applications are from a trusted source and do not execute
+untrusted code which is supplied externally, then the mitigation can be
+disabled. The same applies to virtualized environments with trusted guests.
+
+
+2. Untrusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If there are untrusted applications or guests on the system, enabling TSX
+might allow a malicious actor to leak data from the host or from other
+processes running on the same physical core.
+
+If the microcode is available and the TSX is disabled on the host, attacks
+are prevented in a virtualized environment as well, even if the VMs do not
+explicitly enable the mitigation.
+
+
+.. _taa_default_mitigations:
+
+Default mitigations
+-------------------
+
+The kernel's default action for vulnerable processors is:
+
+  - Deploy TSX disable mitigation (tsx_async_abort=full tsx=off).
diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst
index 5d63b18bd6d1..4f0462af3ca7 100644
--- a/Documentation/admin-guide/iostats.rst
+++ b/Documentation/admin-guide/iostats.rst
@@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding
     This is the total number of milliseconds spent by all discards (as
     measured from __make_request() to end_that_request_last()).
 
+Field 16 -- # of flush requests completed
+    This is the total number of flush requests completed successfully.
+
+    Block layer combines flush requests and executes at most one at a time.
+    This counts flush requests executed by disk. Not tracked for partitions.
+
+Field 17 -- # of milliseconds spent flushing
+    This is the total number of milliseconds spent by all flush requests.
+
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
 introduced when changes collide, so (for instance) adding up all the
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a84a83f8881e..8dee8f68fe15 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2055,6 +2055,25 @@
 			KVM MMU at runtime.
 			Default is 0 (off)
 
+	kvm.nx_huge_pages=
+			[KVM] Controls the software workaround for the
+			X86_BUG_ITLB_MULTIHIT bug.
+			force	: Always deploy workaround.
+			off	: Never deploy workaround.
+			auto    : Deploy workaround based on the presence of
+				  X86_BUG_ITLB_MULTIHIT.
+
+			Default is 'auto'.
+
+			If the software workaround is enabled for the host,
+			guests do need not to enable it for nested guests.
+
+	kvm.nx_huge_pages_recovery_ratio=
+			[KVM] Controls how many 4KiB pages are periodically zapped
+			back to huge pages.  0 disables the recovery, otherwise if
+			the value is N KVM will zap 1/Nth of the 4KiB pages every
+			minute.  The default is 60.
+
 	kvm-amd.nested=	[KVM,AMD] Allow nested virtualization in KVM/SVM.
 			Default is 1 (enabled)
 
@@ -2636,6 +2655,13 @@
 					       ssbd=force-off [ARM64]
 					       l1tf=off [X86]
 					       mds=off [X86]
+					       tsx_async_abort=off [X86]
+					       kvm.nx_huge_pages=off [X86]
+
+				Exceptions:
+					       This does not have any effect on
+					       kvm.nx_huge_pages when
+					       kvm.nx_huge_pages=force.
 
 			auto (default)
 				Mitigate all CPU vulnerabilities, but leave SMT
@@ -2651,6 +2677,7 @@
 				be fully mitigated, even if it means losing SMT.
 				Equivalent to: l1tf=flush,nosmt [X86]
 					       mds=full,nosmt [X86]
+					       tsx_async_abort=full,nosmt [X86]
 
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@@ -4848,6 +4875,71 @@
 			interruptions from clocksource watchdog are not
 			acceptable).
 
+	tsx=		[X86] Control Transactional Synchronization
+			Extensions (TSX) feature in Intel processors that
+			support TSX control.
+
+			This parameter controls the TSX feature. The options are:
+
+			on	- Enable TSX on the system. Although there are
+				mitigations for all known security vulnerabilities,
+				TSX has been known to be an accelerator for
+				several previous speculation-related CVEs, and
+				so there may be unknown	security risks associated
+				with leaving it enabled.
+
+			off	- Disable TSX on the system. (Note that this
+				option takes effect only on newer CPUs which are
+				not vulnerable to MDS, i.e., have
+				MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
+				the new IA32_TSX_CTRL MSR through a microcode
+				update. This new MSR allows for the reliable
+				deactivation of the TSX functionality.)
+
+			auto	- Disable TSX if X86_BUG_TAA is present,
+				  otherwise enable TSX on the system.
+
+			Not specifying this option is equivalent to tsx=off.
+
+			See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
+			for more details.
+
+	tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
+			Abort (TAA) vulnerability.
+
+			Similar to Micro-architectural Data Sampling (MDS)
+			certain CPUs that support Transactional
+			Synchronization Extensions (TSX) are vulnerable to an
+			exploit against CPU internal buffers which can forward
+			information to a disclosure gadget under certain
+			conditions.
+
+			In vulnerable processors, the speculatively forwarded
+			data can be used in a cache side channel attack, to
+			access data to which the attacker does not have direct
+			access.
+
+			This parameter controls the TAA mitigation.  The
+			options are:
+
+			full       - Enable TAA mitigation on vulnerable CPUs
+				     if TSX is enabled.
+
+			full,nosmt - Enable TAA mitigation and disable SMT on
+				     vulnerable CPUs. If TSX is disabled, SMT
+				     is not disabled because CPU is not
+				     vulnerable to cross-thread TAA attacks.
+			off        - Unconditionally disable TAA mitigation
+
+			Not specifying this option is equivalent to
+			tsx_async_abort=full.  On CPUs which are MDS affected
+			and deploy MDS mitigation, TAA mitigation is not
+			required and doesn't provide any additional
+			mitigation.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
+
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
 			Format:
diff --git a/Documentation/admin-guide/perf/imx-ddr.rst b/Documentation/admin-guide/perf/imx-ddr.rst
index 517a205abad6..90056e4e8859 100644
--- a/Documentation/admin-guide/perf/imx-ddr.rst
+++ b/Documentation/admin-guide/perf/imx-ddr.rst
@@ -17,7 +17,8 @@ The "format" directory describes format of the config (event ID) and config1
 (AXI filtering) fields of the perf_event_attr structure, see /sys/bus/event_source/
 devices/imx8_ddr0/format/. The "events" directory describes the events types
 hardware supported that can be used with perf tool, see /sys/bus/event_source/
-devices/imx8_ddr0/events/.
+devices/imx8_ddr0/events/. The "caps" directory describes filter features implemented
+in DDR PMU, see /sys/bus/events_source/devices/imx8_ddr0/caps/.
   e.g.::
         perf stat -a -e imx8_ddr0/cycles/ cmd
         perf stat -a -e imx8_ddr0/read/,imx8_ddr0/write/ cmd
@@ -25,9 +26,12 @@ devices/imx8_ddr0/events/.
 AXI filtering is only used by CSV modes 0x41 (axid-read) and 0x42 (axid-write)
 to count reading or writing matches filter setting. Filter setting is various
 from different DRAM controller implementations, which is distinguished by quirks
-in the driver.
+in the driver. You also can dump info from userspace, filter in "caps" directory
+indicates whether PMU supports AXI ID filter or not; enhanced_filter indicates
+whether PMU supports enhanced AXI ID filter or not. Value 0 for un-supported, and
+value 1 for supported.
 
-* With DDR_CAP_AXI_ID_FILTER quirk.
+* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0).
   Filter is defined with two configuration parts:
   --AXI_ID defines AxID matching value.
   --AXI_MASKING defines which bits of AxID are meaningful for the matching.
@@ -50,3 +54,8 @@ in the driver.
   axi_id to monitor a specific id, rather than having to specify axi_mask.
   e.g.::
         perf stat -a -e imx8_ddr0/axid-read,axi_id=0x12/ cmd, which will monitor ARID=0x12
+
+* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1).
+  This is an extension to the DDR_CAP_AXI_ID_FILTER quirk which permits
+  counting the number of bytes (as opposed to the number of bursts) from DDR
+  read and write transactions concurrently with another set of data counters.
diff --git a/Documentation/admin-guide/perf/thunderx2-pmu.rst b/Documentation/admin-guide/perf/thunderx2-pmu.rst
index 08e33675853a..01f158238ae1 100644
--- a/Documentation/admin-guide/perf/thunderx2-pmu.rst
+++ b/Documentation/admin-guide/perf/thunderx2-pmu.rst
@@ -3,24 +3,26 @@ Cavium ThunderX2 SoC Performance Monitoring Unit (PMU UNCORE)
 =============================================================
 
 The ThunderX2 SoC PMU consists of independent, system-wide, per-socket
-PMUs such as the Level 3 Cache (L3C) and DDR4 Memory Controller (DMC).
+PMUs such as the Level 3 Cache (L3C), DDR4 Memory Controller (DMC) and
+Cavium Coherent Processor Interconnect (CCPI2).
 
 The DMC has 8 interleaved channels and the L3C has 16 interleaved tiles.
 Events are counted for the default channel (i.e. channel 0) and prorated
 to the total number of channels/tiles.
 
-The DMC and L3C support up to 4 counters. Counters are independently
-programmable and can be started and stopped individually. Each counter
-can be set to a different event. Counters are 32-bit and do not support
-an overflow interrupt; they are read every 2 seconds.
+The DMC and L3C support up to 4 counters, while the CCPI2 supports up to 8
+counters. Counters are independently programmable to different events and
+can be started and stopped individually. None of the counters support an
+overflow interrupt. DMC and L3C counters are 32-bit and read every 2 seconds.
+The CCPI2 counters are 64-bit and assumed not to overflow in normal operation.
 
 PMU UNCORE (perf) driver:
 
 The thunderx2_pmu driver registers per-socket perf PMUs for the DMC and
-L3C devices.  Each PMU can be used to count up to 4 events
-simultaneously. The PMUs provide a description of their available events
-and configuration options under sysfs, see
-/sys/devices/uncore_<l3c_S/dmc_S/>; S is the socket id.
+L3C devices.  Each PMU can be used to count up to 4 (DMC/L3C) or up to 8
+(CCPI2) events simultaneously. The PMUs provide a description of their
+available events and configuration options under sysfs, see
+/sys/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
 
 The driver does not support sampling, therefore "perf record" will not
 work. Per-task perf sessions are also not supported.
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst
index d3f3a60fbf25..5d78a6f5b0ae 100644
--- a/Documentation/arm64/booting.rst
+++ b/Documentation/arm64/booting.rst
@@ -213,6 +213,9 @@ Before jumping into the kernel, the following conditions must be met:
 
       - ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
       - ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1.
+      - ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across
+        all CPUs the kernel is executing on, and must stay constant
+        for the lifetime of the kernel.
 
   - If the kernel is entered at EL1:
 
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 2955287e9acc..b6e44884e3ad 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -168,8 +168,15 @@ infrastructure:
      +------------------------------+---------+---------+
 
 
-  3) MIDR_EL1 - Main ID Register
+  3) ID_AA64PFR1_EL1 - Processor Feature Register 1
+     +------------------------------+---------+---------+
+     | Name                         |  bits   | visible |
+     +------------------------------+---------+---------+
+     | SSBS                         | [7-4]   |    y    |
+     +------------------------------+---------+---------+
 
+
+  4) MIDR_EL1 - Main ID Register
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
@@ -188,11 +195,15 @@ infrastructure:
    as available on the CPU where it is fetched and is not a system
    wide safe value.
 
-  4) ID_AA64ISAR1_EL1 - Instruction set attribute register 1
+  5) ID_AA64ISAR1_EL1 - Instruction set attribute register 1
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
+     | SB                           | [39-36] |    y    |
+     +------------------------------+---------+---------+
+     | FRINTTS                      | [35-32] |    y    |
+     +------------------------------+---------+---------+
      | GPI                          | [31-28] |    y    |
      +------------------------------+---------+---------+
      | GPA                          | [27-24] |    y    |
@@ -210,7 +221,7 @@ infrastructure:
      | DPB                          | [3-0]   |    y    |
      +------------------------------+---------+---------+
 
-  5) ID_AA64MMFR2_EL1 - Memory model feature register 2
+  6) ID_AA64MMFR2_EL1 - Memory model feature register 2
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
@@ -218,7 +229,7 @@ infrastructure:
      | AT                           | [35-32] |    y    |
      +------------------------------+---------+---------+
 
-  6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+  7) ID_AA64ZFR0_EL1 - SVE feature ID register 0
 
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 91f79529c58c..7fa3d215ae6a 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -119,10 +119,6 @@ HWCAP_LRCPC
 HWCAP_DCPOP
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
 
-HWCAP2_DCPODP
-
-    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
-
 HWCAP_SHA3
     Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
 
@@ -141,30 +137,6 @@ HWCAP_SHA512
 HWCAP_SVE
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
 
-HWCAP2_SVE2
-
-    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
-
-HWCAP2_SVEAES
-
-    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
-
-HWCAP2_SVEPMULL
-
-    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
-
-HWCAP2_SVEBITPERM
-
-    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
-
-HWCAP2_SVESHA3
-
-    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
-
-HWCAP2_SVESM4
-
-    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
-
 HWCAP_ASIMDFHM
    Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
 
@@ -180,13 +152,12 @@ HWCAP_ILRCPC
 HWCAP_FLAGM
     Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001.
 
-HWCAP2_FLAGM2
-
-    Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010.
-
 HWCAP_SSBS
     Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010.
 
+HWCAP_SB
+    Functionality implied by ID_AA64ISAR1_EL1.SB == 0b0001.
+
 HWCAP_PACA
     Functionality implied by ID_AA64ISAR1_EL1.APA == 0b0001 or
     ID_AA64ISAR1_EL1.API == 0b0001, as described by
@@ -197,6 +168,38 @@ HWCAP_PACG
     ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
     Documentation/arm64/pointer-authentication.rst.
 
+HWCAP2_DCPODP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
+HWCAP2_SVE2
+
+    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
+HWCAP2_FLAGM2
+
+    Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010.
+
 HWCAP2_FRINT
 
     Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001.
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 17ea3fecddaa..99b2545455ff 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -70,8 +70,12 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220        |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A57      | #1319537        | ARM64_ERRATUM_1319367       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A72      | #853709         | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A72      | #1319367        | ARM64_ERRATUM_1319367       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A73      | #858921         | ARM64_ERRATUM_858921        |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A55      | #1024718        | ARM64_ERRATUM_1024718       |
@@ -88,9 +92,16 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
++----------------+-----------------+-----------------+-----------------------------+
+| Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_843419        |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX ITS    | #22375,24313    | CAVIUM_ERRATUM_22375        |
 +----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144        |
@@ -107,6 +118,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX2 SMMUv3| #126            | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| Cavium         | ThunderX2 Core  | #219            | CAVIUM_TX2_ERRATUM_219      |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
@@ -124,7 +137,7 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 +----------------+-----------------+-----------------+-----------------------------+
-| Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
+| Qualcomm Tech. | Kryo/Falkor v1  | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 +----------------+-----------------+-----------------+-----------------------------+
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst
index 9c07bc22b0bc..77311335c08b 100644
--- a/Documentation/block/stat.rst
+++ b/Documentation/block/stat.rst
@@ -41,6 +41,8 @@ discard I/Os    requests      number of discard I/Os processed
 discard merges  requests      number of discard I/Os merged with in-queue I/O
 discard sectors sectors       number of sectors discarded
 discard ticks   milliseconds  total wait time for discard requests
+flush I/Os      requests      number of flush I/Os processed
+flush ticks     milliseconds  total wait time for flush requests
 =============== ============= =================================================
 
 read I/Os, write I/Os, discard I/0s
@@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s
 
 These values increment when an I/O request completes.
 
+flush I/Os
+==========
+
+These values increment when an flush I/O request completes.
+
+Block layer combines flush requests and executes at most one at a time.
+This counts flush requests executed by disk. Not tracked for partitions.
+
 read merges, write merges, discard merges
 =========================================
 
@@ -62,8 +72,8 @@ discarded from this block device.  The "sectors" in question are the
 standard UNIX 512-byte sectors, not any device- or filesystem-specific
 block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks, discard ticks
-======================================
+read ticks, write ticks, discard ticks, flush ticks
+===================================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst
index b0522a4dd107..09dee10d2592 100644
--- a/Documentation/dev-tools/index.rst
+++ b/Documentation/dev-tools/index.rst
@@ -24,6 +24,7 @@ whole; patches welcome!
    gdb-kernel-debugging
    kgdb
    kselftest
+   kunit/index
 
 
 .. only::  subproject and html
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index b72d07d70239..525296121d89 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster.
 Both KASAN modes work with both SLUB and SLAB memory allocators.
 For better bug detection and nicer reporting, enable CONFIG_STACKTRACE.
 
+To augment reports with last allocation and freeing stack of the physical page,
+it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on.
+
 To disable instrumentation for specific files or directories, add a line
 similar to the following to the respective kernel Makefile:
 
diff --git a/Documentation/dev-tools/kunit/api/index.rst b/Documentation/dev-tools/kunit/api/index.rst
new file mode 100644
index 000000000000..9b9bffe5d41a
--- /dev/null
+++ b/Documentation/dev-tools/kunit/api/index.rst
@@ -0,0 +1,16 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+API Reference
+=============
+.. toctree::
+
+	test
+
+This section documents the KUnit kernel testing API. It is divided into the
+following sections:
+
+================================= ==============================================
+:doc:`test`                       documents all of the standard testing API
+                                  excluding mocking or mocking related features.
+================================= ==============================================
diff --git a/Documentation/dev-tools/kunit/api/test.rst b/Documentation/dev-tools/kunit/api/test.rst
new file mode 100644
index 000000000000..aaa97f17e5b3
--- /dev/null
+++ b/Documentation/dev-tools/kunit/api/test.rst
@@ -0,0 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========
+Test API
+========
+
+This file documents all of the standard testing API excluding mocking or mocking
+related features.
+
+.. kernel-doc:: include/kunit/test.h
+   :internal:
diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst
new file mode 100644
index 000000000000..bf2095112d89
--- /dev/null
+++ b/Documentation/dev-tools/kunit/faq.rst
@@ -0,0 +1,62 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+Frequently Asked Questions
+==========================
+
+How is this different from Autotest, kselftest, etc?
+====================================================
+KUnit is a unit testing framework. Autotest, kselftest (and some others) are
+not.
+
+A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is supposed to
+test a single unit of code in isolation, hence the name. A unit test should be
+the finest granularity of testing and as such should allow all possible code
+paths to be tested in the code under test; this is only possible if the code
+under test is very small and does not have any external dependencies outside of
+the test's control like hardware.
+
+There are no testing frameworks currently available for the kernel that do not
+require installing the kernel on a test machine or in a VM and all require
+tests to be written in userspace and run on the kernel under test; this is true
+for Autotest, kselftest, and some others, disqualifying any of them from being
+considered unit testing frameworks.
+
+Does KUnit support running on architectures other than UML?
+===========================================================
+
+Yes, well, mostly.
+
+For the most part, the KUnit core framework (what you use to write the tests)
+can compile to any architecture; it compiles like just another part of the
+kernel and runs when the kernel boots. However, there is some infrastructure,
+like the KUnit Wrapper (``tools/testing/kunit/kunit.py``) that does not support
+other architectures.
+
+In short, this means that, yes, you can run KUnit on other architectures, but
+it might require more work than using KUnit on UML.
+
+For more information, see :ref:`kunit-on-non-uml`.
+
+What is the difference between a unit test and these other kinds of tests?
+==========================================================================
+Most existing tests for the Linux kernel would be categorized as an integration
+test, or an end-to-end test.
+
+- A unit test is supposed to test a single unit of code in isolation, hence the
+  name. A unit test should be the finest granularity of testing and as such
+  should allow all possible code paths to be tested in the code under test; this
+  is only possible if the code under test is very small and does not have any
+  external dependencies outside of the test's control like hardware.
+- An integration test tests the interaction between a minimal set of components,
+  usually just two or three. For example, someone might write an integration
+  test to test the interaction between a driver and a piece of hardware, or to
+  test the interaction between the userspace libraries the kernel provides and
+  the kernel itself; however, one of these tests would probably not test the
+  entire kernel along with hardware interactions and interactions with the
+  userspace.
+- An end-to-end test usually tests the entire system from the perspective of the
+  code under test. For example, someone might write an end-to-end test for the
+  kernel by installing a production configuration of the kernel on production
+  hardware with a production userspace and then trying to exercise some behavior
+  that depends on interactions between the hardware, the kernel, and userspace.
diff --git a/Documentation/dev-tools/kunit/index.rst b/Documentation/dev-tools/kunit/index.rst
new file mode 100644
index 000000000000..26ffb46bdf99
--- /dev/null
+++ b/Documentation/dev-tools/kunit/index.rst
@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+KUnit - Unit Testing for the Linux Kernel
+=========================================
+
+.. toctree::
+	:maxdepth: 2
+
+	start
+	usage
+	api/index
+	faq
+
+What is KUnit?
+==============
+
+KUnit is a lightweight unit testing and mocking framework for the Linux kernel.
+These tests are able to be run locally on a developer's workstation without a VM
+or special hardware.
+
+KUnit is heavily inspired by JUnit, Python's unittest.mock, and
+Googletest/Googlemock for C++. KUnit provides facilities for defining unit test
+cases, grouping related test cases into test suites, providing common
+infrastructure for running tests, and much more.
+
+Get started now: :doc:`start`
+
+Why KUnit?
+==========
+
+A unit test is supposed to test a single unit of code in isolation, hence the
+name. A unit test should be the finest granularity of testing and as such should
+allow all possible code paths to be tested in the code under test; this is only
+possible if the code under test is very small and does not have any external
+dependencies outside of the test's control like hardware.
+
+Outside of KUnit, there are no testing frameworks currently
+available for the kernel that do not require installing the kernel on a test
+machine or in a VM and all require tests to be written in userspace running on
+the kernel; this is true for Autotest, and kselftest, disqualifying
+any of them from being considered unit testing frameworks.
+
+KUnit addresses the problem of being able to run tests without needing a virtual
+machine or actual hardware with User Mode Linux. User Mode Linux is a Linux
+architecture, like ARM or x86; however, unlike other architectures it compiles
+to a standalone program that can be run like any other program directly inside
+of a host operating system; to be clear, it does not require any virtualization
+support; it is just a regular program.
+
+KUnit is fast. Excluding build time, from invocation to completion KUnit can run
+several dozen tests in only 10 to 20 seconds; this might not sound like a big
+deal to some people, but having such fast and easy to run tests fundamentally
+changes the way you go about testing and even writing code in the first place.
+Linus himself said in his `git talk at Google
+<https://gist.github.com/lorn/1272686/revisions#diff-53c65572127855f1b003db4064a94573R874>`_:
+
+	"... a lot of people seem to think that performance is about doing the
+	same thing, just doing it faster, and that is not true. That is not what
+	performance is all about. If you can do something really fast, really
+	well, people will start using it differently."
+
+In this context Linus was talking about branching and merging,
+but this point also applies to testing. If your tests are slow, unreliable, are
+difficult to write, and require a special setup or special hardware to run,
+then you wait a lot longer to write tests, and you wait a lot longer to run
+tests; this means that tests are likely to break, unlikely to test a lot of
+things, and are unlikely to be rerun once they pass. If your tests are really
+fast, you run them all the time, every time you make a change, and every time
+someone sends you some code. Why trust that someone ran all their tests
+correctly on every change when you can just run them yourself in less time than
+it takes to read their test log?
+
+How do I use it?
+================
+
+*   :doc:`start` - for new users of KUnit
+*   :doc:`usage` - for a more detailed explanation of KUnit features
+*   :doc:`api/index` - for the list of KUnit APIs used for testing
diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst
new file mode 100644
index 000000000000..aeeddfafeea2
--- /dev/null
+++ b/Documentation/dev-tools/kunit/start.rst
@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Getting Started
+===============
+
+Installing dependencies
+=======================
+KUnit has the same dependencies as the Linux kernel. As long as you can build
+the kernel, you can run KUnit.
+
+KUnit Wrapper
+=============
+Included with KUnit is a simple Python wrapper that helps format the output to
+easily use and read KUnit output. It handles building and running the kernel, as
+well as formatting the output.
+
+The wrapper can be run with:
+
+.. code-block:: bash
+
+   ./tools/testing/kunit/kunit.py run
+
+Creating a kunitconfig
+======================
+The Python script is a thin wrapper around Kbuild as such, it needs to be
+configured with a ``kunitconfig`` file. This file essentially contains the
+regular Kernel config, with the specific test targets as well.
+
+.. code-block:: bash
+
+	git clone -b master https://kunit.googlesource.com/kunitconfig $PATH_TO_KUNITCONFIG_REPO
+	cd $PATH_TO_LINUX_REPO
+	ln -s $PATH_TO_KUNIT_CONFIG_REPO/kunitconfig kunitconfig
+
+You may want to add kunitconfig to your local gitignore.
+
+Verifying KUnit Works
+---------------------
+
+To make sure that everything is set up correctly, simply invoke the Python
+wrapper from your kernel repo:
+
+.. code-block:: bash
+
+	./tools/testing/kunit/kunit.py run
+
+.. note::
+   You may want to run ``make mrproper`` first.
+
+If everything worked correctly, you should see the following:
+
+.. code-block:: bash
+
+	Generating .config ...
+	Building KUnit Kernel ...
+	Starting KUnit Kernel ...
+
+followed by a list of tests that are run. All of them should be passing.
+
+.. note::
+   Because it is building a lot of sources for the first time, the ``Building
+   kunit kernel`` step may take a while.
+
+Writing your first test
+=======================
+
+In your kernel repo let's add some code that we can test. Create a file
+``drivers/misc/example.h`` with the contents:
+
+.. code-block:: c
+
+	int misc_example_add(int left, int right);
+
+create a file ``drivers/misc/example.c``:
+
+.. code-block:: c
+
+	#include <linux/errno.h>
+
+	#include "example.h"
+
+	int misc_example_add(int left, int right)
+	{
+		return left + right;
+	}
+
+Now add the following lines to ``drivers/misc/Kconfig``:
+
+.. code-block:: kconfig
+
+	config MISC_EXAMPLE
+		bool "My example"
+
+and the following lines to ``drivers/misc/Makefile``:
+
+.. code-block:: make
+
+	obj-$(CONFIG_MISC_EXAMPLE) += example.o
+
+Now we are ready to write the test. The test will be in
+``drivers/misc/example-test.c``:
+
+.. code-block:: c
+
+	#include <kunit/test.h>
+	#include "example.h"
+
+	/* Define the test cases. */
+
+	static void misc_example_add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, misc_example_add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, misc_example_add(1, 1));
+		KUNIT_EXPECT_EQ(test, 0, misc_example_add(-1, 1));
+		KUNIT_EXPECT_EQ(test, INT_MAX, misc_example_add(0, INT_MAX));
+		KUNIT_EXPECT_EQ(test, -1, misc_example_add(INT_MAX, INT_MIN));
+	}
+
+	static void misc_example_test_failure(struct kunit *test)
+	{
+		KUNIT_FAIL(test, "This test never passes.");
+	}
+
+	static struct kunit_case misc_example_test_cases[] = {
+		KUNIT_CASE(misc_example_add_test_basic),
+		KUNIT_CASE(misc_example_test_failure),
+		{}
+	};
+
+	static struct kunit_suite misc_example_test_suite = {
+		.name = "misc-example",
+		.test_cases = misc_example_test_cases,
+	};
+	kunit_test_suite(misc_example_test_suite);
+
+Now add the following to ``drivers/misc/Kconfig``:
+
+.. code-block:: kconfig
+
+	config MISC_EXAMPLE_TEST
+		bool "Test for my example"
+		depends on MISC_EXAMPLE && KUNIT
+
+and the following to ``drivers/misc/Makefile``:
+
+.. code-block:: make
+
+	obj-$(CONFIG_MISC_EXAMPLE_TEST) += example-test.o
+
+Now add it to your ``kunitconfig``:
+
+.. code-block:: none
+
+	CONFIG_MISC_EXAMPLE=y
+	CONFIG_MISC_EXAMPLE_TEST=y
+
+Now you can run the test:
+
+.. code-block:: bash
+
+	./tools/testing/kunit/kunit.py
+
+You should see the following failure:
+
+.. code-block:: none
+
+	...
+	[16:08:57] [PASSED] misc-example:misc_example_add_test_basic
+	[16:08:57] [FAILED] misc-example:misc_example_test_failure
+	[16:08:57] EXPECTATION FAILED at drivers/misc/example-test.c:17
+	[16:08:57] 	This test never passes.
+	...
+
+Congrats! You just wrote your first KUnit test!
+
+Next Steps
+==========
+*   Check out the :doc:`usage` page for a more
+    in-depth explanation of KUnit.
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
new file mode 100644
index 000000000000..c6e69634e274
--- /dev/null
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -0,0 +1,576 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========
+Using KUnit
+===========
+
+The purpose of this document is to describe what KUnit is, how it works, how it
+is intended to be used, and all the concepts and terminology that are needed to
+understand it. This guide assumes a working knowledge of the Linux kernel and
+some basic knowledge of testing.
+
+For a high level introduction to KUnit, including setting up KUnit for your
+project, see :doc:`start`.
+
+Organization of this document
+=============================
+
+This document is organized into two main sections: Testing and Isolating
+Behavior. The first covers what a unit test is and how to use KUnit to write
+them. The second covers how to use KUnit to isolate code and make it possible
+to unit test code that was otherwise un-unit-testable.
+
+Testing
+=======
+
+What is KUnit?
+--------------
+
+"K" is short for "kernel" so "KUnit" is the "(Linux) Kernel Unit Testing
+Framework." KUnit is intended first and foremost for writing unit tests; it is
+general enough that it can be used to write integration tests; however, this is
+a secondary goal. KUnit has no ambition of being the only testing framework for
+the kernel; for example, it does not intend to be an end-to-end testing
+framework.
+
+What is Unit Testing?
+---------------------
+
+A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is a test that
+tests code at the smallest possible scope, a *unit* of code. In the C
+programming language that's a function.
+
+Unit tests should be written for all the publicly exposed functions in a
+compilation unit; so that is all the functions that are exported in either a
+*class* (defined below) or all functions which are **not** static.
+
+Writing Tests
+-------------
+
+Test Cases
+~~~~~~~~~~
+
+The fundamental unit in KUnit is the test case. A test case is a function with
+the signature ``void (*)(struct kunit *test)``. It calls a function to be tested
+and then sets *expectations* for what should happen. For example:
+
+.. code-block:: c
+
+	void example_test_success(struct kunit *test)
+	{
+	}
+
+	void example_test_failure(struct kunit *test)
+	{
+		KUNIT_FAIL(test, "This test never passes.");
+	}
+
+In the above example ``example_test_success`` always passes because it does
+nothing; no expectations are set, so all expectations pass. On the other hand
+``example_test_failure`` always fails because it calls ``KUNIT_FAIL``, which is
+a special expectation that logs a message and causes the test case to fail.
+
+Expectations
+~~~~~~~~~~~~
+An *expectation* is a way to specify that you expect a piece of code to do
+something in a test. An expectation is called like a function. A test is made
+by setting expectations about the behavior of a piece of code under test; when
+one or more of the expectations fail, the test case fails and information about
+the failure is logged. For example:
+
+.. code-block:: c
+
+	void add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, add(1, 1));
+	}
+
+In the above example ``add_test_basic`` makes a number of assertions about the
+behavior of a function called ``add``; the first parameter is always of type
+``struct kunit *``, which contains information about the current test context;
+the second parameter, in this case, is what the value is expected to be; the
+last value is what the value actually is. If ``add`` passes all of these
+expectations, the test case, ``add_test_basic`` will pass; if any one of these
+expectations fail, the test case will fail.
+
+It is important to understand that a test case *fails* when any expectation is
+violated; however, the test will continue running, potentially trying other
+expectations until the test case ends or is otherwise terminated. This is as
+opposed to *assertions* which are discussed later.
+
+To learn about more expectations supported by KUnit, see :doc:`api/test`.
+
+.. note::
+   A single test case should be pretty short, pretty easy to understand,
+   focused on a single behavior.
+
+For example, if we wanted to properly test the add function above, we would
+create additional tests cases which would each test a different property that an
+add function should have like this:
+
+.. code-block:: c
+
+	void add_test_basic(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 1, add(1, 0));
+		KUNIT_EXPECT_EQ(test, 2, add(1, 1));
+	}
+
+	void add_test_negative(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, 0, add(-1, 1));
+	}
+
+	void add_test_max(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, INT_MAX, add(0, INT_MAX));
+		KUNIT_EXPECT_EQ(test, -1, add(INT_MAX, INT_MIN));
+	}
+
+	void add_test_overflow(struct kunit *test)
+	{
+		KUNIT_EXPECT_EQ(test, INT_MIN, add(INT_MAX, 1));
+	}
+
+Notice how it is immediately obvious what all the properties that we are testing
+for are.
+
+Assertions
+~~~~~~~~~~
+
+KUnit also has the concept of an *assertion*. An assertion is just like an
+expectation except the assertion immediately terminates the test case if it is
+not satisfied.
+
+For example:
+
+.. code-block:: c
+
+	static void mock_test_do_expect_default_return(struct kunit *test)
+	{
+		struct mock_test_context *ctx = test->priv;
+		struct mock *mock = ctx->mock;
+		int param0 = 5, param1 = -5;
+		const char *two_param_types[] = {"int", "int"};
+		const void *two_params[] = {&param0, &param1};
+		const void *ret;
+
+		ret = mock->do_expect(mock,
+				      "test_printk", test_printk,
+				      two_param_types, two_params,
+				      ARRAY_SIZE(two_params));
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ret);
+		KUNIT_EXPECT_EQ(test, -4, *((int *) ret));
+	}
+
+In this example, the method under test should return a pointer to a value, so
+if the pointer returned by the method is null or an errno, we don't want to
+bother continuing the test since the following expectation could crash the test
+case. `ASSERT_NOT_ERR_OR_NULL(...)` allows us to bail out of the test case if
+the appropriate conditions have not been satisfied to complete the test.
+
+Test Suites
+~~~~~~~~~~~
+
+Now obviously one unit test isn't very helpful; the power comes from having
+many test cases covering all of your behaviors. Consequently it is common to
+have many *similar* tests; in order to reduce duplication in these closely
+related tests most unit testing frameworks provide the concept of a *test
+suite*, in KUnit we call it a *test suite*; all it is is just a collection of
+test cases for a unit of code with a set up function that gets invoked before
+every test cases and then a tear down function that gets invoked after every
+test case completes.
+
+Example:
+
+.. code-block:: c
+
+	static struct kunit_case example_test_cases[] = {
+		KUNIT_CASE(example_test_foo),
+		KUNIT_CASE(example_test_bar),
+		KUNIT_CASE(example_test_baz),
+		{}
+	};
+
+	static struct kunit_suite example_test_suite = {
+		.name = "example",
+		.init = example_test_init,
+		.exit = example_test_exit,
+		.test_cases = example_test_cases,
+	};
+	kunit_test_suite(example_test_suite);
+
+In the above example the test suite, ``example_test_suite``, would run the test
+cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``,
+each would have ``example_test_init`` called immediately before it and would
+have ``example_test_exit`` called immediately after it.
+``kunit_test_suite(example_test_suite)`` registers the test suite with the
+KUnit test framework.
+
+.. note::
+   A test case will only be run if it is associated with a test suite.
+
+For a more information on these types of things see the :doc:`api/test`.
+
+Isolating Behavior
+==================
+
+The most important aspect of unit testing that other forms of testing do not
+provide is the ability to limit the amount of code under test to a single unit.
+In practice, this is only possible by being able to control what code gets run
+when the unit under test calls a function and this is usually accomplished
+through some sort of indirection where a function is exposed as part of an API
+such that the definition of that function can be changed without affecting the
+rest of the code base. In the kernel this primarily comes from two constructs,
+classes, structs that contain function pointers that are provided by the
+implementer, and architecture specific functions which have definitions selected
+at compile time.
+
+Classes
+-------
+
+Classes are not a construct that is built into the C programming language;
+however, it is an easily derived concept. Accordingly, pretty much every project
+that does not use a standardized object oriented library (like GNOME's GObject)
+has their own slightly different way of doing object oriented programming; the
+Linux kernel is no exception.
+
+The central concept in kernel object oriented programming is the class. In the
+kernel, a *class* is a struct that contains function pointers. This creates a
+contract between *implementers* and *users* since it forces them to use the
+same function signature without having to call the function directly. In order
+for it to truly be a class, the function pointers must specify that a pointer
+to the class, known as a *class handle*, be one of the parameters; this makes
+it possible for the member functions (also known as *methods*) to have access
+to member variables (more commonly known as *fields*) allowing the same
+implementation to have multiple *instances*.
+
+Typically a class can be *overridden* by *child classes* by embedding the
+*parent class* in the child class. Then when a method provided by the child
+class is called, the child implementation knows that the pointer passed to it is
+of a parent contained within the child; because of this, the child can compute
+the pointer to itself because the pointer to the parent is always a fixed offset
+from the pointer to the child; this offset is the offset of the parent contained
+in the child struct. For example:
+
+.. code-block:: c
+
+	struct shape {
+		int (*area)(struct shape *this);
+	};
+
+	struct rectangle {
+		struct shape parent;
+		int length;
+		int width;
+	};
+
+	int rectangle_area(struct shape *this)
+	{
+		struct rectangle *self = container_of(this, struct shape, parent);
+
+		return self->length * self->width;
+	};
+
+	void rectangle_new(struct rectangle *self, int length, int width)
+	{
+		self->parent.area = rectangle_area;
+		self->length = length;
+		self->width = width;
+	}
+
+In this example (as in most kernel code) the operation of computing the pointer
+to the child from the pointer to the parent is done by ``container_of``.
+
+Faking Classes
+~~~~~~~~~~~~~~
+
+In order to unit test a piece of code that calls a method in a class, the
+behavior of the method must be controllable, otherwise the test ceases to be a
+unit test and becomes an integration test.
+
+A fake just provides an implementation of a piece of code that is different than
+what runs in a production instance, but behaves identically from the standpoint
+of the callers; this is usually done to replace a dependency that is hard to
+deal with, or is slow.
+
+A good example for this might be implementing a fake EEPROM that just stores the
+"contents" in an internal buffer. For example, let's assume we have a class that
+represents an EEPROM:
+
+.. code-block:: c
+
+	struct eeprom {
+		ssize_t (*read)(struct eeprom *this, size_t offset, char *buffer, size_t count);
+		ssize_t (*write)(struct eeprom *this, size_t offset, const char *buffer, size_t count);
+	};
+
+And we want to test some code that buffers writes to the EEPROM:
+
+.. code-block:: c
+
+	struct eeprom_buffer {
+		ssize_t (*write)(struct eeprom_buffer *this, const char *buffer, size_t count);
+		int flush(struct eeprom_buffer *this);
+		size_t flush_count; /* Flushes when buffer exceeds flush_count. */
+	};
+
+	struct eeprom_buffer *new_eeprom_buffer(struct eeprom *eeprom);
+	void destroy_eeprom_buffer(struct eeprom *eeprom);
+
+We can easily test this code by *faking out* the underlying EEPROM:
+
+.. code-block:: c
+
+	struct fake_eeprom {
+		struct eeprom parent;
+		char contents[FAKE_EEPROM_CONTENTS_SIZE];
+	};
+
+	ssize_t fake_eeprom_read(struct eeprom *parent, size_t offset, char *buffer, size_t count)
+	{
+		struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent);
+
+		count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset);
+		memcpy(buffer, this->contents + offset, count);
+
+		return count;
+	}
+
+	ssize_t fake_eeprom_write(struct eeprom *this, size_t offset, const char *buffer, size_t count)
+	{
+		struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent);
+
+		count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset);
+		memcpy(this->contents + offset, buffer, count);
+
+		return count;
+	}
+
+	void fake_eeprom_init(struct fake_eeprom *this)
+	{
+		this->parent.read = fake_eeprom_read;
+		this->parent.write = fake_eeprom_write;
+		memset(this->contents, 0, FAKE_EEPROM_CONTENTS_SIZE);
+	}
+
+We can now use it to test ``struct eeprom_buffer``:
+
+.. code-block:: c
+
+	struct eeprom_buffer_test {
+		struct fake_eeprom *fake_eeprom;
+		struct eeprom_buffer *eeprom_buffer;
+	};
+
+	static void eeprom_buffer_test_does_not_write_until_flush(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff};
+
+		eeprom_buffer->flush_count = SIZE_MAX;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0);
+
+		eeprom_buffer->flush(eeprom_buffer);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+	}
+
+	static void eeprom_buffer_test_flushes_after_flush_count_met(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff};
+
+		eeprom_buffer->flush_count = 2;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+	}
+
+	static void eeprom_buffer_test_flushes_increments_of_flush_count(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+		struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer;
+		struct fake_eeprom *fake_eeprom = ctx->fake_eeprom;
+		char buffer[] = {0xff, 0xff};
+
+		eeprom_buffer->flush_count = 2;
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 1);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0);
+
+		eeprom_buffer->write(eeprom_buffer, buffer, 2);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff);
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff);
+		/* Should have only flushed the first two bytes. */
+		KUNIT_EXPECT_EQ(test, fake_eeprom->contents[2], 0);
+	}
+
+	static int eeprom_buffer_test_init(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx;
+
+		ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
+		ctx->fake_eeprom = kunit_kzalloc(test, sizeof(*ctx->fake_eeprom), GFP_KERNEL);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->fake_eeprom);
+		fake_eeprom_init(ctx->fake_eeprom);
+
+		ctx->eeprom_buffer = new_eeprom_buffer(&ctx->fake_eeprom->parent);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->eeprom_buffer);
+
+		test->priv = ctx;
+
+		return 0;
+	}
+
+	static void eeprom_buffer_test_exit(struct kunit *test)
+	{
+		struct eeprom_buffer_test *ctx = test->priv;
+
+		destroy_eeprom_buffer(ctx->eeprom_buffer);
+	}
+
+.. _kunit-on-non-uml:
+
+KUnit on non-UML architectures
+==============================
+
+By default KUnit uses UML as a way to provide dependencies for code under test.
+Under most circumstances KUnit's usage of UML should be treated as an
+implementation detail of how KUnit works under the hood. Nevertheless, there
+are instances where being able to run architecture specific code, or test
+against real hardware is desirable. For these reasons KUnit supports running on
+other architectures.
+
+Running existing KUnit tests on non-UML architectures
+-----------------------------------------------------
+
+There are some special considerations when running existing KUnit tests on
+non-UML architectures:
+
+*   Hardware may not be deterministic, so a test that always passes or fails
+    when run under UML may not always do so on real hardware.
+*   Hardware and VM environments may not be hermetic. KUnit tries its best to
+    provide a hermetic environment to run tests; however, it cannot manage state
+    that it doesn't know about outside of the kernel. Consequently, tests that
+    may be hermetic on UML may not be hermetic on other architectures.
+*   Some features and tooling may not be supported outside of UML.
+*   Hardware and VMs are slower than UML.
+
+None of these are reasons not to run your KUnit tests on real hardware; they are
+only things to be aware of when doing so.
+
+The biggest impediment will likely be that certain KUnit features and
+infrastructure may not support your target environment. For example, at this
+time the KUnit Wrapper (``tools/testing/kunit/kunit.py``) does not work outside
+of UML. Unfortunately, there is no way around this. Using UML (or even just a
+particular architecture) allows us to make a lot of assumptions that make it
+possible to do things which might otherwise be impossible.
+
+Nevertheless, all core KUnit framework features are fully supported on all
+architectures, and using them is straightforward: all you need to do is to take
+your kunitconfig, your Kconfig options for the tests you would like to run, and
+merge them into whatever config your are using for your platform. That's it!
+
+For example, let's say you have the following kunitconfig:
+
+.. code-block:: none
+
+	CONFIG_KUNIT=y
+	CONFIG_KUNIT_EXAMPLE_TEST=y
+
+If you wanted to run this test on an x86 VM, you might add the following config
+options to your ``.config``:
+
+.. code-block:: none
+
+	CONFIG_KUNIT=y
+	CONFIG_KUNIT_EXAMPLE_TEST=y
+	CONFIG_SERIAL_8250=y
+	CONFIG_SERIAL_8250_CONSOLE=y
+
+All these new options do is enable support for a common serial console needed
+for logging.
+
+Next, you could build a kernel with these tests as follows:
+
+
+.. code-block:: bash
+
+	make ARCH=x86 olddefconfig
+	make ARCH=x86
+
+Once you have built a kernel, you could run it on QEMU as follows:
+
+.. code-block:: bash
+
+	qemu-system-x86_64 -enable-kvm \
+			   -m 1024 \
+			   -kernel arch/x86_64/boot/bzImage \
+			   -append 'console=ttyS0' \
+			   --nographic
+
+Interspersed in the kernel logs you might see the following:
+
+.. code-block:: none
+
+	TAP version 14
+		# Subtest: example
+		1..1
+		# example_simple_test: initializing
+		ok 1 - example_simple_test
+	ok 1 - example
+
+Congratulations, you just ran a KUnit test on the x86 architecture!
+
+Writing new tests for other architectures
+-----------------------------------------
+
+The first thing you must do is ask yourself whether it is necessary to write a
+KUnit test for a specific architecture, and then whether it is necessary to
+write that test for a particular piece of hardware. In general, writing a test
+that depends on having access to a particular piece of hardware or software (not
+included in the Linux source repo) should be avoided at all costs.
+
+Even if you only ever plan on running your KUnit test on your hardware
+configuration, other people may want to run your tests and may not have access
+to your hardware. If you write your test to run on UML, then anyone can run your
+tests without knowing anything about your particular setup, and you can still
+run your tests on your hardware setup just by compiling for your architecture.
+
+.. important::
+   Always prefer tests that run on UML to tests that only run under a particular
+   architecture, and always prefer tests that run under QEMU or another easy
+   (and monitarily free) to obtain software environment to a specific piece of
+   hardware.
+
+Nevertheless, there are still valid reasons to write an architecture or hardware
+specific test: for example, you might want to test some code that really belongs
+in ``arch/some-arch/*``. Even so, try your best to write the test so that it
+does not depend on physical hardware: if some of your test cases don't need the
+hardware, only require the hardware for tests that actually need it.
+
+Now that you have narrowed down exactly what bits are hardware specific, the
+actual procedure for writing and running the tests is pretty much the same as
+writing normal KUnit tests. One special caveat is that you have to reset
+hardware state in between test cases; if this is not possible, you may only be
+able to run one test case per invocation.
+
+.. TODO(brendanhiggins@google.com): Add an actual example of an architecture
+   dependent KUnit test.
diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml
index c82c5e57d44c..9c7e70335ac0 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip.yaml
@@ -496,12 +496,12 @@ properties:
 
       - description: Theobroma Systems RK3368-uQ7 with Haikou baseboard
         items:
-          - const: tsd,rk3368-uq7-haikou
+          - const: tsd,rk3368-lion-haikou
           - const: rockchip,rk3368
 
       - description: Theobroma Systems RK3399-Q7 with Haikou baseboard
         items:
-          - const: tsd,rk3399-q7-haikou
+          - const: tsd,rk3399-puma-haikou
           - const: rockchip,rk3399
 
       - description: Tronsmart Orion R68 Meta
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index f4c5d34c4111..7079d44bf3ba 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -1,8 +1,11 @@
 * Advanced Interrupt Controller (AIC)
 
 Required properties:
-- compatible: Should be "atmel,<chip>-aic"
-  <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
+- compatible: Should be:
+    - "atmel,<chip>-aic" where  <chip> can be "at91rm9200", "sama5d2",
+      "sama5d3" or "sama5d4"
+    - "microchip,<chip>-aic" where <chip> can be "sam9x60"
+
 - interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
   The first cell is the IRQ number (aka "Peripheral IDentifier" on datasheet).
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
index 27f38eed389e..d3e423fcb6c2 100644
--- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/arm/allwinner,sun4i-a10-csi.yaml#
+$id: http://devicetree.org/schemas/media/allwinner,sun4i-a10-csi.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Allwinner A10 CMOS Sensor Interface (CSI) Device Tree Bindings
@@ -27,14 +27,12 @@ properties:
   clocks:
     items:
       - description: The CSI interface clock
-      - description: The CSI module clock
       - description: The CSI ISP clock
       - description: The CSI DRAM clock
 
   clock-names:
     items:
       - const: bus
-      - const: mod
       - const: isp
       - const: ram
 
@@ -89,9 +87,8 @@ examples:
         compatible = "allwinner,sun7i-a20-csi0";
         reg = <0x01c09000 0x1000>;
         interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-        clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>,
-                 <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
-        clock-names = "bus", "mod", "isp", "ram";
+        clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
+        clock-names = "bus", "isp", "ram";
         resets = <&ccu RST_CSI0>;
 
         port {
diff --git a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
new file mode 100644
index 000000000000..f3893c4d3c6a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
@@ -0,0 +1,53 @@
+* Cadence NAND controller
+
+Required properties:
+  - compatible : "cdns,hp-nfc"
+  - reg : Contains two entries, each of which is a tuple consisting of a
+	  physical address and length. The first entry is the address and
+	  length of the controller register set. The second entry is the
+	  address and length of the Slave DMA data port.
+  - reg-names: should contain "reg" and "sdma"
+  - #address-cells: should be 1. The cell encodes the chip select connection.
+  - #size-cells : should be 0.
+  - interrupts : The interrupt number.
+  - clocks: phandle of the controller core clock (nf_clk).
+
+Optional properties:
+  - dmas: shall reference DMA channel associated to the NAND controller
+  - cdns,board-delay-ps : Estimated Board delay. The value includes the total
+    round trip delay for the signals and is used for deciding on values
+    associated with data read capture. The example formula for SDR mode is
+    the following:
+    board delay = RE#PAD delay + PCB trace to device + PCB trace from device
+    + DQ PAD delay
+
+Child nodes represent the available NAND chips.
+
+Required properties of NAND chips:
+  - reg: shall contain the native Chip Select ids from 0 to max supported by
+    the cadence nand flash controller
+
+See Documentation/devicetree/bindings/mtd/nand.txt for more details on
+generic bindings.
+
+Example:
+
+nand_controller: nand-controller@60000000 {
+	  compatible = "cdns,hp-nfc";
+	  #address-cells = <1>;
+	  #size-cells = <0>;
+	  reg = <0x60000000 0x10000>, <0x80000000 0x10000>;
+	  reg-names = "reg", "sdma";
+	  clocks = <&nf_clk>;
+	  cdns,board-delay-ps = <4830>;
+	  interrupts = <2 0>;
+	  nand@0 {
+	      reg = <0>;
+	      label = "nand-1";
+	  };
+	  nand@1 {
+	      reg = <1>;
+	      label = "nand-2";
+	  };
+
+};
diff --git a/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt
new file mode 100644
index 000000000000..4bdcb92ae381
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt
@@ -0,0 +1,22 @@
+Flash device on Intel IXP4xx SoC
+
+This flash is regular CFI compatible (Intel or AMD extended) flash chips with
+specific big-endian or mixed-endian memory access pattern.
+
+Required properties:
+- compatible : must be "intel,ixp4xx-flash", "cfi-flash";
+- reg : memory address for the flash chip
+- bank-width : width in bytes of flash interface, should be <2>
+
+For the rest of the properties, see mtd-physmap.txt.
+
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
+Example:
+
+flash@50000000 {
+	compatible = "intel,ixp4xx-flash", "cfi-flash";
+	reg = <0x50000000 0x01000000>;
+	bank-width = <2>;
+};
diff --git a/Documentation/devicetree/bindings/perf/arm-ccn.txt b/Documentation/devicetree/bindings/perf/arm-ccn.txt
index 43b5a71a5a9d..1c53b5aa3317 100644
--- a/Documentation/devicetree/bindings/perf/arm-ccn.txt
+++ b/Documentation/devicetree/bindings/perf/arm-ccn.txt
@@ -6,6 +6,7 @@ Required properties:
 	"arm,ccn-502"
 	"arm,ccn-504"
 	"arm,ccn-508"
+	"arm,ccn-512"
 
 - reg: (standard registers property) physical address and size
 	(16MB) of the configuration registers block
diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
index d77e3f26f9e6..7822a806ea0a 100644
--- a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
+++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
@@ -5,6 +5,7 @@ Required properties:
 - compatible: should be one of:
 	"fsl,imx8-ddr-pmu"
 	"fsl,imx8m-ddr-pmu"
+	"fsl,imx8mp-ddr-pmu"
 
 - reg: physical address and size
 
diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
index f83d888176cc..064b7dfc4252 100644
--- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
@@ -33,13 +33,13 @@ patternProperties:
           allOf:
             - $ref: "/schemas/types.yaml#/definitions/string"
             - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15,
-              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI,
-              ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1,
-              GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2,
-              GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12,
-              I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7,
-              I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC,
-              LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2,
+              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC,
+              ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0,
+              GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1,
+              GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11,
+              I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6,
+              I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ,
+              LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2,
               MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2,
               NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3,
               NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1,
@@ -48,47 +48,45 @@ patternProperties:
               PWM8, PWM9, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3,
               RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10, SALT11, SALT12,
               SALT13, SALT14, SALT15, SALT16, SALT2, SALT3, SALT4, SALT5,
-              SALT6, SALT7, SALT8, SALT9, SD1, SD2, SD3, SD3DAT4, SD3DAT5,
-              SD3DAT6, SD3DAT7, SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO,
-              SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1,
-              SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11,
-              TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, TACH4, TACH5,
-              TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, THRU3, TXD1,
-              TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, UART6, UART7,
-              UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3,
-              WDTRST4, ]
+              SALT6, SALT7, SALT8, SALT9, SD1, SD2, SGPM1, SGPS1, SIOONCTRL,
+              SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1,
+              SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1,
+              TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3,
+              TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2,
+              THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13,
+              UART6, UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2,
+              WDTRST3, WDTRST4, ]
         groups:
           allOf:
             - $ref: "/schemas/types.yaml#/definitions/string"
             - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15,
-              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI,
-              ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, GPIT0,
-              GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1,
-              GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1,
-              I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3,
-              I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6,
-              JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ,
-              MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3,
-              MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4,
-              NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1,
-              NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, OSCCLK, PEWAKE,
-              PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, PWM12G0, PWM12G1,
-              PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, PWM15G1, PWM2, PWM3,
-              PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, PWM9G0, PWM9G1, QSPI1,
-              QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3,
-              RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10G0, SALT10G1,
-              SALT11G0, SALT11G1, SALT12G0, SALT12G1, SALT13G0, SALT13G1,
-              SALT14G0, SALT14G1, SALT15G0, SALT15G1, SALT16G0, SALT16G1,
-              SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, SALT8, SALT9G0,
-              SALT9G1, SD1, SD2, SD3, SD3DAT4, SD3DAT5, SD3DAT6, SD3DAT7,
-              SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD,
-              SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, SPI1WP, SPI2,
-              SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, TACH12, TACH13,
-              TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, TACH6, TACH7, TACH8,
-              TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, TXD2, TXD3, TXD4,
-              UART10, UART11, UART12G0, UART12G1, UART13G0, UART13G1, UART6,
-              UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3,
-              WDTRST4, ]
+              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1,
+              EMMCG4, EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID,
+              FWQSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5,
+              GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6,
+              GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14,
+              I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9,
+              I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD,
+              LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4,
+              MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1,
+              NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2,
+              NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4,
+              OSCCLK, PEWAKE, PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1,
+              PWM12G0, PWM12G1, PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0,
+              PWM15G1, PWM2, PWM3, PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1,
+              PWM9G0, PWM9G1, QSPI1, QSPI2, RGMII1, RGMII2, RGMII3, RGMII4,
+              RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1,
+              SALT10G0, SALT10G1, SALT11G0, SALT11G1, SALT12G0, SALT12G1,
+              SALT13G0, SALT13G1, SALT14G0, SALT14G1, SALT15G0, SALT15G1,
+              SALT16G0, SALT16G1, SALT2, SALT3, SALT4, SALT5, SALT6, SALT7,
+              SALT8, SALT9G0, SALT9G1, SD1, SD2, SD3, SGPM1, SGPS1, SIOONCTRL,
+              SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1,
+              SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1,
+              TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3,
+              TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2,
+              THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12G0,
+              UART12G1, UART13G0, UART13G1, UART6, UART7, UART8, UART9, VB,
+              VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, WDTRST4, ]
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
index a78150c47aa2..f32416968197 100644
--- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
@@ -30,8 +30,8 @@ if:
 properties:
   compatible:
     enum:
-      - const: regulator-fixed
-      - const: regulator-fixed-clock
+      - regulator-fixed
+      - regulator-fixed-clock
 
   regulator-name: true
 
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index b261a3015f84..04819ad379c2 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -24,15 +24,17 @@ description: |
 
 properties:
   compatible:
-    items:
-      - enum:
-          - sifive,rocket0
-          - sifive,e5
-          - sifive,e51
-          - sifive,u54-mc
-          - sifive,u54
-          - sifive,u5
-      - const: riscv
+    oneOf:
+      - items:
+          - enum:
+              - sifive,rocket0
+              - sifive,e5
+              - sifive,e51
+              - sifive,u54-mc
+              - sifive,u54
+              - sifive,u5
+          - const: riscv
+      - const: riscv    # Simulator only
     description:
       Identifies that the hart uses the RISC-V instruction set
       and identifies the type of the hart.
@@ -66,12 +68,8 @@ properties:
       insensitive, letters in the riscv,isa string must be all
       lowercase to simplify parsing.
 
-  timebase-frequency:
-    type: integer
-    minimum: 1
-    description:
-      Specifies the clock frequency of the system timer in Hz.
-      This value is common to all harts on a single system image.
+  # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here
+  timebase-frequency: false
 
   interrupt-controller:
     type: object
@@ -93,7 +91,6 @@ properties:
 
 required:
   - riscv,isa
-  - timebase-frequency
   - interrupt-controller
 
 examples:
diff --git a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
new file mode 100644
index 000000000000..cd69c2efdd37
--- /dev/null
+++ b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt
@@ -0,0 +1,19 @@
+* H1 Secure Microcontroller with Cr50 Firmware on SPI Bus.
+
+H1 Secure Microcontroller running Cr50 firmware provides several
+functions, including TPM-like functionality. It communicates over
+SPI using the FIFO protocol described in the PTP Spec, section 6.
+
+Required properties:
+- compatible: Should be "google,cr50".
+- spi-max-frequency: Maximum SPI frequency.
+
+Example:
+
+&spi0 {
+	tpm@0 {
+		compatible = "google,cr50";
+		reg = <0>;
+		spi-max-frequency = <800000>;
+	};
+};
diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst
index 70e180e6b93d..207f0d24de69 100644
--- a/Documentation/driver-api/libata.rst
+++ b/Documentation/driver-api/libata.rst
@@ -250,23 +250,23 @@ High-level taskfile hooks
 
 ::
 
-    void (*qc_prep) (struct ata_queued_cmd *qc);
+    enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc);
     int (*qc_issue) (struct ata_queued_cmd *qc);
 
 
-Higher-level hooks, these two hooks can potentially supercede several of
+Higher-level hooks, these two hooks can potentially supersede several of
 the above taskfile/DMA engine hooks. ``->qc_prep`` is called after the
 buffers have been DMA-mapped, and is typically used to populate the
-hardware's DMA scatter-gather table. Most drivers use the standard
-:c:func:`ata_qc_prep` helper function, but more advanced drivers roll their
-own.
+hardware's DMA scatter-gather table. Some drivers use the standard
+:c:func:`ata_bmdma_qc_prep` and :c:func:`ata_bmdma_dumb_qc_prep` helper
+functions, but more advanced drivers roll their own.
 
 ``->qc_issue`` is used to make a command active, once the hardware and S/G
 tables have been prepared. IDE BMDMA drivers use the helper function
-:c:func:`ata_qc_issue_prot` for taskfile protocol-based dispatch. More
+:c:func:`ata_sff_qc_issue` for taskfile protocol-based dispatch. More
 advanced drivers implement their own ``->qc_issue``.
 
-:c:func:`ata_qc_issue_prot` calls ``->tf_load()``, ``->bmdma_setup()``, and
+:c:func:`ata_sff_qc_issue` calls ``->sff_tf_load()``, ``->bmdma_setup()``, and
 ``->bmdma_start()`` as necessary to initiate a transfer.
 
 Exception and probe handling (EH)
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 8a0700af9596..471a511c7508 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -256,13 +256,8 @@ alternative master keys or to support rotating master keys.  Instead,
 the master keys may be wrapped in userspace, e.g. as is done by the
 `fscrypt <https://github.com/google/fscrypt>`_ tool.
 
-Including the inode number in the IVs was considered.  However, it was
-rejected as it would have prevented ext4 filesystems from being
-resized, and by itself still wouldn't have been sufficient to prevent
-the same key from being directly reused for both XTS and CTS-CBC.
-
-DIRECT_KEY and per-mode keys
-----------------------------
+DIRECT_KEY policies
+-------------------
 
 The Adiantum encryption mode (see `Encryption modes and usage`_) is
 suitable for both contents and filenames encryption, and it accepts
@@ -285,6 +280,21 @@ IV.  Moreover:
   key derived using the KDF.  Users may use the same master key for
   other v2 encryption policies.
 
+IV_INO_LBLK_64 policies
+-----------------------
+
+When FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 is set in the fscrypt policy,
+the encryption keys are derived from the master key, encryption mode
+number, and filesystem UUID.  This normally results in all files
+protected by the same master key sharing a single contents encryption
+key and a single filenames encryption key.  To still encrypt different
+files' data differently, inode numbers are included in the IVs.
+Consequently, shrinking the filesystem may not be allowed.
+
+This format is optimized for use with inline encryption hardware
+compliant with the UFS or eMMC standards, which support only 64 IV
+bits per I/O request and may have only a small number of keyslots.
+
 Key identifiers
 ---------------
 
@@ -308,8 +318,9 @@ If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair.
 
 AES-128-CBC was added only for low-powered embedded devices with
 crypto accelerators such as CAAM or CESA that do not support XTS.  To
-use AES-128-CBC, CONFIG_CRYPTO_SHA256 (or another SHA-256
-implementation) must be enabled so that ESSIV can be used.
+use AES-128-CBC, CONFIG_CRYPTO_ESSIV and CONFIG_CRYPTO_SHA256 (or
+another SHA-256 implementation) must be enabled so that ESSIV can be
+used.
 
 Adiantum is a (primarily) stream cipher-based mode that is fast even
 on CPUs without dedicated crypto instructions.  It's also a true
@@ -341,10 +352,16 @@ a little endian number, except that:
   is encrypted with AES-256 where the AES-256 key is the SHA-256 hash
   of the file's data encryption key.
 
-- In the "direct key" configuration (FSCRYPT_POLICY_FLAG_DIRECT_KEY
-  set in the fscrypt_policy), the file's nonce is also appended to the
-  IV.  Currently this is only allowed with the Adiantum encryption
-  mode.
+- With `DIRECT_KEY policies`_, the file's nonce is appended to the IV.
+  Currently this is only allowed with the Adiantum encryption mode.
+
+- With `IV_INO_LBLK_64 policies`_, the logical block number is limited
+  to 32 bits and is placed in bits 0-31 of the IV.  The inode number
+  (which is also limited to 32 bits) is placed in bits 32-63.
+
+Note that because file logical block numbers are included in the IVs,
+filesystems must enforce that blocks are never shifted around within
+encrypted files, e.g. via "collapse range" or "insert range".
 
 Filenames encryption
 --------------------
@@ -354,10 +371,10 @@ the requirements to retain support for efficient directory lookups and
 filenames of up to 255 bytes, the same IV is used for every filename
 in a directory.
 
-However, each encrypted directory still uses a unique key; or
-alternatively (for the "direct key" configuration) has the file's
-nonce included in the IVs.  Thus, IV reuse is limited to within a
-single directory.
+However, each encrypted directory still uses a unique key, or
+alternatively has the file's nonce (for `DIRECT_KEY policies`_) or
+inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs.
+Thus, IV reuse is limited to within a single directory.
 
 With CTS-CBC, the IV reuse means that when the plaintext filenames
 share a common prefix at least as long as the cipher block size (16
@@ -431,12 +448,15 @@ This structure must be initialized as follows:
   (1) for ``contents_encryption_mode`` and FSCRYPT_MODE_AES_256_CTS
   (4) for ``filenames_encryption_mode``.
 
-- ``flags`` must contain a value from ``<linux/fscrypt.h>`` which
-  identifies the amount of NUL-padding to use when encrypting
-  filenames.  If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3).
-  Additionally, if the encryption modes are both
-  FSCRYPT_MODE_ADIANTUM, this can contain
-  FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_.
+- ``flags`` contains optional flags from ``<linux/fscrypt.h>``:
+
+  - FSCRYPT_POLICY_FLAGS_PAD_*: The amount of NUL padding to use when
+    encrypting filenames.  If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32
+    (0x3).
+  - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_.
+  - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64
+    policies`_.  This is mutually exclusive with DIRECT_KEY and is not
+    supported on v1 policies.
 
 - For v2 encryption policies, ``__reserved`` must be zeroed.
 
@@ -1089,7 +1109,7 @@ policy structs (see `Setting an encryption policy`_), except that the
 context structs also contain a nonce.  The nonce is randomly generated
 by the kernel and is used as KDF input or as a tweak to cause
 different files to be encrypted differently; see `Per-file keys`_ and
-`DIRECT_KEY and per-mode keys`_.
+`DIRECT_KEY policies`_.
 
 Data path changes
 -----------------
diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst
index 42a0b6dd9e0b..a95536b6443c 100644
--- a/Documentation/filesystems/fsverity.rst
+++ b/Documentation/filesystems/fsverity.rst
@@ -226,6 +226,14 @@ To do so, check for FS_VERITY_FL (0x00100000) in the returned flags.
 The verity flag is not settable via FS_IOC_SETFLAGS.  You must use
 FS_IOC_ENABLE_VERITY instead, since parameters must be provided.
 
+statx
+-----
+
+Since Linux v5.5, the statx() system call sets STATX_ATTR_VERITY if
+the file has fs-verity enabled.  This can perform better than
+FS_IOC_GETFLAGS and FS_IOC_MEASURE_VERITY because it doesn't require
+opening the file, and opening verity files can be expensive.
+
 Accessing verity files
 ======================
 
@@ -398,7 +406,7 @@ pages have been read into the pagecache.  (See `Verifying data`_.)
 ext4
 ----
 
-ext4 supports fs-verity since Linux TODO and e2fsprogs v1.45.2.
+ext4 supports fs-verity since Linux v5.4 and e2fsprogs v1.45.2.
 
 To create verity files on an ext4 filesystem, the filesystem must have
 been formatted with ``-O verity`` or had ``tune2fs -O verity`` run on
@@ -434,7 +442,7 @@ also only supports extent-based files.
 f2fs
 ----
 
-f2fs supports fs-verity since Linux TODO and f2fs-tools v1.11.0.
+f2fs supports fs-verity since Linux v5.4 and f2fs-tools v1.11.0.
 
 To create verity files on an f2fs filesystem, the filesystem must have
 been formatted with ``-O verity``.
diff --git a/Documentation/ioctl/ioctl-number.rst b/Documentation/ioctl/ioctl-number.rst
index bef79cd4c6b4..4ef86433bd67 100644
--- a/Documentation/ioctl/ioctl-number.rst
+++ b/Documentation/ioctl/ioctl-number.rst
@@ -233,6 +233,7 @@ Code  Seq#    Include File                                           Comments
 'f'   00-0F  fs/ext4/ext4.h                                          conflict!
 'f'   00-0F  linux/fs.h                                              conflict!
 'f'   00-0F  fs/ocfs2/ocfs2_fs.h                                     conflict!
+'f'   13-27  linux/fscrypt.h
 'f'   81-8F  linux/fsverity.h
 'g'   00-0F  linux/usb/gadgetfs.h
 'g'   20-2F  linux/usb/g_printer.h
diff --git a/Documentation/networking/device_drivers/intel/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst
index 2b9f4887beda..caf023cc88de 100644
--- a/Documentation/networking/device_drivers/intel/e100.rst
+++ b/Documentation/networking/device_drivers/intel/e100.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==============================================================
-Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
-==============================================================
+=============================================================
+Linux Base Driver for the Intel(R) PRO/100 Family of Adapters
+=============================================================
 
 June 1, 2018
 
@@ -21,7 +21,7 @@ Contents
 In This Release
 ===============
 
-This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of
+This file describes the Linux Base Driver for the Intel(R) PRO/100 Family of
 Adapters. This driver includes support for Itanium(R)2-based systems.
 
 For questions related to hardware requirements, refer to the documentation
@@ -138,9 +138,9 @@ version 1.6 or later is required for this functionality.
 The latest release of ethtool can be found from
 https://www.kernel.org/pub/software/network/ethtool/
 
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is provided through the ethtool* utility.  For instructions on
+Enabling Wake on LAN (WoL)
+--------------------------
+WoL is provided through the ethtool utility.  For instructions on
 enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
 enabled on the system during the next shut down or reboot.  For this
 driver version, in order to enable WoL, the e100 driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst
index 956560b6e745..4aaae0f7d6ba 100644
--- a/Documentation/networking/device_drivers/intel/e1000.rst
+++ b/Documentation/networking/device_drivers/intel/e1000.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===========================================================
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
+==========================================================
+Linux Base Driver for Intel(R) Ethernet Network Connection
+==========================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 1999 - 2013 Intel Corporation.
@@ -438,10 +438,10 @@ ethtool
   The latest release of ethtool can be found from
   https://www.kernel.org/pub/software/network/ethtool/
 
-Enabling Wake on LAN* (WoL)
----------------------------
+Enabling Wake on LAN (WoL)
+--------------------------
 
-  WoL is configured through the ethtool* utility.
+  WoL is configured through the ethtool utility.
 
   WoL will be enabled on the system during the next shut down or reboot.
   For this driver version, in order to enable WoL, the e1000 driver must be
diff --git a/Documentation/networking/device_drivers/intel/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst
index 01999f05509c..f49cd370e7bf 100644
--- a/Documentation/networking/device_drivers/intel/e1000e.rst
+++ b/Documentation/networking/device_drivers/intel/e1000e.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-======================================================
-Linux* Driver for Intel(R) Ethernet Network Connection
-======================================================
+=====================================================
+Linux Driver for Intel(R) Ethernet Network Connection
+=====================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 2008-2018 Intel Corporation.
@@ -338,7 +338,7 @@ and higher cannot be forced. Use the autonegotiation advertising setting to
 manually set devices for 1 Gbps and higher.
 
 Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
+ethtool utility.
 
 Caution: Only experienced network administrators should force speed and duplex
 or change autonegotiation advertising manually. The settings at the switch must
@@ -351,9 +351,9 @@ will not attempt to auto-negotiate with its link partner since those adapters
 operate only in full duplex and only at their native speed.
 
 
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
+Enabling Wake on LAN (WoL)
+--------------------------
+WoL is configured through the ethtool utility.
 
 WoL will be enabled on the system during the next shut down or reboot. For
 this driver version, in order to enable WoL, the e1000e driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst
index ac3269e34f55..4d279e64e221 100644
--- a/Documentation/networking/device_drivers/intel/fm10k.rst
+++ b/Documentation/networking/device_drivers/intel/fm10k.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==============================================================
-Linux* Base Driver for Intel(R) Ethernet Multi-host Controller
-==============================================================
+=============================================================
+Linux Base Driver for Intel(R) Ethernet Multi-host Controller
+=============================================================
 
 August 20, 2018
 Copyright(c) 2015-2018 Intel Corporation.
@@ -120,8 +120,8 @@ rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r
 Known Issues/Troubleshooting
 ============================
 
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS under Linux KVM
----------------------------------------------------------------------------------------
+Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS under Linux KVM
+-------------------------------------------------------------------------------------
 KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This
 includes traditional PCIe devices, as well as SR-IOV-capable devices based on
 the Intel Ethernet Controller XL710.
diff --git a/Documentation/networking/device_drivers/intel/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst
index 848fd388fa6e..8a9b18573688 100644
--- a/Documentation/networking/device_drivers/intel/i40e.rst
+++ b/Documentation/networking/device_drivers/intel/i40e.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==================================================================
-Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series
-==================================================================
+=================================================================
+Linux Base Driver for the Intel(R) Ethernet Controller 700 Series
+=================================================================
 
 Intel 40 Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -384,7 +384,7 @@ NOTE: You cannot set the speed for devices based on the Intel(R) Ethernet
 Network Adapter XXV710 based devices.
 
 Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
+ethtool utility.
 
 Caution: Only experienced network administrators should force speed and duplex
 or change autonegotiation advertising manually. The settings at the switch must
diff --git a/Documentation/networking/device_drivers/intel/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst
index cfc08842e32c..84ac7e75f363 100644
--- a/Documentation/networking/device_drivers/intel/iavf.rst
+++ b/Documentation/networking/device_drivers/intel/iavf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==================================================================
-Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function
-==================================================================
+=================================================================
+Linux Base Driver for Intel(R) Ethernet Adaptive Virtual Function
+=================================================================
 
 Intel Ethernet Adaptive Virtual Function Linux driver.
 Copyright(c) 2013-2018 Intel Corporation.
@@ -19,7 +19,7 @@ Contents
 Overview
 ========
 
-This file describes the iavf Linux* Base Driver. This driver was formerly
+This file describes the iavf Linux Base Driver. This driver was formerly
 called i40evf.
 
 The iavf driver supports the below mentioned virtual function devices and
diff --git a/Documentation/networking/device_drivers/intel/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst
index c220aa2711c6..ee43ea57d443 100644
--- a/Documentation/networking/device_drivers/intel/ice.rst
+++ b/Documentation/networking/device_drivers/intel/ice.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===================================================================
-Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series
-===================================================================
+==================================================================
+Linux Base Driver for the Intel(R) Ethernet Connection E800 Series
+==================================================================
 
 Intel ice Linux driver.
 Copyright(c) 2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst
index fc8cfaa5dcfa..87e560fe5eaa 100644
--- a/Documentation/networking/device_drivers/intel/igb.rst
+++ b/Documentation/networking/device_drivers/intel/igb.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===========================================================
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
+==========================================================
+Linux Base Driver for Intel(R) Ethernet Network Connection
+==========================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -129,9 +129,9 @@ version is required for this functionality. Download it at:
 https://www.kernel.org/pub/software/network/ethtool/
 
 
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
+Enabling Wake on LAN (WoL)
+--------------------------
+WoL is configured through the ethtool utility.
 
 WoL will be enabled on the system during the next shut down or reboot. For
 this driver version, in order to enable WoL, the igb driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst
index 9cddabe8108e..557fc020ef31 100644
--- a/Documentation/networking/device_drivers/intel/igbvf.rst
+++ b/Documentation/networking/device_drivers/intel/igbvf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-============================================================
-Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet
-============================================================
+===========================================================
+Linux Base Virtual Function Driver for Intel(R) 1G Ethernet
+===========================================================
 
 Intel Gigabit Virtual Function Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/intel/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst
index c7d25483fedb..f1d5233e5e51 100644
--- a/Documentation/networking/device_drivers/intel/ixgbe.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbe.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-=============================================================================
-Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
-=============================================================================
+===========================================================================
+Linux Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
+===========================================================================
 
 Intel 10 Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -519,8 +519,8 @@ The offload is also supported for ixgbe's VFs, but the VF must be set as
 Known Issues/Troubleshooting
 ============================
 
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS
------------------------------------------------------------------------
+Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS
+---------------------------------------------------------------------
 Linux KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.
 This includes traditional PCIe devices, as well as SR-IOV-capable devices based
 on the Intel Ethernet Controller XL710.
diff --git a/Documentation/networking/device_drivers/intel/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst
index 5d4977360157..76bbde736f21 100644
--- a/Documentation/networking/device_drivers/intel/ixgbevf.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-=============================================================
-Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet
-=============================================================
+============================================================
+Linux Base Virtual Function Driver for Intel(R) 10G Ethernet
+============================================================
 
 Intel 10 Gigabit Virtual Function Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst
index 67b6839d516b..c17d680cf334 100644
--- a/Documentation/networking/device_drivers/pensando/ionic.rst
+++ b/Documentation/networking/device_drivers/pensando/ionic.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==========================================================
-Linux* Driver for the Pensando(R) Ethernet adapter family
-==========================================================
+========================================================
+Linux Driver for the Pensando(R) Ethernet adapter family
+========================================================
 
 Pensando Linux Ethernet driver.
 Copyright(c) 2019 Pensando Systems, Inc
@@ -36,8 +36,10 @@ Support
 =======
 For general Linux networking support, please use the netdev mailing
 list, which is monitored by Pensando personnel::
+
   netdev@vger.kernel.org
 
 For more specific support needs, please use the Pensando driver support
 email::
-	drivers@pensando.io
+
+  drivers@pensando.io
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 49e95f438ed7..8d4ad1d1ae26 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -207,8 +207,8 @@ TCP variables:
 
 somaxconn - INTEGER
 	Limit of socket listen() backlog, known in userspace as SOMAXCONN.
-	Defaults to 128.  See also tcp_max_syn_backlog for additional tuning
-	for TCP sockets.
+	Defaults to 4096. (Was 128 before linux-5.4)
+	See also tcp_max_syn_backlog for additional tuning for TCP sockets.
 
 tcp_abort_on_overflow - BOOLEAN
 	If listening service is too slow to accept new connections,
@@ -408,11 +408,14 @@ tcp_max_orphans - INTEGER
 	up to ~64K of unswappable memory.
 
 tcp_max_syn_backlog - INTEGER
-	Maximal number of remembered connection requests, which have not
-	received an acknowledgment from connecting client.
+	Maximal number of remembered connection requests (SYN_RECV),
+	which have not received an acknowledgment from connecting client.
+	This is a per-listener limit.
 	The minimal value is 128 for low memory machines, and it will
 	increase in proportion to the memory of machine.
 	If server suffers from overload, try increasing this number.
+	Remember to also check /proc/sys/net/core/somaxconn
+	A SYN_RECV request socket consumes about 304 bytes of memory.
 
 tcp_max_tw_buckets - INTEGER
 	Maximal number of timewait sockets held by system simultaneously.
diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.txt
index 9cb31c5e2dcd..9bdb7d5a3ba3 100644
--- a/Documentation/networking/net_dim.txt
+++ b/Documentation/networking/net_dim.txt
@@ -92,16 +92,16 @@ under some conditions.
 Part III: Registering a Network Device to DIM
 ==============================================
 
-Net DIM API exposes the main function net_dim(struct net_dim *dim,
-struct net_dim_sample end_sample). This function is the entry point to the Net
+Net DIM API exposes the main function net_dim(struct dim *dim,
+struct dim_sample end_sample). This function is the entry point to the Net
 DIM algorithm and has to be called every time the driver would like to check if
 it should change interrupt moderation parameters. The driver should provide two
-data structures: struct net_dim and struct net_dim_sample. Struct net_dim
+data structures: struct dim and struct dim_sample. Struct dim
 describes the state of DIM for a specific object (RX queue, TX queue,
 other queues, etc.). This includes the current selected profile, previous data
 samples, the callback function provided by the driver and more.
-Struct net_dim_sample describes a data sample, which will be compared to the
-data sample stored in struct net_dim in order to decide on the algorithm's next
+Struct dim_sample describes a data sample, which will be compared to the
+data sample stored in struct dim in order to decide on the algorithm's next
 step. The sample should include bytes, packets and interrupts, measured by
 the driver.
 
@@ -110,9 +110,9 @@ main net_dim() function. The recommended method is to call net_dim() on each
 interrupt. Since Net DIM has a built-in moderation and it might decide to skip
 iterations under certain conditions, there is no need to moderate the net_dim()
 calls as well. As mentioned above, the driver needs to provide an object of type
-struct net_dim to the net_dim() function call. It is advised for each entity
-using Net DIM to hold a struct net_dim as part of its data structure and use it
-as the main Net DIM API object. The struct net_dim_sample should hold the latest
+struct dim to the net_dim() function call. It is advised for each entity
+using Net DIM to hold a struct dim as part of its data structure and use it
+as the main Net DIM API object. The struct dim_sample should hold the latest
 bytes, packets and interrupts count. No need to perform any calculations, just
 include the raw data.
 
@@ -132,19 +132,19 @@ usage is not complete but it should make the outline of the usage clear.
 
 my_driver.c:
 
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 
 /* Callback for net DIM to schedule on a decision to change moderation */
 void my_driver_do_dim_work(struct work_struct *work)
 {
-	/* Get struct net_dim from struct work_struct */
-	struct net_dim *dim = container_of(work, struct net_dim,
-					   work);
+	/* Get struct dim from struct work_struct */
+	struct dim *dim = container_of(work, struct dim,
+				       work);
 	/* Do interrupt moderation related stuff */
 	...
 
 	/* Signal net DIM work is done and it should move to next iteration */
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
 
 /* My driver's interrupt handler */
@@ -152,13 +152,13 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...)
 {
 	...
 	/* A struct to hold current measured data */
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 	...
 	/* Initiate data sample struct with current data */
-	net_dim_sample(my_entity->events,
-		       my_entity->packets,
-		       my_entity->bytes,
-		       &dim_sample);
+	dim_update_sample(my_entity->events,
+		          my_entity->packets,
+		          my_entity->bytes,
+		          &dim_sample);
 	/* Call net DIM */
 	net_dim(&my_entity->dim, dim_sample);
 	...
diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index 0dd3f748239f..f914e81fd3a6 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -436,6 +436,10 @@ by the driver:
    encryption.
  * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream
    but did not arrive in the expected order.
+ * ``tx_tls_skip_no_sync_data`` - number of TX packets which were part of
+   a TLS stream and arrived out-of-order, but skipped the HW offload routine
+   and went to the regular transmit flow as they were retransmissions of the
+   connection handshake.
  * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of
    a TLS stream dropped, because they arrived out of order and associated
    record could not be found.
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
index af64c4bb4447..a8de2fbc1caa 100644
--- a/Documentation/x86/index.rst
+++ b/Documentation/x86/index.rst
@@ -27,6 +27,7 @@ x86-specific Documentation
    mds
    microcode
    resctrl_ui
+   tsx_async_abort
    usb-legacy-support
    i386/index
    x86_64/index
diff --git a/Documentation/x86/tsx_async_abort.rst b/Documentation/x86/tsx_async_abort.rst
new file mode 100644
index 000000000000..583ddc185ba2
--- /dev/null
+++ b/Documentation/x86/tsx_async_abort.rst
@@ -0,0 +1,117 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+TSX Async Abort (TAA) mitigation
+================================
+
+.. _tsx_async_abort:
+
+Overview
+--------
+
+TSX Async Abort (TAA) is a side channel attack on internal buffers in some
+Intel processors similar to Microachitectural Data Sampling (MDS).  In this
+case certain loads may speculatively pass invalid data to dependent operations
+when an asynchronous abort condition is pending in a Transactional
+Synchronization Extensions (TSX) transaction.  This includes loads with no
+fault or assist condition. Such loads may speculatively expose stale data from
+the same uarch data structures as in MDS, with same scope of exposure i.e.
+same-thread and cross-thread. This issue affects all current processors that
+support TSX.
+
+Mitigation strategy
+-------------------
+
+a) TSX disable - one of the mitigations is to disable TSX. A new MSR
+IA32_TSX_CTRL will be available in future and current processors after
+microcode update which can be used to disable TSX. In addition, it
+controls the enumeration of the TSX feature bits (RTM and HLE) in CPUID.
+
+b) Clear CPU buffers - similar to MDS, clearing the CPU buffers mitigates this
+vulnerability. More details on this approach can be found in
+:ref:`Documentation/admin-guide/hw-vuln/mds.rst <mds>`.
+
+Kernel internal mitigation modes
+--------------------------------
+
+ =============    ============================================================
+ off              Mitigation is disabled. Either the CPU is not affected or
+                  tsx_async_abort=off is supplied on the kernel command line.
+
+ tsx disabled     Mitigation is enabled. TSX feature is disabled by default at
+                  bootup on processors that support TSX control.
+
+ verw             Mitigation is enabled. CPU is affected and MD_CLEAR is
+                  advertised in CPUID.
+
+ ucode needed     Mitigation is enabled. CPU is affected and MD_CLEAR is not
+                  advertised in CPUID. That is mainly for virtualization
+                  scenarios where the host has the updated microcode but the
+                  hypervisor does not expose MD_CLEAR in CPUID. It's a best
+                  effort approach without guarantee.
+ =============    ============================================================
+
+If the CPU is affected and the "tsx_async_abort" kernel command line parameter is
+not provided then the kernel selects an appropriate mitigation depending on the
+status of RTM and MD_CLEAR CPUID bits.
+
+Below tables indicate the impact of tsx=on|off|auto cmdline options on state of
+TAA mitigation, VERW behavior and TSX feature for various combinations of
+MSR_IA32_ARCH_CAPABILITIES bits.
+
+1. "tsx=off"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=off
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default         Yes           Same as MDS           Same as MDS
+    0          0           1        Invalid case   Invalid case       Invalid case          Invalid case
+    0          1           0         HW default         No         Need ucode update     Need ucode update
+    0          1           1          Disabled          Yes           TSX disabled          TSX disabled
+    1          X           1          Disabled           X             None needed           None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+2. "tsx=on"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=on
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default        Yes            Same as MDS          Same as MDS
+    0          0           1        Invalid case   Invalid case       Invalid case         Invalid case
+    0          1           0         HW default        No          Need ucode update     Need ucode update
+    0          1           1          Enabled          Yes               None              Same as MDS
+    1          X           1          Enabled          X              None needed          None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+3. "tsx=auto"
+
+=========  =========  ============  ============  ==============  ===================  ======================
+MSR_IA32_ARCH_CAPABILITIES bits     Result with cmdline tsx=auto
+----------------------------------  -------------------------------------------------------------------------
+TAA_NO     MDS_NO     TSX_CTRL_MSR  TSX state     VERW can clear  TAA mitigation       TAA mitigation
+                                    after bootup  CPU buffers     tsx_async_abort=off  tsx_async_abort=full
+=========  =========  ============  ============  ==============  ===================  ======================
+    0          0           0         HW default    Yes                Same as MDS           Same as MDS
+    0          0           1        Invalid case  Invalid case        Invalid case          Invalid case
+    0          1           0         HW default    No              Need ucode update     Need ucode update
+    0          1           1          Disabled      Yes               TSX disabled          TSX disabled
+    1          X           1          Enabled       X                 None needed           None needed
+=========  =========  ============  ============  ==============  ===================  ======================
+
+In the tables, TSX_CTRL_MSR is a new bit in MSR_IA32_ARCH_CAPABILITIES that
+indicates whether MSR_IA32_TSX_CTRL is supported.
+
+There are two control bits in IA32_TSX_CTRL MSR:
+
+      Bit 0: When set it disables the Restricted Transactional Memory (RTM)
+             sub-feature of TSX (will force all transactions to abort on the
+             XBEGIN instruction).
+
+      Bit 1: When set it disables the enumeration of the RTM and HLE feature
+             (i.e. it will make CPUID(EAX=7).EBX{bit4} and
+             CPUID(EAX=7).EBX{bit11} read as 0).
diff --git a/MAINTAINERS b/MAINTAINERS
index 63c8ddc299bf..a5689e2c1aa5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -643,7 +643,7 @@ F:	drivers/net/ethernet/alacritech/*
 
 FORCEDETH GIGABIT ETHERNET DRIVER
 M:	Rain River <rain.1986.08.12@gmail.com>
-M:	Zhu Yanjun <yanjun.zhu@oracle.com>
+M:	Zhu Yanjun <zyjzyj2000@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/nvidia/*
@@ -2323,11 +2323,13 @@ F:	drivers/edac/altera_edac.
 
 ARM/SPREADTRUM SoC SUPPORT
 M:	Orson Zhai <orsonzhai@gmail.com>
-M:	Baolin Wang <baolin.wang@linaro.org>
+M:	Baolin Wang <baolin.wang7@gmail.com>
 M:	Chunyan Zhang <zhang.lyra@gmail.com>
 S:	Maintained
 F:	arch/arm64/boot/dts/sprd
 N:	sprd
+N:	sc27xx
+N:	sc2731
 
 ARM/STI ARCHITECTURE
 M:	Patrice Chotard <patrice.chotard@st.com>
@@ -2609,6 +2611,7 @@ S:	Maintained
 F:	arch/arm64/
 X:	arch/arm64/boot/dts/
 F:	Documentation/arm64/
+F:	tools/testing/selftests/arm64/
 
 AS3645A LED FLASH CONTROLLER DRIVER
 M:	Sakari Ailus <sakari.ailus@iki.fi>
@@ -3051,6 +3054,7 @@ M:	Daniel Borkmann <daniel@iogearbox.net>
 R:	Martin KaFai Lau <kafai@fb.com>
 R:	Song Liu <songliubraving@fb.com>
 R:	Yonghong Song <yhs@fb.com>
+R:	Andrii Nakryiko <andriin@fb.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
@@ -3183,7 +3187,7 @@ N:	bcm216*
 N:	kona
 F:	arch/arm/mach-bcm/
 
-BROADCOM BCM2835 ARM ARCHITECTURE
+BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE
 M:	Eric Anholt <eric@anholt.net>
 M:	Stefan Wahren <wahrenst@gmx.net>
 L:	bcm-kernel-feedback-list@broadcom.com
@@ -3191,6 +3195,7 @@ L:	linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://github.com/anholt/linux
 S:	Maintained
+N:	bcm2711
 N:	bcm2835
 F:	drivers/staging/vc04_services
 
@@ -3237,8 +3242,6 @@ S:	Maintained
 F:	drivers/usb/gadget/udc/bcm63xx_udc.*
 
 BROADCOM BCM7XXX ARM ARCHITECTURE
-M:	Brian Norris <computersforpeace@gmail.com>
-M:	Gregory Fong <gregory.0xf0@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -3259,7 +3262,6 @@ S:	Maintained
 F:	drivers/cpufreq/bmips-cpufreq.c
 
 BROADCOM BMIPS MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-mips@vger.kernel.org
@@ -3594,6 +3596,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/media/cdns,*.txt
 F:	drivers/media/platform/cadence/cdns-csi2*
 
+CADENCE NAND DRIVER
+M:	Piotr Sroka <piotrs@cadence.com>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/nand/raw/cadence-nand-controller.c
+F:	Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt
+
 CADET FM/AM RADIO RECEIVER DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
@@ -3736,7 +3745,6 @@ F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
 M:	Robert Richter <rrichter@cavium.com>
-M:	Jayachandran C <jnair@caviumnetworks.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*
@@ -8298,11 +8306,14 @@ F:	drivers/hid/intel-ish-hid/
 
 INTEL IOMMU (VT-d)
 M:	David Woodhouse <dwmw2@infradead.org>
+M:	Lu Baolu <baolu.lu@linux.intel.com>
 L:	iommu@lists.linux-foundation.org
-T:	git git://git.infradead.org/iommu-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 S:	Supported
-F:	drivers/iommu/intel-iommu.c
+F:	drivers/iommu/dmar.c
+F:	drivers/iommu/intel*.[ch]
 F:	include/linux/intel-iommu.h
+F:	include/linux/intel-svm.h
 
 INTEL IOP-ADMA DMA DRIVER
 R:	Dan Williams <dan.j.williams@intel.com>
@@ -8561,12 +8572,13 @@ F:	include/linux/iova.h
 
 IO_URING
 M:	Jens Axboe <axboe@kernel.dk>
-L:	linux-block@vger.kernel.org
-L:	linux-fsdevel@vger.kernel.org
+L:	io-uring@vger.kernel.org
 T:	git git://git.kernel.dk/linux-block
 T:	git git://git.kernel.dk/liburing
 S:	Maintained
 F:	fs/io_uring.c
+F:	fs/io-wq.c
+F:	fs/io-wq.h
 F:	include/uapi/linux/io_uring.h
 
 IPMI SUBSYSTEM
@@ -8917,6 +8929,17 @@ S:	Maintained
 F:	tools/testing/selftests/
 F:	Documentation/dev-tools/kselftest*
 
+KERNEL UNIT TESTING FRAMEWORK (KUnit)
+M:	Brendan Higgins <brendanhiggins@google.com>
+L:	linux-kselftest@vger.kernel.org
+L:	kunit-dev@googlegroups.com
+W:	https://google.github.io/kunit-docs/third_party/kernel/docs/
+S:	Maintained
+F:	Documentation/dev-tools/kunit/
+F:	include/kunit/
+F:	lib/kunit/
+F:	tools/testing/kunit/
+
 KERNEL USERMODE HELPER
 M:	Luis Chamberlain <mcgrof@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -9122,7 +9145,7 @@ F:	drivers/auxdisplay/ks0108.c
 F:	include/linux/ks0108.h
 
 L3MDEV
-M:	David Ahern <dsa@cumulusnetworks.com>
+M:	David Ahern <dsahern@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	net/l3mdev
@@ -9494,6 +9517,13 @@ F:	Documentation/misc-devices/lis3lv02d.rst
 F:	drivers/misc/lis3lv02d/
 F:	drivers/platform/x86/hp_accel.c
 
+LIST KUNIT TEST
+M:	David Gow <davidgow@google.com>
+L:	linux-kselftest@vger.kernel.org
+L:	kunit-dev@googlegroups.com
+S:	Maintained
+F:	lib/list-test.c
+
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Jiri Kosina <jikos@kernel.org>
@@ -10255,7 +10285,7 @@ MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@openwrt.org>
 M:	John Crispin <john@phrozen.org>
 M:	Sean Wang <sean.wang@mediatek.com>
-M:	Nelson Chang <nelson.chang@mediatek.com>
+M:	Mark Lee <Mark-MC.Lee@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/mediatek/
@@ -10518,8 +10548,12 @@ F:	mm/memblock.c
 F:	Documentation/core-api/boot-time-mm.rst
 
 MEMORY MANAGEMENT
+M:	Andrew Morton <akpm@linux-foundation.org>
 L:	linux-mm@kvack.org
 W:	http://www.linux-mm.org
+T:	quilt https://ozlabs.org/~akpm/mmotm/
+T:	quilt https://ozlabs.org/~akpm/mmots/
+T:	git git://github.com/hnaz/linux-mm.git
 S:	Maintained
 F:	include/linux/mm.h
 F:	include/linux/gfp.h
@@ -10529,15 +10563,13 @@ F:	include/linux/vmalloc.h
 F:	mm/
 
 MEMORY TECHNOLOGY DEVICES (MTD)
-M:	David Woodhouse <dwmw2@infradead.org>
-M:	Brian Norris <computersforpeace@gmail.com>
-M:	Marek Vasut <marek.vasut@gmail.com>
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Richard Weinberger <richard@nod.at>
 M:	Vignesh Raghavendra <vigneshr@ti.com>
 L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
+C:	irc://irc.oftc.net/mtd
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/next
 S:	Maintained
@@ -11407,7 +11439,6 @@ F:	include/trace/events/tcp.h
 NETWORKING [TLS]
 M:	Boris Pismenny <borisp@mellanox.com>
 M:	Aviad Yehezkel <aviadye@mellanox.com>
-M:	Dave Watson <davejwatson@fb.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <jakub.kicinski@netronome.com>
@@ -11631,6 +11662,7 @@ F:	drivers/nvme/target/fcloop.c
 NVM EXPRESS TARGET DRIVER
 M:	Christoph Hellwig <hch@lst.de>
 M:	Sagi Grimberg <sagi@grimberg.me>
+M:	Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
 L:	linux-nvme@lists.infradead.org
 T:	git://git.infradead.org/nvme.git
 W:	http://git.infradead.org/nvme.git
@@ -12312,12 +12344,15 @@ F:	arch/parisc/
 F:	Documentation/parisc/
 F:	drivers/parisc/
 F:	drivers/char/agp/parisc-agp.c
+F:	drivers/input/misc/hp_sdc_rtc.c
 F:	drivers/input/serio/gscps2.c
+F:	drivers/input/serio/hp_sdc*
 F:	drivers/parport/parport_gsc.*
 F:	drivers/tty/serial/8250/8250_gsc.c
 F:	drivers/video/fbdev/sti*
 F:	drivers/video/console/sti*
 F:	drivers/video/logo/logo_parisc*
+F:	include/linux/hp_sdc.h
 
 PARMAN
 M:	Jiri Pirko <jiri@mellanox.com>
@@ -13123,12 +13158,14 @@ F:	Documentation/filesystems/proc.txt
 PROC SYSCTL
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Kees Cook <keescook@chromium.org>
+M:	Iurii Zaikin <yzaikin@google.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/proc/proc_sysctl.c
 F:	include/linux/sysctl.h
 F:	kernel/sysctl.c
+F:	kernel/sysctl-test.c
 F:	tools/testing/selftests/sysctl/
 
 PS3 NETWORK SUPPORT
@@ -13361,7 +13398,7 @@ S:	Maintained
 F:	drivers/scsi/qla1280.[ch]
 
 QLOGIC QLA2XXX FC-SCSI DRIVER
-M:	qla2xxx-upstream@qlogic.com
+M:	hmadhani@marvell.com
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	Documentation/scsi/LICENSE.qla2xxx
@@ -13902,7 +13939,7 @@ F:	drivers/mtd/nand/raw/r852.h
 
 RISC-V ARCHITECTURE
 M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Albert Ou <aou@eecs.berkeley.edu>
 L:	linux-riscv@lists.infradead.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git
@@ -14779,7 +14816,7 @@ F:	drivers/media/usb/siano/
 F:	drivers/media/mmc/siano/
 
 SIFIVE DRIVERS
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 L:	linux-riscv@lists.infradead.org
 T:	git git://github.com/sifive/riscv-linux.git
@@ -14789,7 +14826,7 @@ N:	sifive
 
 SIFIVE FU540 SYSTEM-ON-CHIP
 M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 L:	linux-riscv@lists.infradead.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git
 S:	Supported
@@ -15285,7 +15322,6 @@ F:	arch/arm/boot/dts/spear*
 F:	arch/arm/mach-spear/
 
 SPI NOR SUBSYSTEM
-M:	Marek Vasut <marek.vasut@gmail.com>
 M:	Tudor Ambarus <tudor.ambarus@microchip.com>
 L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
@@ -16582,10 +16618,9 @@ F:	drivers/media/pci/tw686x/
 
 UBI FILE SYSTEM (UBIFS)
 M:	Richard Weinberger <richard@nod.at>
-M:	Artem Bityutskiy <dedekind1@gmail.com>
-M:	Adrian Hunter <adrian.hunter@intel.com>
 L:	linux-mtd@lists.infradead.org
-T:	git git://git.infradead.org/ubifs-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes
 W:	http://www.linux-mtd.infradead.org/doc/ubifs.html
 S:	Supported
 F:	Documentation/filesystems/ubifs.txt
@@ -16700,11 +16735,11 @@ S:	Maintained
 F:	drivers/scsi/ufs/ufs-mediatek*
 
 UNSORTED BLOCK IMAGES (UBI)
-M:	Artem Bityutskiy <dedekind1@gmail.com>
 M:	Richard Weinberger <richard@nod.at>
 W:	http://www.linux-mtd.infradead.org/
 L:	linux-mtd@lists.infradead.org
-T:	git git://git.infradead.org/ubifs-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes
 S:	Supported
 F:	drivers/mtd/ubi/
 F:	include/linux/mtd/ubi.h
@@ -17206,6 +17241,7 @@ F:	virt/lib/
 
 VIRTIO AND VHOST VSOCK DRIVER
 M:	Stefan Hajnoczi <stefanha@redhat.com>
+M:	Stefano Garzarella <sgarzare@redhat.com>
 L:	kvm@vger.kernel.org
 L:	virtualization@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
@@ -17430,7 +17466,7 @@ F:	include/linux/regulator/
 K:	regulator_get_optional
 
 VRF
-M:	David Ahern <dsa@cumulusnetworks.com>
+M:	David Ahern <dsahern@kernel.org>
 M:	Shrijeet Mukherjee <shrijeet@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -18031,6 +18067,7 @@ F:	Documentation/vm/zsmalloc.rst
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
 M:	Dan Streetman <ddstreet@ieee.org>
+M:	Vitaly Wool <vitaly.wool@konsulko.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zswap.c
diff --git a/Makefile b/Makefile
index ffd7a912fc46..d4d36c61940b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
-NAME = Nesting Opossum
+EXTRAVERSION =
+NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -917,6 +917,9 @@ ifeq ($(CONFIG_RELR),y)
 LDFLAGS_vmlinux	+= --pack-dyn-relocs=relr
 endif
 
+# make the checker run with the right architecture
+CHECKFLAGS += --arch=$(ARCH)
+
 # insure the checker run with the right endianness
 CHECKFLAGS += $(if $(CONFIG_CPU_BIG_ENDIAN),-mbig-endian,-mlittle-endian)
 
@@ -1037,7 +1040,7 @@ export KBUILD_VMLINUX_OBJS := $(head-y) $(init-y) $(core-y) $(libs-y2) \
 export KBUILD_VMLINUX_LIBS := $(libs-y1)
 export KBUILD_LDS          := arch/$(SRCARCH)/kernel/vmlinux.lds
 export LDFLAGS_vmlinux
-# used by scripts/package/Makefile
+# used by scripts/Makefile.package
 export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) LICENSES arch include scripts tools)
 
 vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_OBJS) $(KBUILD_VMLINUX_LIBS)
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index bfc7f5f5d6f2..9acbeba832c0 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -65,6 +65,14 @@
 		clock-frequency = <33333333>;
 	};
 
+	reg_5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "5v0-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
 	cpu_intc: cpu-interrupt-controller {
 		compatible = "snps,archs-intc";
 		interrupt-controller;
@@ -264,6 +272,21 @@
 			clocks = <&input_clk>;
 			cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>,
 				   <&creg_gpio 1 GPIO_ACTIVE_LOW>;
+
+			spi-flash@0 {
+				compatible = "sst26wf016b", "jedec,spi-nor";
+				reg = <0>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				spi-max-frequency = <4000000>;
+			};
+
+			adc@1 {
+				compatible = "ti,adc108s102";
+				reg = <1>;
+				vref-supply = <&reg_5v0>;
+				spi-max-frequency = <1000000>;
+			};
 		};
 
 		creg_gpio: gpio@14b0 {
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 9b9a74444ce2..0974226fab55 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -32,6 +32,8 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_MTD=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -55,6 +57,8 @@ CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_SNPS_CREG=y
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_DRM=y
 # CONFIG_DRM_FBDEV_EMULATION is not set
 CONFIG_DRM_UDL=y
@@ -72,6 +76,8 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 CONFIG_DMADEVICES=y
 CONFIG_DW_AXI_DMAC=y
+CONFIG_IIO=y
+CONFIG_TI_ADC108S102=y
 CONFIG_EXT3_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 861a8aea51f9..661fd842ea97 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -614,8 +614,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	/* loop thru all available h/w condition indexes */
 	for (i = 0; i < cc_bcr.c; i++) {
 		write_aux_reg(ARC_REG_CC_INDEX, i);
-		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
-		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
+		cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0));
+		cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1));
 
 		arc_pmu_map_hw_event(i, cc_name.str);
 		arc_pmu_add_raw_event_attr(i, cc_name.str);
diff --git a/arch/arm/boot/dts/am3874-iceboard.dts b/arch/arm/boot/dts/am3874-iceboard.dts
index 883fb85135d4..1b4b2b0500e4 100644
--- a/arch/arm/boot/dts/am3874-iceboard.dts
+++ b/arch/arm/boot/dts/am3874-iceboard.dts
@@ -111,13 +111,13 @@
 		reg = <0x70>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		i2c-mux-idle-disconnect;
 
 		i2c@0 {
 			/* FMC A */
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@1 {
@@ -125,7 +125,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <1>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@2 {
@@ -133,7 +132,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <2>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@3 {
@@ -141,7 +139,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <3>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@4 {
@@ -149,14 +146,12 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <4>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@5 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <5>;
-			i2c-mux-idle-disconnect;
 
 			ina230@40 { compatible = "ti,ina230"; reg = <0x40>; shunt-resistor = <5000>; };
 			ina230@41 { compatible = "ti,ina230"; reg = <0x41>; shunt-resistor = <5000>; };
@@ -182,14 +177,12 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <6>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@7 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <7>;
-			i2c-mux-idle-disconnect;
 
 			u41: pca9575@20 {
 				compatible = "nxp,pca9575";
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index 09a088f98566..b75af21069f9 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -113,6 +113,7 @@
 	#address-cells = <1>;
 	#size-cells = <0>;
 	pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>;
+	bus-width = <4>;
 	mmc-pwrseq = <&wifi_pwrseq>;
 	non-removable;
 	status = "okay";
diff --git a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
index 7c3cb7ece6cb..925cb37c22f0 100644
--- a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
+++ b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
@@ -9,6 +9,14 @@
 		reg = <0 0x40000000>;
 	};
 
+	leds {
+		/*
+		 * Since there is no upstream GPIO driver yet,
+		 * remove the incomplete node.
+		 */
+		/delete-node/ act;
+	};
+
 	reg_3v3: fixed-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "3V3";
diff --git a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
index 2a6ce87071f9..9e027b9a5f91 100644
--- a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
+++ b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
@@ -328,6 +328,10 @@
 	pinctrl-0 = <&pinctrl_pwm3>;
 };
 
+&snvs_pwrkey {
+	status = "okay";
+};
+
 &ssi2 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6-logicpd-som.dtsi b/arch/arm/boot/dts/imx6-logicpd-som.dtsi
index 7ceae3573248..547fb141ec0c 100644
--- a/arch/arm/boot/dts/imx6-logicpd-som.dtsi
+++ b/arch/arm/boot/dts/imx6-logicpd-som.dtsi
@@ -207,6 +207,10 @@
 	vin-supply = <&sw1c_reg>;
 };
 
+&snvs_poweroff {
+	status = "okay";
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_hog>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index f3404dd10537..cf628465cd0a 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -230,6 +230,8 @@
 			accelerometer@1c {
 				compatible = "fsl,mma8451";
 				reg = <0x1c>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_mma8451_int>;
 				interrupt-parent = <&gpio6>;
 				interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 			};
@@ -628,6 +630,12 @@
 			>;
 		};
 
+		pinctrl_mma8451_int: mma8451intgrp {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_BCLK__GPIO6_IO31		0xb0b1
+			>;
+		};
+
 		pinctrl_pwm3: pwm1grp {
 			fsl,pins = <
 				MX6QDL_PAD_SD4_DAT1__PWM3_OUT		0x1b0b1
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 710f850e785c..e2e604d6ba0b 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -448,7 +448,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302d0000 0x10000>;
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT1_ROOT_CLK>,
 					 <&clks IMX7D_GPT1_ROOT_CLK>;
 				clock-names = "ipg", "per";
 			};
@@ -457,7 +457,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302e0000 0x10000>;
 				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT2_ROOT_CLK>,
 					 <&clks IMX7D_GPT2_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -467,7 +467,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302f0000 0x10000>;
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT3_ROOT_CLK>,
 					 <&clks IMX7D_GPT3_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -477,7 +477,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x30300000 0x10000>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT4_ROOT_CLK>,
 					 <&clks IMX7D_GPT4_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 3fdd0a72f87f..506b118e511a 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -192,3 +192,7 @@
 &twl_gpio {
 	ti,use-leds;
 };
+
+&twl_keypad {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/mt7629-rfb.dts b/arch/arm/boot/dts/mt7629-rfb.dts
index 3621b7d2b22a..9980c10c6e29 100644
--- a/arch/arm/boot/dts/mt7629-rfb.dts
+++ b/arch/arm/boot/dts/mt7629-rfb.dts
@@ -66,9 +66,21 @@
 	pinctrl-1 = <&ephy_leds_pins>;
 	status = "okay";
 
+	gmac0: mac@0 {
+		compatible = "mediatek,eth-mac";
+		reg = <0>;
+		phy-mode = "2500base-x";
+		fixed-link {
+			speed = <2500>;
+			full-duplex;
+			pause;
+		};
+	};
+
 	gmac1: mac@1 {
 		compatible = "mediatek,eth-mac";
 		reg = <1>;
+		phy-mode = "gmii";
 		phy-handle = <&phy0>;
 	};
 
@@ -78,7 +90,6 @@
 
 		phy0: ethernet-phy@0 {
 			reg = <0>;
-			phy-mode = "gmii";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/mt7629.dtsi b/arch/arm/boot/dts/mt7629.dtsi
index 9608bc2ccb3f..867b88103b9d 100644
--- a/arch/arm/boot/dts/mt7629.dtsi
+++ b/arch/arm/boot/dts/mt7629.dtsi
@@ -468,14 +468,12 @@
 			compatible = "mediatek,mt7629-sgmiisys", "syscon";
 			reg = <0x1b128000 0x3000>;
 			#clock-cells = <1>;
-			mediatek,physpeed = "2500";
 		};
 
 		sgmiisys1: syscon@1b130000 {
 			compatible = "mediatek,mt7629-sgmiisys", "syscon";
 			reg = <0x1b130000 0x3000>;
 			#clock-cells = <1>;
-			mediatek,physpeed = "2500";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index 4454449de00c..a40fe8d49da6 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -369,7 +369,7 @@
 		compatible = "ti,wl1285", "ti,wl1283";
 		reg = <2>;
 		/* gpio_100 with gpmc_wait2 pad as wakeirq */
-		interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>,
+		interrupts-extended = <&gpio4 4 IRQ_TYPE_LEVEL_HIGH>,
 				      <&omap4_pmx_core 0x4e>;
 		interrupt-names = "irq", "wakeup";
 		ref-clock-frequency = <26000000>;
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index 14be2ecb62b1..55ea8b6189af 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -474,7 +474,7 @@
 		compatible = "ti,wl1271";
 		reg = <2>;
 		/* gpio_53 with gpmc_ncs3 pad as wakeup */
-		interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_RISING>,
+		interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_HIGH>,
 				      <&omap4_pmx_core 0x3a>;
 		interrupt-names = "irq", "wakeup";
 		ref-clock-frequency = <38400000>;
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index 3c274965ff40..91480ac1f328 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -512,7 +512,7 @@
 		compatible = "ti,wl1281";
 		reg = <2>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <21 IRQ_TYPE_EDGE_RISING>; /* gpio 53 */
+		interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* gpio 53 */
 		ref-clock-frequency = <26000000>;
 		tcxo-clock-frequency = <26000000>;
 	};
diff --git a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
index 6dbbc9b3229c..d0032213101e 100644
--- a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
+++ b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
@@ -69,7 +69,7 @@
 		compatible = "ti,wl1271";
 		reg = <2>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <9 IRQ_TYPE_EDGE_RISING>; /* gpio 41 */
+		interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; /* gpio 41 */
 		ref-clock-frequency = <38400000>;
 	};
 };
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 7fff555ee394..68ac04641bdb 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -362,7 +362,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&wlcore_irq_pin>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <14 IRQ_TYPE_EDGE_RISING>;	/* gpio 14 */
+		interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;	/* gpio 14 */
 		ref-clock-frequency = <26000000>;
 	};
 };
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index fac2e57dcca9..4791834dacb2 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -1146,7 +1146,7 @@
 		};
 	};
 
-	gpu_cm: clock-controller@1500 {
+	gpu_cm: gpu_cm@1500 {
 		compatible = "ti,omap4-cm";
 		reg = <0x1500 0x100>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
index e4a0d51ec3a8..0a3a7d66737b 100644
--- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
@@ -609,13 +609,13 @@
 						 <STM32_PINMUX('F', 6, AF9)>; /* QSPI_BK1_IO3 */
 					bias-disable;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 				pins2 {
 					pinmux = <STM32_PINMUX('B', 6, AF10)>; /* QSPI_BK1_NCS */
 					bias-pull-up;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 			};
 
@@ -637,13 +637,13 @@
 						 <STM32_PINMUX('G', 7, AF11)>; /* QSPI_BK2_IO3 */
 					bias-disable;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 				pins2 {
 					pinmux = <STM32_PINMUX('C', 0, AF10)>; /* QSPI_BK2_NCS */
 					bias-pull-up;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 			};
 
diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts
index 89d29b50c3f4..91fc0a315c49 100644
--- a/arch/arm/boot/dts/stm32mp157c-ev1.dts
+++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts
@@ -183,14 +183,12 @@
 
 	ov5640: camera@3c {
 		compatible = "ovti,ov5640";
-		pinctrl-names = "default";
-		pinctrl-0 = <&ov5640_pins>;
 		reg = <0x3c>;
 		clocks = <&clk_ext_camera>;
 		clock-names = "xclk";
 		DOVDD-supply = <&v2v8>;
-		powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>;
-		reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>;
+		powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>;
+		reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>;
 		rotation = <180>;
 		status = "okay";
 
@@ -223,15 +221,8 @@
 
 			joystick_pins: joystick {
 				pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4";
-				drive-push-pull;
 				bias-pull-down;
 			};
-
-			ov5640_pins: camera {
-				pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */
-				drive-push-pull;
-				output-low;
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 9b11654a0a39..f98e0370c0bc 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -932,7 +932,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 
@@ -945,7 +945,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 874231be04e4..8aebefd6accf 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -380,9 +380,8 @@
 			compatible = "allwinner,sun7i-a20-csi0";
 			reg = <0x01c09000 0x1000>;
 			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>,
-				 <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
-			clock-names = "bus", "mod", "isp", "ram";
+			clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
+			clock-names = "bus", "isp", "ram";
 			resets = <&ccu RST_CSI0>;
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
index 568b90ece342..3bec3e0a81b2 100644
--- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
@@ -192,6 +192,7 @@
 	vqmmc-supply = <&reg_dldo1>;
 	non-removable;
 	wakeup-source;
+	keep-power-in-suspend;
 	status = "okay";
 
 	brcmf: wifi@1 {
diff --git a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
index dc8a5f37a1ef..c8ebb23c4e02 100644
--- a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
+++ b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
@@ -602,6 +602,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		reg = <0x70>;
+		i2c-mux-idle-disconnect;
 
 		sff0_i2c: i2c@1 {
 			#address-cells = <1>;
@@ -640,6 +641,7 @@
 		reg = <0x71>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		i2c-mux-idle-disconnect;
 
 		sff5_i2c: i2c@1 {
 			#address-cells = <1>;
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 01e3c0f4be92..231f8973bbb2 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -167,6 +167,7 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_DA8XX=y
 CONFIG_BACKLIGHT_PWM=m
+CONFIG_BACKLIGHT_GPIO=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 9bfffbe22d53..0f7381ee0c37 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -276,6 +276,7 @@ CONFIG_VIDEO_OV5640=m
 CONFIG_VIDEO_OV5645=m
 CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
+CONFIG_DRM_MSM=y
 CONFIG_DRM_PANEL_LVDS=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_SEIKO_43WVF1G=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index d3f50971e451..40d7f1a4fc45 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -356,15 +356,15 @@ CONFIG_DRM_OMAP_CONNECTOR_HDMI=m
 CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV=m
 CONFIG_DRM_OMAP_PANEL_DPI=m
 CONFIG_DRM_OMAP_PANEL_DSI_CM=m
-CONFIG_DRM_OMAP_PANEL_SONY_ACX565AKM=m
-CONFIG_DRM_OMAP_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DRM_OMAP_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1=m
-CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m
-CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m
 CONFIG_DRM_TILCDC=m
 CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_DRM_TI_TFP410=m
+CONFIG_DRM_PANEL_LG_LB035Q02=m
+CONFIG_DRM_PANEL_NEC_NL8048HL11=m
+CONFIG_DRM_PANEL_SHARP_LS037V7DW01=m
+CONFIG_DRM_PANEL_SONY_ACX565AKM=m
+CONFIG_DRM_PANEL_TPO_TD028TTEC1=m
+CONFIG_DRM_PANEL_TPO_TD043MTEA1=m
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 567dbede4785..f1d0a7807cd0 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -82,7 +82,7 @@
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_CPU_CP15_MMU
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	unsigned int domain;
 
@@ -94,7 +94,7 @@ static inline unsigned int get_domain(void)
 	return domain;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
@@ -102,12 +102,12 @@ static inline void set_domain(unsigned val)
 	isb();
 }
 #else
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	return 0;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 }
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 303248e5b990..98c6b91be4a8 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -22,7 +22,7 @@
  * perform such accesses (eg, via list poison values) which could then
  * be exploited for priviledge escalation.
  */
-static inline unsigned int uaccess_save_and_enable(void)
+static __always_inline unsigned int uaccess_save_and_enable(void)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	unsigned int old_domain = get_domain();
@@ -37,7 +37,7 @@ static inline unsigned int uaccess_save_and_enable(void)
 #endif
 }
 
-static inline void uaccess_restore(unsigned int flags)
+static __always_inline void uaccess_restore(unsigned int flags)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/* Restore the user access mask */
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index a7810be07da1..4a3982812a40 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -68,7 +68,7 @@ ENDPROC(__vet_atags)
  * The following fragment of code is executed with the MMU on in MMU mode,
  * and uses absolute addresses; this is not position independent.
  *
- *  r0  = cp#15 control register
+ *  r0  = cp#15 control register (exc_ret for M-class)
  *  r1  = machine ID
  *  r2  = atags/dtb pointer
  *  r9  = processor ID
@@ -137,7 +137,8 @@ __mmap_switched_data:
 #ifdef CONFIG_CPU_CP15
 	.long	cr_alignment			@ r3
 #else
-	.long	0				@ r3
+M_CLASS(.long	exc_ret)			@ r3
+AR_CLASS(.long	0)				@ r3
 #endif
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index afa350f44dea..0fc814bbc34b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -201,6 +201,8 @@ M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
 	bic	r0, r0, #V7M_SCB_CCR_IC
 #endif
 	str	r0, [r12, V7M_SCB_CCR]
+	/* Pass exc_ret to __mmap_switched */
+	mov	r0, r10
 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */
 	ret	lr
 ENDPROC(__after_proc_init)
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8062412be70f..9fc5c73cc0be 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -462,8 +462,8 @@ static s8 dm365_queue_priority_mapping[][2] = {
 };
 
 static const struct dma_slave_map dm365_edma_map[] = {
-	{ "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) },
-	{ "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) },
+	{ "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) },
+	{ "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) },
 	{ "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) },
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index d942a3357090..2efd18e8824c 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -89,6 +89,13 @@ static struct iommu_platform_data omap3_iommu_pdata = {
 	.reset_name = "mmu",
 	.assert_reset = omap_device_assert_hardreset,
 	.deassert_reset = omap_device_deassert_hardreset,
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
+};
+
+static struct iommu_platform_data omap3_iommu_isp_pdata = {
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
 };
 
 static int omap3_sbc_t3730_twl_callback(struct device *dev,
@@ -424,6 +431,8 @@ static struct iommu_platform_data omap4_iommu_pdata = {
 	.reset_name = "mmu_cache",
 	.assert_reset = omap_device_assert_hardreset,
 	.deassert_reset = omap_device_deassert_hardreset,
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
 };
 #endif
 
@@ -617,6 +626,8 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = {
 #ifdef CONFIG_ARCH_OMAP3
 	OF_DEV_AUXDATA("ti,omap2-iommu", 0x5d000000, "5d000000.mmu",
 		       &omap3_iommu_pdata),
+	OF_DEV_AUXDATA("ti,omap2-iommu", 0x480bd400, "480bd400.mmu",
+		       &omap3_iommu_isp_pdata),
 	OF_DEV_AUXDATA("ti,omap3-smartreflex-core", 0x480cb000,
 		       "480cb000.smartreflex", &omap_sr_pdata[OMAP_SR_CORE]),
 	OF_DEV_AUXDATA("ti,omap3-smartreflex-mpu-iva", 0x480c9000,
diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c
index 239084cf8192..26cbce135338 100644
--- a/arch/arm/mach-sunxi/mc_smp.c
+++ b/arch/arm/mach-sunxi/mc_smp.c
@@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu)
 static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 {
 	u32 reg;
+	int gating_bit = cpu;
 
 	pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu);
 	if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS)
 		return -EINVAL;
 
+	if (is_a83t && cpu == 0)
+		gating_bit = 4;
+
 	/* gate processor power */
 	reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster));
-	reg |= PRCM_PWROFF_GATING_REG_CORE(cpu);
+	reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit);
 	writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster));
 	udelay(20);
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 04b36436cbc0..788c5cf46de5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -324,7 +324,7 @@ union offset_union {
 	__put32_unaligned_check("strbt", val, addr)
 
 static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset)
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset)
 {
 	if (!LDST_U_BIT(instr))
 		offset.un = -offset.un;
@@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs
 }
 
 static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
 }
 
 static int
-do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
-		      struct pt_regs *regs)
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 	unsigned int rd2;
@@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
 }
 
 static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
  * PU = 10             A                    B
  */
 static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd, rn, correction, nr_regs, regbits;
 	unsigned long eaddr, newaddr;
@@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 	 * processor for us.
 	 */
 	if (addr != eaddr) {
-		pr_err("LDMSTM: PC = %08lx, instr = %08lx, "
+		pr_err("LDMSTM: PC = %08lx, instr = %08x, "
 			"addr = %08lx, eaddr = %08lx\n",
 			 instruction_pointer(regs), instr, addr, eaddr);
 		show_regs(regs);
@@ -716,10 +715,10 @@ thumb2arm(u16 tinstr)
  * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
  */
 static void *
-do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
 			    union offset_union *poffset)
 {
-	unsigned long instr = *pinstr;
+	u32 instr = *pinstr;
 	u16 tinst1 = (instr >> 16) & 0xffff;
 	u16 tinst2 = instr & 0xffff;
 
@@ -767,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 	return NULL;
 }
 
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_arm(instr);
+
+	return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_thumb16(instr);
+
+	return fault;
+}
+
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	union offset_union uninitialized_var(offset);
-	unsigned long instr = 0, instrptr;
-	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
+	unsigned long instrptr;
+	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
 	unsigned int type;
-	unsigned int fault;
+	u32 instr = 0;
 	u16 tinstr = 0;
 	int isize = 4;
 	int thumb2_32b = 0;
+	int fault;
 
 	if (interrupts_enabled(regs))
 		local_irq_enable();
@@ -786,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
-		fault = probe_kernel_address(ptr, tinstr);
-		tinstr = __mem_to_opcode_thumb16(tinstr);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
-				u16 tinst2 = 0;
-				fault = probe_kernel_address(ptr + 1, tinst2);
-				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
 				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
@@ -803,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address((void *)instrptr, instr);
-		instr = __mem_to_opcode_arm(instr);
+		fault = alignment_get_arm(regs, (void *)instrptr, &instr);
 	}
 
 	if (fault) {
@@ -926,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * Oops, we didn't handle the instruction.
 	 */
 	pr_err("Alignment trap: not handling instruction "
-		"%0*lx at [<%08lx>]\n",
+		"%0*x at [<%08lx>]\n",
 		isize << 1,
 		isize == 2 ? tinstr : instr, instrptr);
 	ai_skipped += 1;
@@ -936,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	ai_user += 1;
 
 	if (ai_usermode & UM_WARN)
-		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
+		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
 			isize << 1,
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 9a07916af8dd..54d87506d3b5 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/arm-smccc.h>
 #include <linux/kernel.h>
-#include <linux/psci.h>
 #include <linux/smp.h>
 
 #include <asm/cp15.h>
@@ -75,11 +74,8 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A72: {
 		struct arm_smccc_res res;
 
-		if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-			break;
-
-		switch (psci_ops.conduit) {
-		case PSCI_CONDUIT_HVC:
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
 			arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
@@ -90,7 +86,7 @@ static void cpu_v7_spectre_init(void)
 			spectre_v2_method = "hypervisor";
 			break;
 
-		case PSCI_CONDUIT_SMC:
+		case SMCCC_CONDUIT_SMC:
 			arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1448f144e7fb..1a49d503eafc 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -132,13 +132,11 @@ __v7m_setup_cont:
 	dsb
 	mov	r6, lr			@ save LR
 	ldr	sp, =init_thread_union + THREAD_START_SP
-	stmia	sp, {r0-r3, r12}
 	cpsie	i
 	svc	#0
 1:	cpsid	i
-	ldr	r0, =exc_ret
-	orr	lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK
-	str	lr, [r0]
+	/* Calculate exc_ret */
+	orr	r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK
 	ldmia	sp, {r0-r3, r12}
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 950a56b71ff0..d66a9727344d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -143,6 +143,8 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS \
+		if $(cc-option,-fpatchable-function-entry=2)
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
@@ -266,6 +268,10 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
+config ZONE_DMA
+	bool "Support DMA zone" if EXPERT
+	default y
+
 config ZONE_DMA32
 	bool "Support DMA32 zone" if EXPERT
 	default y
@@ -538,6 +544,16 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
+config ARM64_ERRATUM_1319367
+	bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	default y
+	help
+	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
+	  and A72 erratum 1319367
+
+	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
+	  speculating an AT instruction during a guest context switch.
+
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_1463225
@@ -558,6 +574,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -616,6 +648,23 @@ config CAVIUM_ERRATUM_30115
 
 	  If unsure, say Y.
 
+config CAVIUM_TX2_ERRATUM_219
+	bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails"
+	default y
+	help
+	  On Cavium ThunderX2, a load, store or prefetch instruction between a
+	  TTBR update and the corresponding context synchronizing operation can
+	  cause a spurious Data Abort to be delivered to any hardware thread in
+	  the CPU core.
+
+	  Work around the issue by avoiding the problematic code sequence and
+	  trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The
+	  trap handler performs the corresponding register access, skips the
+	  instruction and ensures context synchronization by virtue of the
+	  exception return.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
@@ -828,10 +877,26 @@ config ARM64_PA_BITS
 	default 48 if ARM64_PA_BITS_48
 	default 52 if ARM64_PA_BITS_52
 
+choice
+	prompt "Endianness"
+	default CPU_LITTLE_ENDIAN
+	help
+	  Select the endianness of data accesses performed by the CPU. Userspace
+	  applications will need to be compiled and linked for the endianness
+	  that is selected here.
+
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help
-         Say Y if you plan on running a kernel in big-endian mode.
+	  Say Y if you plan on running a kernel with a big-endian userspace.
+
+config CPU_LITTLE_ENDIAN
+	bool "Build little-endian kernel"
+	help
+	  Say Y if you plan on running a kernel with a little-endian userspace.
+	  This is usually the case for distributions targeting arm64.
+
+endchoice
 
 config SCHED_MC
 	bool "Multi-core scheduler support"
@@ -1580,6 +1645,7 @@ config CMDLINE
 
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
+	depends on CMDLINE != ""
 	help
 	  Always use the default kernel command string, even if the boot
 	  loader passes other arguments to the kernel.
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2c0238ce0551..1fbe24d4fdb6 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDS_MODULE	+= $(srctree)/arch/arm64/kernel/module.lds
 endif
 
+ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
+  KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+  CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
index 24f1aac366d6..d5b6e8159a33 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
@@ -63,3 +63,12 @@
 		reg = <1>;
 	};
 };
+
+&reg_dc1sw {
+	/*
+	 * Ethernet PHY needs 30ms to properly power up and some more
+	 * to initialize. 100ms should be plenty of time to finish
+	 * whole process.
+	 */
+	regulator-enable-ramp-delay = <100000>;
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
index e6fb9683f213..25099202c52c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
@@ -159,6 +159,12 @@
 };
 
 &reg_dc1sw {
+	/*
+	 * Ethernet PHY needs 30ms to properly power up and some more
+	 * to initialize. 100ms should be plenty of time to finish
+	 * whole process.
+	 */
+	regulator-enable-ramp-delay = <100000>;
 	regulator-name = "vcc-phy";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 3eccbdba7154..70f4cce6be43 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -142,15 +142,6 @@
 		clock-output-names = "ext-osc32k";
 	};
 
-	pmu {
-		compatible = "arm,cortex-a53-pmu";
-		interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
-	};
-
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
index 8a3a770e8f2c..56789ccf9454 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
@@ -42,13 +42,14 @@
 
 		pinmux: pinmux@14029c {
 			compatible = "pinctrl-single";
-			reg = <0x0014029c 0x250>;
+			reg = <0x0014029c 0x26c>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			pinctrl-single,register-width = <32>;
 			pinctrl-single,function-mask = <0xf>;
 			pinctrl-single,gpio-range = <
-				&range 0 154 MODE_GPIO
+				&range 0  91 MODE_GPIO
+				&range 95 60 MODE_GPIO
 				>;
 			range: gpio-range {
 				#pinctrl-single,gpio-range-cells = <3>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index 71e2e34400d4..0098dfdef96c 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -464,8 +464,7 @@
 					<&pinmux 108 16 27>,
 					<&pinmux 135 77 6>,
 					<&pinmux 141 67 4>,
-					<&pinmux 145 149 6>,
-					<&pinmux 151 91 4>;
+					<&pinmux 145 149 6>;
 		};
 
 		i2c1: i2c@e0000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
index d98346da01df..078a5010228c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
@@ -127,7 +127,7 @@
 	status = "okay";
 
 	i2c-mux@77 {
-		compatible = "nxp,pca9847";
+		compatible = "nxp,pca9547";
 		reg = <0x77>;
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 408e0ecdce6a..b032f3890c8c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -33,7 +33,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster0_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@1 {
@@ -49,7 +49,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster0_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@100 {
@@ -65,7 +65,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster1_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@101 {
@@ -81,7 +81,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster1_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@200 {
@@ -97,7 +97,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster2_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@201 {
@@ -113,7 +113,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster2_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@300 {
@@ -129,7 +129,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster3_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@301 {
@@ -145,7 +145,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster3_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@400 {
@@ -161,7 +161,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster4_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@401 {
@@ -177,7 +177,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster4_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@500 {
@@ -193,7 +193,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster5_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@501 {
@@ -209,7 +209,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster5_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@600 {
@@ -225,7 +225,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster6_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@601 {
@@ -241,7 +241,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster6_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@700 {
@@ -257,7 +257,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster7_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@701 {
@@ -273,7 +273,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster7_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cluster0_l2: l2-cache0 {
@@ -340,9 +340,9 @@
 			cache-level = <2>;
 		};
 
-		cpu_pw20: cpu-pw20 {
+		cpu_pw15: cpu-pw15 {
 			compatible = "arm,idle-state";
-			idle-state-name = "PW20";
+			idle-state-name = "PW15";
 			arm,psci-suspend-param = <0x0>;
 			entry-latency-us = <2000>;
 			exit-latency-us = <2000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index 5f9d0da196e1..23c8fad7932b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -394,7 +394,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>,
@@ -405,7 +405,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>,
@@ -694,7 +694,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -710,7 +710,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -724,7 +724,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b60000 0x10000>;
 				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC3_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -737,7 +737,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 785f4c420fa4..43c4db312146 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -288,7 +288,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>,
@@ -299,7 +299,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>,
@@ -569,7 +569,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -585,7 +585,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -599,7 +599,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b60000 0x10000>;
 				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC3_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -612,7 +612,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
index af99473ada04..32ce14936b01 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
@@ -88,9 +88,9 @@
 		regulator-name = "0V9_ARM";
 		regulator-min-microvolt = <900000>;
 		regulator-max-microvolt = <1000000>;
-		gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
-		states = <1000000 0x0
-		           900000 0x1>;
+		gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+		states = <1000000 0x1
+		           900000 0x0>;
 		regulator-always-on;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 04115ca6bfb5..55a3d1c4bdf0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -850,7 +850,7 @@
 				             "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MQ_CLK_DUMMY>,
+				clocks = <&clk IMX8MQ_CLK_IPG_ROOT>,
 				         <&clk IMX8MQ_CLK_NAND_USDHC_BUS>,
 				         <&clk IMX8MQ_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -867,7 +867,7 @@
 				             "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MQ_CLK_DUMMY>,
+				clocks = <&clk IMX8MQ_CLK_IPG_ROOT>,
 				         <&clk IMX8MQ_CLK_NAND_USDHC_BUS>,
 				         <&clk IMX8MQ_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index d105986c6be1..5f350cc71a2f 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -60,11 +60,6 @@
 		gpio = <&gpiosb 0 GPIO_ACTIVE_HIGH>;
 	};
 
-	usb3_phy: usb3-phy {
-		compatible = "usb-nop-xceiv";
-		vcc-supply = <&exp_usb3_vbus>;
-	};
-
 	vsdc_reg: vsdc-reg {
 		compatible = "regulator-gpio";
 		regulator-name = "vsdc";
@@ -255,10 +250,16 @@
 	status = "okay";
 };
 
+&comphy2 {
+	connector {
+		compatible = "usb-a-connector";
+		phy-supply = <&exp_usb3_vbus>;
+	};
+};
+
 &usb3 {
 	status = "okay";
 	phys = <&comphy2 0>;
-	usb-phy = <&usb3_phy>;
 };
 
 &mdio {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
index e152b0ca0290..b8066868a3fe 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
@@ -44,7 +44,7 @@
 		power-supply = <&pp3300_disp>;
 
 		panel-timing {
-			clock-frequency = <266604720>;
+			clock-frequency = <266666667>;
 			hactive = <2400>;
 			hfront-porch = <48>;
 			hback-porch = <84>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
index 0d1f5f9a0de9..c133e8d64b2a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
@@ -644,7 +644,7 @@
 	status = "okay";
 
 	u2phy0_host: host-port {
-		phy-supply = <&vcc5v0_host>;
+		phy-supply = <&vcc5v0_typec>;
 		status = "okay";
 	};
 
@@ -712,7 +712,7 @@
 
 &usbdrd_dwc3_0 {
 	status = "okay";
-	dr_mode = "otg";
+	dr_mode = "host";
 };
 
 &usbdrd3_1 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
index 0401d4ec1f45..e544deb61d28 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
@@ -173,7 +173,7 @@
 		regulator-always-on;
 		regulator-boot-on;
 		regulator-min-microvolt = <800000>;
-		regulator-max-microvolt = <1400000>;
+		regulator-max-microvolt = <1700000>;
 		vin-supply = <&vcc5v0_sys>;
 	};
 };
@@ -247,8 +247,8 @@
 	rk808: pmic@1b {
 		compatible = "rockchip,rk808";
 		reg = <0x1b>;
-		interrupt-parent = <&gpio1>;
-		interrupts = <21 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 		#clock-cells = <1>;
 		clock-output-names = "xin32k", "rk808-clkout2";
 		pinctrl-names = "default";
@@ -574,7 +574,7 @@
 
 	pmic {
 		pmic_int_l: pmic-int-l {
-			rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>;
+			rockchip,pins = <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 
 		vsel1_gpio: vsel1-gpio {
@@ -624,7 +624,6 @@
 
 &sdmmc {
 	bus-width = <4>;
-	cap-mmc-highspeed;
 	cap-sd-highspeed;
 	cd-gpios = <&gpio0 7 GPIO_ACTIVE_LOW>;
 	disable-wp;
@@ -636,8 +635,7 @@
 
 &sdhci {
 	bus-width = <8>;
-	mmc-hs400-1_8v;
-	mmc-hs400-enhanced-strobe;
+	mmc-hs200-1_8v;
 	non-removable;
 	status = "okay";
 };
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index f74909ba29bd..f68a0e64482a 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -58,30 +58,4 @@ alternative_else_nop_endif
 	.endm
 #endif
 
-/*
- * These macros are no-ops when UAO is present.
- */
-	.macro	uaccess_disable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_disable \tmp1, \tmp2
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(1)
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_enable_not_uao, tmp1, tmp2, tmp3
-	uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(0)
-alternative_else_nop_endif
-	.endm
-
-/*
- * Remove the address tag from a virtual address, if present.
- */
-	.macro	clear_address_tag, dst, addr
-	tst	\addr, #(1 << 55)
-	bic	\dst, \addr, #(0xff << 56)
-	csel	\dst, \dst, \addr, eq
-	.endm
-
 #endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index e0e2b1946f42..7d9cc5ec4971 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -29,6 +29,18 @@
 						 SB_BARRIER_INSN"nop\n",	\
 						 ARM64_HAS_SB))
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+#define pmr_sync()						\
+	do {							\
+		extern struct static_key_false gic_pmr_sync;	\
+								\
+		if (static_branch_unlikely(&gic_pmr_sync))	\
+			dsb(sy);				\
+	} while(0)
+#else
+#define pmr_sync()	do {} while (0)
+#endif
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 43da6dd29592..806e9dc2a852 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -11,6 +11,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -18,7 +19,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f19fe4b9acc4..b92683871119 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -52,7 +52,11 @@
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
 #define ARM64_HAS_DCPODP			43
 #define ARM64_WORKAROUND_1463225		44
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
+#define ARM64_WORKAROUND_1542419		47
+#define ARM64_WORKAROUND_1319367		48
 
-#define ARM64_NCAPS				45
+#define ARM64_NCAPS				49
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9cde5d2e768f..4261d55e8506 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
 	default: return CONFIG_ARM64_PA_BITS;
 	}
 }
+
+/* Check whether hardware update of the Access flag is supported */
+static inline bool cpu_has_hw_af(void)
+{
+	u64 mmfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
+		return false;
+
+	mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(mmfr1,
+						ID_AA64MMFR1_HADBS_SHIFT);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index b1454d117cd2..aca07c2f6e6e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -79,6 +79,7 @@
 #define CAVIUM_CPU_PART_THUNDERX_83XX	0x0A3
 #define CAVIUM_CPU_PART_THUNDERX2	0x0AF
 
+#define BRCM_CPU_PART_BRAHMA_B53	0x100
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define QCOM_CPU_PART_FALKOR_V1		0x800
@@ -105,6 +106,7 @@
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
 #define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53)
 #define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 063c964af705..72acd2db167f 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -8,7 +8,9 @@
 #include <linux/irqflags.h>
 
 #include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
+#include <asm/ptrace.h>
 
 #define DAIF_PROCCTX		0
 #define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
@@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags)
 
 		if (system_uses_irq_prio_masking()) {
 			gic_write_pmr(GIC_PRIO_IRQON);
-			dsb(sy);
+			pmr_sync();
 		}
 	} else if (system_uses_irq_prio_masking()) {
 		u64 pmr;
@@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags)
 		trace_hardirqs_off();
 }
 
+/*
+ * Called by synchronous exception handlers to restore the DAIF bits that were
+ * modified by taking an exception.
+ */
+static inline void local_daif_inherit(struct pt_regs *regs)
+{
+	unsigned long flags = regs->pstate & DAIF_MASK;
+
+	/*
+	 * We can't use local_daif_restore(regs->pstate) here as
+	 * system_has_prio_mask_debugging() won't restore the I bit if it can
+	 * use the pmr instead.
+	 */
+	write_sysreg(flags, daif);
+}
 #endif
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index a17393ff6677..4d5f3b5f50cd 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -8,14 +8,15 @@
 #define __ASM_EXCEPTION_H
 
 #include <asm/esr.h>
+#include <asm/kprobes.h>
+#include <asm/ptrace.h>
 
 #include <linux/interrupt.h>
 
-#define __exception	__attribute__((section(".exception.text")))
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define __exception_irq_entry	__irq_entry
 #else
-#define __exception_irq_entry	__exception
+#define __exception_irq_entry	__kprobes
 #endif
 
 static inline u32 disr_to_esr(u64 disr)
@@ -31,5 +32,22 @@ static inline u32 disr_to_esr(u64 disr)
 }
 
 asmlinkage void enter_from_user_mode(void);
+void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void do_undefinstr(struct pt_regs *regs);
+asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+			struct pt_regs *regs);
+void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
+void do_sve_acc(unsigned int esr, struct pt_regs *regs);
+void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
+void do_sysinstr(unsigned int esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
+void do_cp15instr(unsigned int esr, struct pt_regs *regs);
+void el0_svc_handler(struct pt_regs *regs);
+void el0_svc_compat_handler(struct pt_regs *regs);
+void do_el0_ia_bp_hardening(unsigned long addr,  unsigned int esr,
+			    struct pt_regs *regs);
 
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index d48667b04c41..91fa4baa1a93 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -11,9 +11,20 @@
 #include <asm/insn.h>
 
 #define HAVE_FUNCTION_GRAPH_FP_TEST
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#else
 #define MCOUNT_ADDR		((unsigned long)_mcount)
+#endif
+
+/* The BL at the callsite's adjusted rec->ip */
 #define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
 
+#define FTRACE_PLT_IDX		0
+#define FTRACE_REGS_PLT_IDX	1
+#define NR_FTRACE_PLTS		2
+
 /*
  * Currently, gcc tends to save the link register after the local variables
  * on the stack. This causes the max stack tracer to report the function
@@ -44,12 +55,24 @@ extern void return_to_handler(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
+	 * Adjust addr to point at the BL in the callsite.
+	 * See ftrace_init_nop() for the callsite sequence.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		return addr + AARCH64_INSN_SIZE;
+	/*
 	 * addr is the address of the mcount call instruction.
 	 * recordmcount does the necessary offset calculation.
 	 */
 	return addr;
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct dyn_ftrace;
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+#endif
+
 #define ftrace_return_address(n) return_address(n)
 
 /*
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 39e7780bedd6..bb313dde58a4 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant);
 u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
 				       enum aarch64_insn_variant variant,
 				       enum aarch64_insn_register Rn,
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 1a59f0ed1ae3..aa4b6521ef14 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -6,6 +6,7 @@
 #define __ASM_IRQFLAGS_H
 
 #include <asm/alternative.h>
+#include <asm/barrier.h>
 #include <asm/ptrace.h>
 #include <asm/sysreg.h>
 
@@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void)
 	}
 
 	asm volatile(ALTERNATIVE(
-		"msr	daifclr, #2		// arch_local_irq_enable\n"
-		"nop",
-		__msr_s(SYS_ICC_PMR_EL1, "%0")
-		"dsb	sy",
+		"msr	daifclr, #2		// arch_local_irq_enable",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" ((unsigned long) GIC_PRIO_IRQON)
 		: "memory");
+
+	pmr_sync();
 }
 
 static inline void arch_local_irq_disable(void)
@@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void)
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(ALTERNATIVE(
-			"msr	daif, %0\n"
-			"nop",
-			__msr_s(SYS_ICC_PMR_EL1, "%0")
-			"dsb	sy",
-			ARM64_HAS_IRQ_PRIO_MASKING)
+		"msr	daif, %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
+		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" (flags)
 		: "memory");
+
+	pmr_sync();
 }
 
 #endif /* __ASM_IRQFLAGS_H */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f656169db8c3..5ecb091c8576 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -600,8 +600,7 @@ static inline void kvm_arm_vhe_guest_enter(void)
 	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
 	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
 	 */
-	if (system_uses_irq_prio_masking())
-		dsb(sy);
+	pmr_sync();
 }
 
 static inline void kvm_arm_vhe_guest_exit(void)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b61b50bf68b1..a4f9ca5479b0 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -69,12 +69,6 @@
 #define KERNEL_START		_text
 #define KERNEL_END		_end
 
-#ifdef CONFIG_ARM64_VA_BITS_52
-#define MAX_USER_VA_BITS	52
-#else
-#define MAX_USER_VA_BITS	VA_BITS
-#endif
-
 /*
  * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual
  * address space for the shadow region respectively. They can bloat the stack
@@ -215,12 +209,18 @@ static inline unsigned long kaslr_offset(void)
  * up with a tagged userland pointer. Clear the tag to get a sane pointer to
  * pass on to access_ok(), for instance.
  */
-#define untagged_addr(addr)	\
+#define __untagged_addr(addr)	\
 	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
+#define untagged_addr(addr)	({					\
+	u64 __addr = (__force u64)addr;					\
+	__addr &= __untagged_addr(__addr);				\
+	(__force __typeof__(addr))__addr;				\
+})
+
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
-#define __tag_reset(addr)	untagged_addr(addr)
+#define __tag_reset(addr)	__untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
 #else
 #define __tag_shifted(tag)	0UL
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index f80e13cbf8ec..1e93de68c044 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -21,7 +21,7 @@ struct mod_arch_specific {
 	struct mod_plt_sec	init;
 
 	/* for CONFIG_DYNAMIC_FTRACE */
-	struct plt_entry 	*ftrace_trampoline;
+	struct plt_entry	*ftrace_trampolines;
 };
 #endif
 
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 3df60f97da1f..d9fbd433cc17 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -69,7 +69,7 @@
 #define PGDIR_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
 #define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE-1))
-#define PTRS_PER_PGD		(1 << (MAX_USER_VA_BITS - PGDIR_SHIFT))
+#define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
 
 /*
  * Section address mask and size definitions.
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 9a21b84536f2..8dc6c5cdabe6 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -32,11 +32,11 @@
 #define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
 #define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -80,8 +80,9 @@
 #define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
+/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */
+#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
 #define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7576df00eb50..5d15b4735a0e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -17,7 +17,7 @@
  * VMALLOC range.
  *
  * VMALLOC_START: beginning of the kernel vmalloc space
- * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space
+ * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space
  *	and fixed mappings
  */
 #define VMALLOC_START		(MODULES_END)
@@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pte);
 }
 
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t pte_a, pte_t pte_b)
-{
-	pteval_t lhs, rhs;
-
-	lhs = pte_val(pte_a);
-	rhs = pte_val(pte_b);
-
-	if (pte_present(pte_a))
-		lhs &= ~PTE_RDONLY;
-
-	if (pte_present(pte_b))
-		rhs &= ~PTE_RDONLY;
-
-	return (lhs == rhs);
-}
-
 /*
  * Huge pte definitions.
  */
@@ -876,15 +859,26 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
-#define kc_vaddr_to_offset(v)	((v) & ~PAGE_END)
-#define kc_offset_to_vaddr(o)	((o) | PAGE_END)
-
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
 #else
 #define phys_to_ttbr(addr)	(addr)
 #endif
 
+/*
+ * On arm64 without hardware Access Flag, copying from user will fail because
+ * the pte is old and cannot be marked young. So we always end up with zeroed
+ * page after fork() + CoW for pfn mappings. We don't always have a
+ * hardware-managed access flag on arm64.
+ */
+static inline bool arch_faults_on_old_pte(void)
+{
+	WARN_ON(preemptible());
+
+	return !cpu_has_hw_af();
+}
+#define arch_faults_on_old_pte arch_faults_on_old_pte
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5623685c7d13..5ba63204d078 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -9,7 +9,7 @@
 #define __ASM_PROCESSOR_H
 
 #define KERNEL_DS		UL(-1)
-#define USER_DS			((UL(1) << MAX_USER_VA_BITS) - 1)
+#define USER_DS			((UL(1) << VA_BITS) - 1)
 
 /*
  * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
@@ -26,10 +26,12 @@
 #include <linux/init.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
+#include <linux/thread_info.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/kasan.h>
 #include <asm/lse.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pointer_auth.h>
@@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->sp = sp;
 }
 
+static inline bool is_ttbr0_addr(unsigned long addr)
+{
+	/* entry assembly clears tags for TTBR0 addrs */
+	return addr < TASK_SIZE;
+}
+
+static inline bool is_ttbr1_addr(unsigned long addr)
+{
+	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
+	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
+}
+
 #ifdef CONFIG_COMPAT
 static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
index 06d880b3526c..b383b4802a7b 100644
--- a/arch/arm64/include/asm/syscall_wrapper.h
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -66,24 +66,18 @@ struct pt_regs;
 	}									\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
-#ifndef SYSCALL_DEFINE0
 #define SYSCALL_DEFINE0(sname)							\
 	SYSCALL_METADATA(_##sname, 0);						\
 	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused);	\
 	ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO);			\
 	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused)
-#endif
 
-#ifndef COND_SYSCALL
 #define COND_SYSCALL(name)							\
 	asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs)	\
 	{									\
 		return sys_ni_syscall();					\
 	}
-#endif
 
-#ifndef SYS_NI
 #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
-#endif
 
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 972d196c7714..6e919fafb43d 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -212,7 +212,7 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
-#define SYS_PAR_EL1_F			BIT(1)
+#define SYS_PAR_EL1_F			BIT(0)
 #define SYS_PAR_EL1_FST			GENMASK(6, 1)
 
 /*** Statistical Profiling Extension ***/
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 59690613ac31..cee5928e1b7d 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
 
-static inline int in_exception_text(unsigned long ptr)
-{
-	int in;
-
-	in = ptr >= (unsigned long)&__exception_text_start &&
-	     ptr < (unsigned long)&__exception_text_end;
-
-	return in ? : __in_irqentry_text(ptr);
-}
-
 static inline int in_entry_text(unsigned long ptr)
 {
 	return ptr >= (unsigned long)&__entry_text_start &&
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 097d6bfac0b7..127712b0b970 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -378,20 +378,34 @@ do {									\
 extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
 #define raw_copy_from_user(to, from, n)					\
 ({									\
-	__arch_copy_from_user((to), __uaccess_mask_ptr(from), (n));	\
+	unsigned long __acfu_ret;					\
+	uaccess_enable_not_uao();					\
+	__acfu_ret = __arch_copy_from_user((to),			\
+				      __uaccess_mask_ptr(from), (n));	\
+	uaccess_disable_not_uao();					\
+	__acfu_ret;							\
 })
 
 extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
 #define raw_copy_to_user(to, from, n)					\
 ({									\
-	__arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n));	\
+	unsigned long __actu_ret;					\
+	uaccess_enable_not_uao();					\
+	__actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to),	\
+				    (from), (n));			\
+	uaccess_disable_not_uao();					\
+	__actu_ret;							\
 })
 
 extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n);
 #define raw_copy_in_user(to, from, n)					\
 ({									\
-	__arch_copy_in_user(__uaccess_mask_ptr(to),			\
-			    __uaccess_mask_ptr(from), (n));		\
+	unsigned long __aciu_ret;					\
+	uaccess_enable_not_uao();					\
+	__aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to),	\
+				    __uaccess_mask_ptr(from), (n));	\
+	uaccess_disable_not_uao();					\
+	__aciu_ret;							\
 })
 
 #define INLINE_COPY_TO_USER
@@ -400,8 +414,11 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi
 extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n);
 static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n)
 {
-	if (access_ok(to, n))
+	if (access_ok(to, n)) {
+		uaccess_enable_not_uao();
 		n = __arch_clear_user(__uaccess_mask_ptr(to), n);
+		uaccess_disable_not_uao();
+	}
 	return n;
 }
 #define clear_user	__clear_user
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index 0c731bfc7c8c..0c20a7c1bee5 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -31,13 +31,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk)
 #define __arch_get_clock_mode __arm64_get_clock_mode
 
 static __always_inline
-int __arm64_use_vsyscall(struct vdso_data *vdata)
-{
-	return !vdata[CS_HRES_COARSE].clock_mode;
-}
-#define __arch_use_vsyscall __arm64_use_vsyscall
-
-static __always_inline
 void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
 {
 	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 478491f07b4f..fc6488660f64 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
-			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
-			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o	\
+			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
+			   setup.o signal.o sys.o stacktrace.o time.o traps.o	\
+			   io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 214685760e1c..a5bdce8af65b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -56,6 +56,7 @@ int main(void)
   DEFINE(S_X24,			offsetof(struct pt_regs, regs[24]));
   DEFINE(S_X26,			offsetof(struct pt_regs, regs[26]));
   DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
+  DEFINE(S_FP,			offsetof(struct pt_regs, regs[29]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
   DEFINE(S_PSTATE,		offsetof(struct pt_regs, pstate));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index f593f4cffc0d..bbdc95ee4642 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -6,12 +6,12 @@
  */
 
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/smp_plat.h>
 
 static bool __maybe_unused
 is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
@@ -87,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -166,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-#include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
-#include <linux/psci.h>
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -212,11 +218,8 @@ static int detect_harden_bp_fw(void)
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return -1;
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		switch ((int)res.a0) {
@@ -234,7 +237,7 @@ static int detect_harden_bp_fw(void)
 		}
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		switch ((int)res.a0) {
@@ -308,11 +311,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 1);
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		insn = aarch64_insn_get_hvc_value();
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		insn = aarch64_insn_get_smc_value();
 		break;
 	default:
@@ -351,12 +354,12 @@ void arm64_set_ssbd_mitigation(bool state)
 		return;
 	}
 
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
 		break;
 
@@ -390,20 +393,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		goto out_printmsg;
 	}
 
-	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
-		ssbd_state = ARM64_SSBD_UNKNOWN;
-		if (!this_cpu_safe)
-			__ssb_safe = false;
-		return false;
-	}
-
-	switch (psci_ops.conduit) {
-	case PSCI_CONDUIT_HVC:
+	switch (arm_smccc_1_1_get_conduit()) {
+	case SMCCC_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 		break;
 
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_2, &res);
 		break;
@@ -488,6 +484,7 @@ static const struct midr_range arm64_ssb_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 	{},
 };
 
@@ -572,6 +569,7 @@ static const struct midr_range spectre_v2_safe_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 	{ /* sentinel */ }
 };
 
@@ -623,9 +621,45 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+static const __maybe_unused struct midr_range tx2_family_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+	{},
+};
+
+static bool __maybe_unused
+needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
+			 int scope)
+{
+	int i;
+
+	if (!is_affected_midr_range_list(entry, scope) ||
+	    !is_hyp_mode_available())
+		return false;
+
+	for_each_possible_cpu(i) {
+		if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0)
+			return true;
+	}
 
-static const struct midr_range arm64_harden_el2_vectors[] = {
+	return false;
+}
+
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
+#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367)
+
+static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 	{},
@@ -634,17 +668,23 @@ static const struct midr_range arm64_harden_el2_vectors[] = {
 #endif
 
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
-
-static const struct midr_range arm64_repeat_tlbi_cpus[] = {
+static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
-	MIDR_RANGE(MIDR_QCOM_FALKOR_V1, 0, 0, 0, 0),
+	{
+		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0)
+	},
+	{
+		.midr_range.model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1286807
-	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	{
+		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
 #endif
 	{},
 };
-
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
@@ -712,6 +752,33 @@ static const struct midr_range erratum_1418040_list[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_845719
+static const struct midr_range erratum_845719_list[] = {
+	/* Cortex-A53 r0p[01234] */
+	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+	/* Brahma-B53 r0p[0] */
+	MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	{},
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_843419
+static const struct arm64_cpu_capabilities erratum_843419_list[] = {
+	{
+		/* Cortex-A53 r0p[01234] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		MIDR_FIXED(0x4, BIT(8)),
+	},
+	{
+		/* Brahma-B53 r0p[0] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	},
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -743,19 +810,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_843419
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 843419",
 		.capability = ARM64_WORKAROUND_843419,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
-		MIDR_FIXED(0x4, BIT(8)),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = erratum_843419_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 845719",
 		.capability = ARM64_WORKAROUND_845719,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		ERRATA_MIDR_RANGE_LIST(erratum_845719_list),
 	},
 #endif
 #ifdef CONFIG_CAVIUM_ERRATUM_23154
@@ -791,6 +857,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Qualcomm Technologies Falkor/Kryo erratum 1003",
 		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = cpucap_multi_entry_cap_matches,
 		.match_list = qcom_erratum_1003_list,
 	},
@@ -799,7 +866,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Qualcomm erratum 1009, ARM erratum 1286807",
 		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
-		ERRATA_MIDR_RANGE_LIST(arm64_repeat_tlbi_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = arm64_repeat_tlbi_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_858921
@@ -819,7 +888,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
-		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
 	},
 #endif
 	{
@@ -852,6 +921,36 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.matches = has_cortex_a76_erratum_1463225,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+		.matches = needs_tx2_tvm_workaround,
+	},
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (PRFM removal)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1319367
+	{
+		.desc = "ARM erratum 1319367",
+		.capability = ARM64_WORKAROUND_1319367,
+		ERRATA_MIDR_RANGE_LIST(ca57_a72),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index cabebf1a7976..04cf64e9f0c9 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -176,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -977,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 05933c065732..56bba746da1c 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_cntfrq = arch_timer_get_cntfrq();
 	/*
 	 * Use the effective value of the CTR_EL0 than the raw value
-	 * exposed by the CPU. CTR_E0.IDC field value must be interpreted
+	 * exposed by the CPU. CTR_EL0.IDC field value must be interpreted
 	 * with the CLIDR_EL1 fields to avoid triggering false warnings
 	 * when there is a mismatch across the CPUs. Keep track of the
 	 * effective value of the CTR_EL0 in our internal records for
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
new file mode 100644
index 000000000000..5dce5e56995a
--- /dev/null
+++ b/arch/arm64/kernel/entry-common.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exception handling code
+ *
+ * Copyright (C) 2019 ARM Ltd.
+ */
+
+#include <linux/context_tracking.h>
+#include <linux/ptrace.h>
+#include <linux/thread_info.h>
+
+#include <asm/cpufeature.h>
+#include <asm/daifflags.h>
+#include <asm/esr.h>
+#include <asm/exception.h>
+#include <asm/kprobes.h>
+#include <asm/mmu.h>
+#include <asm/sysreg.h>
+
+static void notrace el1_abort(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_abort);
+
+static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	local_daif_inherit(regs);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_pc);
+
+static void el1_undef(struct pt_regs *regs)
+{
+	local_daif_inherit(regs);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el1_undef);
+
+static void el1_inv(struct pt_regs *regs, unsigned long esr)
+{
+	local_daif_inherit(regs);
+	bad_mode(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el1_inv);
+
+static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * The CPU masked interrupts, and we are leaving them masked during
+	 * do_debug_exception(). Update PMR as if we had called
+	 * local_mask_daif().
+	 */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	do_debug_exception(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el1_dbg);
+
+asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_DABT_CUR:
+	case ESR_ELx_EC_IABT_CUR:
+		el1_abort(regs, esr);
+		break;
+	/*
+	 * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a
+	 * recursive exception when trying to push the initial pt_regs.
+	 */
+	case ESR_ELx_EC_PC_ALIGN:
+		el1_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_UNKNOWN:
+		el1_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_CUR:
+	case ESR_ELx_EC_SOFTSTP_CUR:
+	case ESR_ELx_EC_WATCHPT_CUR:
+	case ESR_ELx_EC_BRK64:
+		el1_dbg(regs, esr);
+		break;
+	default:
+		el1_inv(regs, esr);
+	};
+}
+NOKPROBE_SYMBOL(el1_sync_handler);
+
+static void notrace el0_da(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	far = untagged_addr(far);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_da);
+
+static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (!is_ttbr0_addr(far))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_mem_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_ia);
+
+static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_acc);
+
+static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sve_acc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sve_acc);
+
+static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_fpsimd_exc(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_fpsimd_exc);
+
+static void notrace el0_sys(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sysinstr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sys);
+
+static void notrace el0_pc(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long far = read_sysreg(far_el1);
+
+	if (!is_ttbr0_addr(instruction_pointer(regs)))
+		arm64_apply_bp_hardening();
+
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_sp_pc_abort(far, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_pc);
+
+static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	do_sp_pc_abort(regs->sp, esr, regs);
+}
+NOKPROBE_SYMBOL(el0_sp);
+
+static void notrace el0_undef(struct pt_regs *regs)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_undefinstr(regs);
+}
+NOKPROBE_SYMBOL(el0_undef);
+
+static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	bad_el0_sync(regs, 0, esr);
+}
+NOKPROBE_SYMBOL(el0_inv);
+
+static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
+{
+	/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
+	unsigned long far = read_sysreg(far_el1);
+
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	user_exit_irqoff();
+	do_debug_exception(far, esr, regs);
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+}
+NOKPROBE_SYMBOL(el0_dbg);
+
+static void notrace el0_svc(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc);
+
+asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC64:
+		el0_svc(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_SVE:
+		el0_sve_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC64:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_SYS64:
+	case ESR_ELx_EC_WFx:
+		el0_sys(regs, esr);
+		break;
+	case ESR_ELx_EC_SP_ALIGN:
+		el0_sp(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BRK64:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_handler);
+
+#ifdef CONFIG_COMPAT
+static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_cp15instr(esr, regs);
+}
+NOKPROBE_SYMBOL(el0_cp15);
+
+static void notrace el0_svc_compat(struct pt_regs *regs)
+{
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	el0_svc_compat_handler(regs);
+}
+NOKPROBE_SYMBOL(el0_svc_compat);
+
+asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_SVC32:
+		el0_svc_compat(regs);
+		break;
+	case ESR_ELx_EC_DABT_LOW:
+		el0_da(regs, esr);
+		break;
+	case ESR_ELx_EC_IABT_LOW:
+		el0_ia(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_ASIMD:
+		el0_fpsimd_acc(regs, esr);
+		break;
+	case ESR_ELx_EC_FP_EXC32:
+		el0_fpsimd_exc(regs, esr);
+		break;
+	case ESR_ELx_EC_PC_ALIGN:
+		el0_pc(regs, esr);
+		break;
+	case ESR_ELx_EC_UNKNOWN:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_CP14_64:
+		el0_undef(regs);
+		break;
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+		el0_cp15(regs, esr);
+		break;
+	case ESR_ELx_EC_BREAKPT_LOW:
+	case ESR_ELx_EC_SOFTSTP_LOW:
+	case ESR_ELx_EC_WATCHPT_LOW:
+	case ESR_ELx_EC_BKPT32:
+		el0_dbg(regs, esr);
+		break;
+	default:
+		el0_inv(regs, esr);
+	}
+}
+NOKPROBE_SYMBOL(el0_sync_compat_handler);
+#endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 33d003d80121..4fe1514fcbfd 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -7,10 +7,137 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+/*
+ * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
+ * the regular function prologue. For an enabled callsite, ftrace_init_nop() and
+ * ftrace_make_call() have patched those NOPs to:
+ *
+ * 	MOV	X9, LR
+ * 	BL	<entry>
+ *
+ * ... where <entry> is either ftrace_caller or ftrace_regs_caller.
+ *
+ * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are
+ * live, and x9-x18 are safe to clobber.
+ *
+ * We save the callsite's context into a pt_regs before invoking any ftrace
+ * callbacks. So that we can get a sensible backtrace, we create a stack record
+ * for the callsite and the ftrace entry assembly. This is not sufficient for
+ * reliable stacktrace: until we create the callsite stack record, its caller
+ * is missing from the LR and existing chain of frame records.
+ */
+	.macro  ftrace_regs_entry, allregs=0
+	/* Make room for pt_regs, plus a callee frame */
+	sub	sp, sp, #(S_FRAME_SIZE + 16)
+
+	/* Save function arguments (and x9 for simplicity) */
+	stp	x0, x1, [sp, #S_X0]
+	stp	x2, x3, [sp, #S_X2]
+	stp	x4, x5, [sp, #S_X4]
+	stp	x6, x7, [sp, #S_X6]
+	stp	x8, x9, [sp, #S_X8]
+
+	/* Optionally save the callee-saved registers, always save the FP */
+	.if \allregs == 1
+	stp	x10, x11, [sp, #S_X10]
+	stp	x12, x13, [sp, #S_X12]
+	stp	x14, x15, [sp, #S_X14]
+	stp	x16, x17, [sp, #S_X16]
+	stp	x18, x19, [sp, #S_X18]
+	stp	x20, x21, [sp, #S_X20]
+	stp	x22, x23, [sp, #S_X22]
+	stp	x24, x25, [sp, #S_X24]
+	stp	x26, x27, [sp, #S_X26]
+	stp	x28, x29, [sp, #S_X28]
+	.else
+	str	x29, [sp, #S_FP]
+	.endif
+
+	/* Save the callsite's SP and LR */
+	add	x10, sp, #(S_FRAME_SIZE + 16)
+	stp	x9, x10, [sp, #S_LR]
+
+	/* Save the PC after the ftrace callsite */
+	str	x30, [sp, #S_PC]
+
+	/* Create a frame record for the callsite above pt_regs */
+	stp	x29, x9, [sp, #S_FRAME_SIZE]
+	add	x29, sp, #S_FRAME_SIZE
+
+	/* Create our frame record within pt_regs. */
+	stp	x29, x30, [sp, #S_STACKFRAME]
+	add	x29, sp, #S_STACKFRAME
+	.endm
+
+ENTRY(ftrace_regs_caller)
+	ftrace_regs_entry	1
+	b	ftrace_common
+ENDPROC(ftrace_regs_caller)
+
+ENTRY(ftrace_caller)
+	ftrace_regs_entry	0
+	b	ftrace_common
+ENDPROC(ftrace_caller)
+
+ENTRY(ftrace_common)
+	sub	x0, x30, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
+	mov	x1, x9				// parent_ip (callsite's LR)
+	ldr_l	x2, function_trace_op		// op
+	mov	x3, sp				// regs
+
+GLOBAL(ftrace_call)
+	bl	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+/*
+ * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
+ * x19-x29 per the AAPCS, and we created frame records upon entry, so we need
+ * to restore x0-x8, x29, and x30.
+ */
+ftrace_common_return:
+	/* Restore function arguments */
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #S_X2]
+	ldp	x4, x5, [sp, #S_X4]
+	ldp	x6, x7, [sp, #S_X6]
+	ldr	x8, [sp, #S_X8]
+
+	/* Restore the callsite's FP, LR, PC */
+	ldr	x29, [sp, #S_FP]
+	ldr	x30, [sp, #S_LR]
+	ldr	x9, [sp, #S_PC]
+
+	/* Restore the callsite's SP */
+	add	sp, sp, #S_FRAME_SIZE + 16
+
+	ret	x9
+ENDPROC(ftrace_common)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	ldr	x0, [sp, #S_PC]
+	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
+	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
+	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	bl	prepare_ftrace_return
+	b	ftrace_common_return
+ENDPROC(ftrace_graph_caller)
+#else
+#endif
+
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
 /*
  * Gcc with -pg will put the following code in the beginning of each function:
  *      mov x0, x30
@@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
 
 	mcount_exit
 ENDPROC(ftrace_caller)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(ftrace_stub)
-	ret
-ENDPROC(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller)
 
 	mcount_exit
 ENDPROC(ftrace_graph_caller)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * void return_to_handler(void)
  *
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e304fe04b098..583f71abbe98 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -269,8 +269,10 @@ alternative_else_nop_endif
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	ldr	x20, [sp, #S_PMR_SAVE]
 	msr_s	SYS_ICC_PMR_EL1, x20
-	/* Ensure priority change is seen by redistributor */
-	dsb	sy
+	mrs_s	x21, SYS_ICC_CTLR_EL1
+	tbz	x21, #6, .L__skip_pmr_sync\@	// Check for ICC_CTLR_EL1.PMHE
+	dsb	sy				// Ensure priority change is seen by redistributor
+.L__skip_pmr_sync\@:
 alternative_else_nop_endif
 
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
@@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid)
 	.align	6
 el1_sync:
 	kernel_entry 1
-	mrs	x1, esr_el1			// read the syndrome register
-	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
-	b.eq	el1_da
-	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
-	b.eq	el1_ia
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el1_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL1
-	b.eq	el1_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
-	b.ge	el1_dbg
-	b	el1_inv
-
-el1_ia:
-	/*
-	 * Fall through to the Data abort case
-	 */
-el1_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x3, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	clear_address_tag x0, x3
-	mov	x2, sp				// struct pt_regs
-	bl	do_mem_abort
-
-	kernel_exit 1
-el1_pc:
-	/*
-	 * PC alignment exception handling. We don't handle SP alignment faults,
-	 * since we will have hit a recursive exception when trying to push the
-	 * initial pt_regs.
-	 */
-	mrs	x0, far_el1
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	ASM_BUG()
-el1_undef:
-	/*
-	 * Undefined instruction
-	 */
-	inherit_daif	pstate=x23, tmp=x2
 	mov	x0, sp
-	bl	do_undefinstr
+	bl	el1_sync_handler
 	kernel_exit 1
-el1_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
-	cinc	x24, x24, eq			// set bit '0'
-	tbz	x24, #0, el1_inv		// EL1 only
-	gic_prio_kentry_setup tmp=x3
-	mrs	x0, far_el1
-	mov	x2, sp				// struct pt_regs
-	bl	do_debug_exception
-	kernel_exit 1
-el1_inv:
-	// TODO: add support for undefined instructions in kernel mode
-	inherit_daif	pstate=x23, tmp=x2
-	mov	x0, sp
-	mov	x2, x1
-	mov	x1, #BAD_SYNC
-	bl	bad_mode
-	ASM_BUG()
 ENDPROC(el1_sync)
 
 	.align	6
@@ -680,7 +615,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	orr	x24, x24, x0
 alternative_else_nop_endif
 	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	preempt_schedule_irq		// irq en/disable is done inside
+	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
 1:
 #endif
 
@@ -714,71 +649,18 @@ ENDPROC(el1_irq)
 	.align	6
 el0_sync:
 	kernel_entry 0
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC64		// SVC in 64-bit state
-	b.eq	el0_svc
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_SVE		// SVE access
-	b.eq	el0_sve_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
-	ccmp	x24, #ESR_ELx_EC_WFx, #4, ne
-	b.eq	el0_sys
-	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
-	b.eq	el0_sp
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
+	mov	x0, sp
+	bl	el0_sync_handler
+	b	ret_to_user
 
 #ifdef CONFIG_COMPAT
 	.align	6
 el0_sync_compat:
 	kernel_entry 0, 32
-	mrs	x25, esr_el1			// read the syndrome register
-	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
-	cmp	x24, #ESR_ELx_EC_SVC32		// SVC in 32-bit state
-	b.eq	el0_svc_compat
-	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
-	b.eq	el0_da
-	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
-	b.eq	el0_ia
-	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
-	b.eq	el0_fpsimd_acc
-	cmp	x24, #ESR_ELx_EC_FP_EXC32	// FP/ASIMD exception
-	b.eq	el0_fpsimd_exc
-	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
-	b.eq	el0_pc
-	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP15_32	// CP15 MRC/MCR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP15_64	// CP15 MRRC/MCRR trap
-	b.eq	el0_cp15
-	cmp	x24, #ESR_ELx_EC_CP14_MR	// CP14 MRC/MCR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_LS	// CP14 LDC/STC trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_CP14_64	// CP14 MRRC/MCRR trap
-	b.eq	el0_undef
-	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
-	b.ge	el0_dbg
-	b	el0_inv
-el0_svc_compat:
-	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
-	bl	el0_svc_compat_handler
+	bl	el0_sync_compat_handler
 	b	ret_to_user
+ENDPROC(el0_sync)
 
 	.align	6
 el0_irq_compat:
@@ -788,140 +670,8 @@ el0_irq_compat:
 el0_error_compat:
 	kernel_entry 0, 32
 	b	el0_error_naked
-
-el0_cp15:
-	/*
-	 * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_cp15instr
-	b	ret_to_user
 #endif
 
-el0_da:
-	/*
-	 * Data abort handling
-	 */
-	mrs	x26, far_el1
-	ct_user_exit_irqoff
-	enable_daif
-	clear_address_tag x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_mem_abort
-	b	ret_to_user
-el0_ia:
-	/*
-	 * Instruction abort handling
-	 */
-	mrs	x26, far_el1
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_el0_ia_bp_hardening
-	b	ret_to_user
-el0_fpsimd_acc:
-	/*
-	 * Floating Point or Advanced SIMD access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_acc
-	b	ret_to_user
-el0_sve_acc:
-	/*
-	 * Scalable Vector Extension access
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sve_acc
-	b	ret_to_user
-el0_fpsimd_exc:
-	/*
-	 * Floating Point, Advanced SIMD or SVE exception
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_fpsimd_exc
-	b	ret_to_user
-el0_sp:
-	ldr	x26, [sp, #S_SP]
-	b	el0_sp_pc
-el0_pc:
-	mrs	x26, far_el1
-el0_sp_pc:
-	/*
-	 * Stack or PC alignment exception handling
-	 */
-	gic_prio_kentry_setup tmp=x0
-	ct_user_exit_irqoff
-	enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
-	mov	x0, x26
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_sp_pc_abort
-	b	ret_to_user
-el0_undef:
-	/*
-	 * Undefined instruction
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	bl	do_undefinstr
-	b	ret_to_user
-el0_sys:
-	/*
-	 * System instructions, for trapped cache maintenance instructions
-	 */
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, x25
-	mov	x1, sp
-	bl	do_sysinstr
-	b	ret_to_user
-el0_dbg:
-	/*
-	 * Debug exception handling
-	 */
-	tbnz	x24, #0, el0_inv		// EL0 only
-	mrs	x24, far_el1
-	gic_prio_kentry_setup tmp=x3
-	ct_user_exit_irqoff
-	mov	x0, x24
-	mov	x1, x25
-	mov	x2, sp
-	bl	do_debug_exception
-	enable_da_f
-	b	ret_to_user
-el0_inv:
-	ct_user_exit_irqoff
-	enable_daif
-	mov	x0, sp
-	mov	x1, #BAD_SYNC
-	mov	x2, x25
-	bl	bad_el0_sync
-	b	ret_to_user
-ENDPROC(el0_sync)
-
 	.align	6
 el0_irq:
 	kernel_entry 0
@@ -999,17 +749,6 @@ finish_ret_to_user:
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
-/*
- * SVC handler.
- */
-	.align	6
-el0_svc:
-	gic_prio_kentry_setup tmp=x1
-	mov	x0, sp
-	bl	el0_svc_handler
-	b	ret_to_user
-ENDPROC(el0_svc)
-
 	.popsection				// .entry.text
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
@@ -1071,7 +810,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
 #else
 	ldr	x30, =vectors
 #endif
+alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+alternative_else_nop_endif
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
 	isb
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 37d3912cfe06..3eb338f14386 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task)
  * would have disabled the SVE access trap for userspace during
  * ret_to_user, making an SVE access trap impossible in that case.
  */
-asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
+void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* Even if we chose not to use SVE, the hardware could still trap: */
 	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
@@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Trapped FP/ASIMD access.
  */
-asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 {
 	/* TODO: implement lazy context saving/restoring */
 	WARN_ON(1);
@@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
 /*
  * Raise a SIGFPE for the current process.
  */
-asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
+void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned int si_code = FPE_FLTUNK;
 
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 06e56b470315..8618faa82e6d 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
+{
+#ifdef CONFIG_ARM64_MODULE_PLTS
+	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+
+	if (addr == FTRACE_ADDR)
+		return &plt[FTRACE_PLT_IDX];
+	if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS))
+		return &plt[FTRACE_REGS_PLT_IDX];
+#endif
+	return NULL;
+}
+
 /*
  * Turn on the call to ftrace_caller() in instrumented function
  */
@@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline, *dst;
 		struct module *mod;
+		struct plt_entry *plt;
+
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
 
 		/*
 		 * On kernels that support module PLTs, the offset between the
@@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		if (WARN_ON(!mod))
 			return -EINVAL;
 
-		/*
-		 * There is only one ftrace trampoline per module. For now,
-		 * this is not a problem since on arm64, all dynamic ftrace
-		 * invocations are routed via ftrace_caller(). This will need
-		 * to be revisited if support for multiple ftrace entry points
-		 * is added in the future, but for now, the pr_err() below
-		 * deals with a theoretical issue only.
-		 *
-		 * Note that PLTs are place relative, and plt_entries_equal()
-		 * checks whether they point to the same target. Here, we need
-		 * to check if the actual opcodes are in fact identical,
-		 * regardless of the offset in memory so use memcmp() instead.
-		 */
-		dst = mod->arch.ftrace_trampoline;
-		trampoline = get_plt_entry(addr, dst);
-		if (memcmp(dst, &trampoline, sizeof(trampoline))) {
-			if (plt_entry_is_initialized(dst)) {
-				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
-				return -EINVAL;
-			}
-
-			/* point the trampoline to our ftrace entry point */
-			module_disable_ro(mod);
-			*dst = trampoline;
-			module_enable_ro(mod, true);
-
-			/*
-			 * Ensure updated trampoline is visible to instruction
-			 * fetch before we patch in the branch. Although the
-			 * architecture doesn't require an IPI in this case,
-			 * Neoverse-N1 erratum #1542419 does require one
-			 * if the TLB maintenance in module_enable_ro() is
-			 * skipped due to rodata_enabled. It doesn't seem worth
-			 * it to make it conditional given that this is
-			 * certainly not a fast-path.
-			 */
-			flush_icache_range((unsigned long)&dst[0],
-					   (unsigned long)&dst[1]);
+		plt = get_ftrace_plt(mod, addr);
+		if (!plt) {
+			pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
+			return -EINVAL;
 		}
-		addr = (unsigned long)dst;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
+
+		addr = (unsigned long)plt;
 	}
 
 	old = aarch64_insn_gen_nop();
@@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, old_addr,
+					  AARCH64_INSN_BRANCH_LINK);
+	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * The compiler has inserted two NOPs before the regular function prologue.
+ * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
+ * and x9-x18 are free for our use.
+ *
+ * At runtime we want to be able to swing a single NOP <-> BL to enable or
+ * disable the ftrace call. The BL requires us to save the original LR value,
+ * so here we insert a <MOV X9, LR> over the first NOP so the instructions
+ * before the regular prologue are:
+ *
+ * | Compiled | Disabled   | Enabled    |
+ * +----------+------------+------------+
+ * | NOP      | MOV X9, LR | MOV X9, LR |
+ * | NOP      | NOP        | BL <entry> |
+ *
+ * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * before returning to the regular function prologue. When a function is not
+ * being traced, the MOV is not harmful given x9 is not live per the AAPCS.
+ *
+ * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of
+ * the BL.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
+					AARCH64_INSN_REG_LR,
+					AARCH64_INSN_VARIANT_64BIT);
+	return ftrace_modify_code(pc, old, new, true);
+}
+#endif
+
 /*
  * Turn off the call to ftrace_caller() in instrumented function
  */
@@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	long offset = (long)pc - (long)addr;
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
-#ifdef CONFIG_ARM64_MODULE_PLTS
 		u32 replaced;
 
+		if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+			return -EINVAL;
+
 		/*
 		 * 'mod' is only set at module load time, but if we end up
 		 * dealing with an out-of-range condition, we can assume it
@@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 			return -EINVAL;
 
 		validate = false;
-#else /* CONFIG_ARM64_MODULE_PLTS */
-		return -EINVAL;
-#endif /* CONFIG_ARM64_MODULE_PLTS */
 	} else {
 		old = aarch64_insn_gen_branch_imm(pc, addr,
 						  AARCH64_INSN_BRANCH_LINK);
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index e0a7fce0e01c..a96b2921d22c 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 gfp_t mask)
 {
 	int rc = 0;
+	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
-	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	trans_pgd = allocator(mask);
+	if (!trans_pgd) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = allocator(mask);
 		if (!pudp) {
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index d801a7094076..513b29c3e735 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
 
+/*
+ * MOV (register) is architecturally an alias of ORR (shifted register) where
+ * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m>
+ */
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant)
+{
+	return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR,
+						    src, 0, variant,
+						    AARCH64_INSN_LOGIC_ORR);
+}
+
 u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
 			 enum aarch64_insn_register reg,
 			 enum aarch64_insn_adr_type type)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 416f537bf614..2a11a962e571 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -19,6 +19,14 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 
+enum kaslr_status {
+	KASLR_ENABLED,
+	KASLR_DISABLED_CMDLINE,
+	KASLR_DISABLED_NO_SEED,
+	KASLR_DISABLED_FDT_REMAP,
+};
+
+static enum kaslr_status __initdata kaslr_status;
 u64 __ro_after_init module_alloc_base;
 u16 __initdata memstart_offset_seed;
 
@@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	early_fixmap_init();
 	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
-	if (!fdt)
+	if (!fdt) {
+		kaslr_status = KASLR_DISABLED_FDT_REMAP;
 		return 0;
+	}
 
 	/*
 	 * Retrieve (and wipe) the seed from the FDT
 	 */
 	seed = get_kaslr_seed(fdt);
-	if (!seed)
-		return 0;
 
 	/*
 	 * Check if 'nokaslr' appears on the command line, and
@@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 */
 	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
-	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
+	if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) {
+		kaslr_status = KASLR_DISABLED_CMDLINE;
+		return 0;
+	}
+
+	if (!seed) {
+		kaslr_status = KASLR_DISABLED_NO_SEED;
 		return 0;
+	}
 
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
@@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys)
 
 	return offset;
 }
+
+static int __init kaslr_init(void)
+{
+	switch (kaslr_status) {
+	case KASLR_ENABLED:
+		pr_info("KASLR enabled\n");
+		break;
+	case KASLR_DISABLED_CMDLINE:
+		pr_info("KASLR disabled on command line\n");
+		break;
+	case KASLR_DISABLED_NO_SEED:
+		pr_warn("KASLR disabled due to lack of seed\n");
+		break;
+	case KASLR_DISABLED_FDT_REMAP:
+		pr_warn("KASLR disabled due to FDT remapping failure\n");
+		break;
+	}
+
+	return 0;
+}
+core_initcall(kaslr_init)
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index b182442b87a3..65b08a74aec6 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sort.h>
@@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		tramp->sh_type = SHT_NOBITS;
 		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 		tramp->sh_addralign = __alignof__(struct plt_entry);
-		tramp->sh_size = sizeof(struct plt_entry);
+		tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 03ff15bffbb6..1cd1a4d0ed30 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -9,6 +9,7 @@
 
 #include <linux/bitops.h>
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/gfp.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
@@ -470,22 +471,58 @@ overflow:
 	return -ENOEXEC;
 }
 
-int module_finalize(const Elf_Ehdr *hdr,
-		    const Elf_Shdr *sechdrs,
-		    struct module *me)
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
 {
 	const Elf_Shdr *s, *se;
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
-		if (strcmp(".altinstructions", secstrs + s->sh_name) == 0)
-			apply_alternatives_module((void *)s->sh_addr, s->sh_size);
-#ifdef CONFIG_ARM64_MODULE_PLTS
-		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
-		    !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name))
-			me->arch.ftrace_trampoline = (void *)s->sh_addr;
-#endif
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
 	}
 
+	return NULL;
+}
+
+static inline void __init_plt(struct plt_entry *plt, unsigned long addr)
+{
+	*plt = get_plt_entry(addr, plt);
+}
+
+static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
+				  const Elf_Shdr *sechdrs,
+				  struct module *mod)
+{
+#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
+	const Elf_Shdr *s;
+	struct plt_entry *plts;
+
+	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plts = (void *)s->sh_addr;
+
+	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
+
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		__init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR);
+
+	mod->arch.ftrace_trampolines = plts;
+#endif
 	return 0;
 }
+
+int module_finalize(const Elf_Ehdr *hdr,
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
+{
+	const Elf_Shdr *s;
+	s = find_section(hdr, sechdrs, ".altinstructions");
+	if (s)
+		apply_alternatives_module((void *)s->sh_addr, s->sh_size);
+
+	return module_init_ftrace_plt(hdr, sechdrs, me);
+}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a0b4f1bca491..e40b65645c86 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR(name, config) \
-	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
-		       config, armv8pmu_events_sysfs_show)
-
-ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR);
-ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE);
-ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL);
-ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED);
-ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED);
-ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED);
-ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN);
-ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN);
-ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED);
-ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED);
-ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED);
-ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES);
-ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED);
-ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS);
-ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE);
-ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE);
-ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB);
-ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS);
-ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR);
-ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC);
-ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED);
-ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES);
-/* Don't expose the chain event in /sys, since it's useless in isolation */
-ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED);
-ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED);
-ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND);
-ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND);
-ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB);
-ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB);
-ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE);
-ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE);
-ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL);
-ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE);
-ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB);
-ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL);
-ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
-ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB);
-ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS);
-ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE);
-ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS);
-ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK);
-ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK);
-ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD);
-ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD);
-ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD);
-ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP);
-ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED);
-ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE);
-ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION);
+#define ARMV8_EVENT_ATTR(name, config)						\
+	(&((struct perf_pmu_events_attr) {					\
+		.attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL),	\
+		.id = config,							\
+	}).attr.attr)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
-	&armv8_event_attr_sw_incr.attr.attr,
-	&armv8_event_attr_l1i_cache_refill.attr.attr,
-	&armv8_event_attr_l1i_tlb_refill.attr.attr,
-	&armv8_event_attr_l1d_cache_refill.attr.attr,
-	&armv8_event_attr_l1d_cache.attr.attr,
-	&armv8_event_attr_l1d_tlb_refill.attr.attr,
-	&armv8_event_attr_ld_retired.attr.attr,
-	&armv8_event_attr_st_retired.attr.attr,
-	&armv8_event_attr_inst_retired.attr.attr,
-	&armv8_event_attr_exc_taken.attr.attr,
-	&armv8_event_attr_exc_return.attr.attr,
-	&armv8_event_attr_cid_write_retired.attr.attr,
-	&armv8_event_attr_pc_write_retired.attr.attr,
-	&armv8_event_attr_br_immed_retired.attr.attr,
-	&armv8_event_attr_br_return_retired.attr.attr,
-	&armv8_event_attr_unaligned_ldst_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred.attr.attr,
-	&armv8_event_attr_cpu_cycles.attr.attr,
-	&armv8_event_attr_br_pred.attr.attr,
-	&armv8_event_attr_mem_access.attr.attr,
-	&armv8_event_attr_l1i_cache.attr.attr,
-	&armv8_event_attr_l1d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_cache.attr.attr,
-	&armv8_event_attr_l2d_cache_refill.attr.attr,
-	&armv8_event_attr_l2d_cache_wb.attr.attr,
-	&armv8_event_attr_bus_access.attr.attr,
-	&armv8_event_attr_memory_error.attr.attr,
-	&armv8_event_attr_inst_spec.attr.attr,
-	&armv8_event_attr_ttbr_write_retired.attr.attr,
-	&armv8_event_attr_bus_cycles.attr.attr,
-	&armv8_event_attr_l1d_cache_allocate.attr.attr,
-	&armv8_event_attr_l2d_cache_allocate.attr.attr,
-	&armv8_event_attr_br_retired.attr.attr,
-	&armv8_event_attr_br_mis_pred_retired.attr.attr,
-	&armv8_event_attr_stall_frontend.attr.attr,
-	&armv8_event_attr_stall_backend.attr.attr,
-	&armv8_event_attr_l1d_tlb.attr.attr,
-	&armv8_event_attr_l1i_tlb.attr.attr,
-	&armv8_event_attr_l2i_cache.attr.attr,
-	&armv8_event_attr_l2i_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache_allocate.attr.attr,
-	&armv8_event_attr_l3d_cache_refill.attr.attr,
-	&armv8_event_attr_l3d_cache.attr.attr,
-	&armv8_event_attr_l3d_cache_wb.attr.attr,
-	&armv8_event_attr_l2d_tlb_refill.attr.attr,
-	&armv8_event_attr_l2i_tlb_refill.attr.attr,
-	&armv8_event_attr_l2d_tlb.attr.attr,
-	&armv8_event_attr_l2i_tlb.attr.attr,
-	&armv8_event_attr_remote_access.attr.attr,
-	&armv8_event_attr_ll_cache.attr.attr,
-	&armv8_event_attr_ll_cache_miss.attr.attr,
-	&armv8_event_attr_dtlb_walk.attr.attr,
-	&armv8_event_attr_itlb_walk.attr.attr,
-	&armv8_event_attr_ll_cache_rd.attr.attr,
-	&armv8_event_attr_ll_cache_miss_rd.attr.attr,
-	&armv8_event_attr_remote_access_rd.attr.attr,
-	&armv8_event_attr_sample_pop.attr.attr,
-	&armv8_event_attr_sample_feed.attr.attr,
-	&armv8_event_attr_sample_filtrate.attr.attr,
-	&armv8_event_attr_sample_collision.attr.attr,
+	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+	ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE),
+	ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED),
+	ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED),
+	ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED),
+	ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN),
+	ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN),
+	ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED),
+	ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED),
+	ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED),
+	ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES),
+	ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED),
+	ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS),
+	ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE),
+	ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE),
+	ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB),
+	ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS),
+	ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR),
+	ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC),
+	ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES),
+	/* Don't expose the chain event in /sys, since it's useless in isolation */
+	ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED),
+	ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND),
+	ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB),
+	ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB),
+	ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE),
+	ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE),
+	ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB),
+	ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB),
+	ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS),
+	ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE),
+	ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS),
+	ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK),
+	ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK),
+	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
+	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
+	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
+	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
+	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
+	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
 	NULL,
 };
 
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c4452827419b..d1c95dcf1d78 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void)
 					(unsigned long)__irqentry_text_end);
 	if (ret)
 		return ret;
-	ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start,
-					(unsigned long)__exception_text_end);
-	if (ret)
-		return ret;
 	ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
 					(unsigned long)__idmap_text_end);
 	if (ret)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1fb2819fc048..71f788cd2b18 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
+#include <linux/lockdep.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -44,6 +45,7 @@
 #include <asm/alternative.h>
 #include <asm/arch_gicv3.h>
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
@@ -631,3 +633,19 @@ static int __init tagged_addr_init(void)
 
 core_initcall(tagged_addr_init);
 #endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+asmlinkage void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (static_branch_likely(&arm64_const_caps_ready))
+		preempt_schedule_irq();
+}
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index c9f72b2665f1..43ae4e0c968f 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
 {
-	int err, i;
+	int err;
+	unsigned long start, end;
 
 	if (!psci_ops.affinity_info)
 		return 0;
@@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	 * while it is dying. So, try again a few times.
 	 */
 
-	for (i = 0; i < 10; i++) {
+	start = jiffies;
+	end = start + msecs_to_jiffies(100);
+	do {
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
+			pr_info("CPU%d killed (polled %d ms)\n", cpu,
+				jiffies_to_msecs(jiffies - start));
 			return 0;
 		}
 
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
+		usleep_range(100, 1000);
+	} while (time_before(jiffies, end));
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index ea94cf8f9dc6..d6259dac62b6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2017 Arm Ltd.
 #define pr_fmt(fmt) "sdei: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/arm_sdei.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
-	sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
+	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	if (arm64_kernel_unmapped_at_el0()) {
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..9a9d98a443fc 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -154,14 +154,14 @@ static inline void sve_user_discard(void)
 	sve_user_disable();
 }
 
-asmlinkage void el0_svc_handler(struct pt_regs *regs)
+void el0_svc_handler(struct pt_regs *regs)
 {
 	sve_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
 #ifdef CONFIG_COMPAT
-asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
+void el0_svc_compat_handler(struct pt_regs *regs)
 {
 	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
 		       compat_sys_call_table);
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 34739e80211b..73caf35c2262 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -35,6 +35,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/insn.h>
+#include <asm/kprobes.h>
 #include <asm/traps.h>
 #include <asm/smp.h>
 #include <asm/stack_pointer.h>
@@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr)
 	force_signal_inject(SIGSEGV, code, addr);
 }
 
-asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+void do_undefinstr(struct pt_regs *regs)
 {
 	/* check for AArch32 breakpoint instructions */
 	if (!aarch32_break_handler(regs))
@@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	BUG_ON(!user_mode(regs));
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
 }
+NOKPROBE_SYMBOL(do_undefinstr);
 
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
@@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
@@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
 	{},
 };
 
-asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook, *hook_base;
 
@@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_cp15instr);
 #endif
 
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+void do_sysinstr(unsigned int esr, struct pt_regs *regs)
 {
 	const struct sys64_hook *hook;
 
@@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 	 */
 	do_undefinstr(regs);
 }
+NOKPROBE_SYMBOL(do_sysinstr);
 
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
@@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
  * bad_el0_sync handles unexpected, but potentially recoverable synchronous
  * exceptions taken from EL0. Unlike bad_mode, this returns.
  */
-asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
 	void __user *pc = (void __user *)instruction_pointer(regs);
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index aa76f7259668..009057517bdd 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -111,9 +111,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			__exception_text_start = .;
-			*(.exception.text)
-			__exception_text_end = .;
 			IRQENTRY_TEXT
 			SOFTIRQENTRY_TEXT
 			ENTRY_TEXT
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 3d3815020e36..72fbbd86eb5e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -12,7 +12,7 @@
 
 #include <kvm/arm_psci.h>
 
-#include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
@@ -118,12 +118,29 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
 }
 
 static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
 	write_sysreg(hcr, hcr_el2);
 
 	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
@@ -156,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps_nvhe (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
 	__deactivate_traps_common();
 
 	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
@@ -174,8 +208,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	 * the crucial bit is "On taking a vSError interrupt,
 	 * HCR_EL2.VSE is cleared to 0."
 	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE)
-		vcpu->arch.hcr_el2 = read_sysreg(hcr_el2);
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
 
 	if (has_vhe())
 		deactivate_traps_vhe();
@@ -380,6 +416,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -399,6 +490,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
 	/*
 	 * We trap the first access to the FP/SIMD to save the host context
 	 * and restore the guest context lazily.
@@ -592,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	 */
 	if (system_uses_irq_prio_masking()) {
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-		dsb(sy);
+		pmr_sync();
 	}
 
 	vcpu = kern_hyp_va(vcpu);
@@ -605,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 
 	__sysreg_save_state_nvhe(host_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
-	__activate_traps(vcpu);
-
-	__hyp_vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
 	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
 	__debug_switch_to_guest(vcpu);
 
 	__set_guest_arch_workaround_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 7ddbc849b580..22b8128d19f6 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
-	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+
+	if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	} else	if (!ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for guest registers, hence the context
+		 * test. We're coming from the host, so SCTLR.M is already
+		 * set. Pairs with __activate_traps_nvhe().
+		 */
+		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+				  TCR_EPD1_MASK | TCR_EPD0_MASK),
+				 SYS_TCR);
+		isb();
+	}
+
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],		actlr_el1);
 	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
 	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
 	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
 	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
 	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
@@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) &&
+	    ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for host registers, hence the context
+		 * test. Pairs with __deactivate_traps_nvhe().
+		 */
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * deconfigured and disabled. We can now restore the host's
+		 * S1 configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index eb0efc5557f3..c2bc17ca6430 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -63,6 +63,22 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * For CPUs that are affected by ARM 1319367, we need to
+		 * avoid a host Stage-1 walk while we have the guest's
+		 * VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the S1 MMU is enabled, so we can
+		 * simply set the EPD bits to avoid any further TLB fill.
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		isb();
+	}
+
 	__load_guest_stage2(kvm);
 	isb();
 }
@@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 						 struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		/* Ensure write of the host VMID */
+		isb();
+		/* Restore the host's TCR_EL1 */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+	}
 }
 
 static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2071260a275b..46822afc57e0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	if (!system_supports_32bit_el0())
+		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
@@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		if (!system_supports_32bit_el0())
+			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 		kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 10415572e82f..aeafc03e961a 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -20,7 +20,6 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__arch_clear_user)
-	uaccess_enable_not_uao x2, x3, x4
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -40,7 +39,6 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-	uaccess_disable_not_uao x2, x3
 	ret
 ENDPROC(__arch_clear_user)
 EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 680e74409ff9..ebb3c06cbb5d 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -54,10 +54,8 @@
 
 end	.req	x5
 ENTRY(__arch_copy_from_user)
-	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3, x4
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 0bedae3f3792..3d8153a1ebce 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -56,10 +56,8 @@
 end	.req	x5
 
 ENTRY(__arch_copy_in_user)
-	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 2d88c736e8f2..357eae2c18eb 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -53,10 +53,8 @@
 
 end	.req	x5
 ENTRY(__arch_copy_to_user)
-	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c
index cbfcbe6470a5..bfa30b75b2b8 100644
--- a/arch/arm64/lib/uaccess_flushcache.c
+++ b/arch/arm64/lib/uaccess_flushcache.c
@@ -28,7 +28,11 @@ void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
 unsigned long __copy_user_flushcache(void *to, const void __user *from,
 				     unsigned long n)
 {
-	unsigned long rc = __arch_copy_from_user(to, from, n);
+	unsigned long rc;
+
+	uaccess_enable_not_uao();
+	rc = __arch_copy_from_user(to, from, n);
+	uaccess_disable_not_uao();
 
 	/* See above */
 	__clean_dcache_area_pop(to, n - rc);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 855f2a7954e6..077b02a2d4d3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -32,7 +32,8 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
-#include <asm/kasan.h>
+#include <asm/kprobes.h>
+#include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/pgtable.h>
@@ -101,18 +102,6 @@ static void mem_abort_decode(unsigned int esr)
 		data_abort_decode(esr);
 }
 
-static inline bool is_ttbr0_addr(unsigned long addr)
-{
-	/* entry assembly clears tags for TTBR0 addrs */
-	return addr < TASK_SIZE;
-}
-
-static inline bool is_ttbr1_addr(unsigned long addr)
-{
-	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
-	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
-}
-
 static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm)
 {
 	/* Either init_pg_dir or swapper_pg_dir */
@@ -268,8 +257,12 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	par = read_sysreg(par_el1);
 	local_irq_restore(flags);
 
+	/*
+	 * If we now have a valid translation, treat the translation fault as
+	 * spurious.
+	 */
 	if (!(par & SYS_PAR_EL1_F))
-		return false;
+		return true;
 
 	/*
 	 * If we got a different type of fault from the AT instruction,
@@ -314,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	if (is_el1_permission_fault(addr, esr, regs)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
+		else if (is_el1_instruction_abort(esr))
+			msg = "execute from non-executable memory";
 		else
 			msg = "read from unreadable memory";
 	} else if (addr < PAGE_SIZE) {
@@ -732,8 +727,7 @@ static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 63"			},
 };
 
-asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
-					 struct pt_regs *regs)
+void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_fault_info(esr);
 
@@ -749,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die(inf->name, regs,
 			 inf->sig, inf->code, (void __user *)addr, esr);
 }
+NOKPROBE_SYMBOL(do_mem_abort);
 
-asmlinkage void __exception do_el0_irq_bp_hardening(void)
+void do_el0_irq_bp_hardening(void)
 {
 	/* PC has already been checked in entry.S */
 	arm64_apply_bp_hardening();
 }
+NOKPROBE_SYMBOL(do_el0_irq_bp_hardening);
 
-asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
-						   unsigned int esr,
-						   struct pt_regs *regs)
-{
-	/*
-	 * We've taken an instruction abort from userspace and not yet
-	 * re-enabled IRQs. If the address is a kernel address, apply
-	 * BP hardening prior to enabling IRQs and pre-emption.
-	 */
-	if (!is_ttbr0_addr(addr))
-		arm64_apply_bp_hardening();
-
-	local_daif_restore(DAIF_PROCCTX);
-	do_mem_abort(addr, esr, regs);
-}
-
-
-asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
-					   unsigned int esr,
-					   struct pt_regs *regs)
+void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		if (!is_ttbr0_addr(instruction_pointer(regs)))
-			arm64_apply_bp_hardening();
-		local_daif_restore(DAIF_PROCCTX);
-	}
-
 	arm64_notify_die("SP/PC alignment exception", regs,
 			 SIGBUS, BUS_ADRALN, (void __user *)addr, esr);
 }
+NOKPROBE_SYMBOL(do_sp_pc_abort);
 
 int __init early_brk64(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs);
@@ -868,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit);
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
-static int __exception
-cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs))
 		return 0;
@@ -888,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 	return 1;
 }
 #else
-static int __exception
-cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 {
 	return 0;
 }
 #endif /* CONFIG_ARM64_ERRATUM_1463225 */
+NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler);
 
-asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
-					       unsigned int esr,
-					       struct pt_regs *regs)
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+			struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_debug_fault_info(esr);
 	unsigned long pc = instruction_pointer(regs);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 45c00a54909c..be9481cdf3b9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -20,6 +20,7 @@
 #include <linux/sort.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
@@ -41,6 +42,8 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
+#define ARM64_ZONE_DMA_BITS	30
+
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
@@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset);
 struct page *vmemmap __ro_after_init;
 EXPORT_SYMBOL(vmemmap);
 
+/*
+ * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
+ * memory as some devices, namely the Raspberry Pi 4, have peripherals with
+ * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
+ * bit addressable memory area.
+ */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
+static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void)
 {
 }
 #endif /* CONFIG_CRASH_DUMP */
+
 /*
- * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
- * currently assumes that for memory starting above 4G, 32-bit devices will
- * use a DMA offset.
+ * Return the maximum physical address for a zone with a given address size
+ * limit. It currently assumes that for memory starting above 4G, 32-bit
+ * devices will use a DMA offset.
  */
-static phys_addr_t __init max_zone_dma_phys(void)
+static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
 {
-	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
-	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits);
+	return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_NUMA
@@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
+#endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max;
 
@@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma = min;
+	unsigned long max_dma32 = min;
+	unsigned long __maybe_unused max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-	/* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 	max_dma = PFN_DOWN(arm64_dma_phys_limit);
-	zone_size[ZONE_DMA32] = max_dma - min;
+	zone_size[ZONE_DMA] = max_dma - min;
+	max_dma32 = max_dma;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	max_dma32 = PFN_DOWN(arm64_dma32_phys_limit);
+	zone_size[ZONE_DMA32] = max_dma32 - max_dma;
 #endif
-	zone_size[ZONE_NORMAL] = max - max_dma;
+	zone_size[ZONE_NORMAL] = max - max_dma32;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 		if (start < max_dma) {
-			unsigned long dma_end = min(end, max_dma);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+			unsigned long dma_end = min_not_zero(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
 #endif
-		if (end > max_dma) {
+#ifdef CONFIG_ZONE_DMA32
+		if (start < max_dma32) {
+			unsigned long dma32_end = min(end, max_dma32);
+			unsigned long dma32_start = max(start, max_dma);
+			zhole_size[ZONE_DMA32] -= dma32_end - dma32_start;
+		}
+#endif
+		if (end > max_dma32) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma);
+			unsigned long normal_start = max(start, max_dma32);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -418,11 +443,15 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		zone_dma_bits = ARM64_ZONE_DMA_BITS;
+		arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS);
+	}
+
 	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma_phys_limit = max_zone_dma_phys();
+		arm64_dma32_phys_limit = max_zone_phys(32);
 	else
-		arm64_dma_phys_limit = PHYS_MASK + 1;
+		arm64_dma32_phys_limit = PHYS_MASK + 1;
 
 	reserve_crashkernel();
 
@@ -430,7 +459,7 @@ void __init arm64_memblock_init(void)
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
-	dma_contiguous_reserve(arm64_dma_phys_limit);
+	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -534,7 +563,7 @@ static void __init free_unused_memmap(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
@@ -571,7 +600,7 @@ void free_initmem(void)
 {
 	free_reserved_area(lm_alias(__init_begin),
 			   lm_alias(__init_end),
-			   0, "unused kernel");
+			   POISON_FREE_INITMEM, "unused kernel");
 	/*
 	 * Unmap the __init region but leave the VM area in place. This
 	 * prevents the region from being reused for kernel modules, which
@@ -580,18 +609,6 @@ void free_initmem(void)
 	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	unsigned long aligned_start, aligned_end;
-
-	aligned_start = __virt_to_phys(start) & PAGE_MASK;
-	aligned_end = PAGE_ALIGN(__virt_to_phys(end));
-	memblock_free(aligned_start, aligned_end - aligned_start);
-	free_reserved_area((void *)start, (void *)end, 0, "initrd");
-}
-#endif
-
 /*
  * Dump out memory limit information on panic.
  */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60c929f3683b..a9f541912289 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 phys_addr_t (*pgtable_alloc)(int),
 				 int flags)
 {
-	unsigned long addr, length, end, next;
+	unsigned long addr, end, next;
 	pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
 
 	/*
@@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 
 	phys &= PAGE_MASK;
 	addr = virt & PAGE_MASK;
-	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
+	end = PAGE_ALIGN(virt + size);
 
-	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
 		alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 73bf5ea9ee1b..7ec3161e8517 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -869,8 +869,28 @@ static const struct resource atari_scsi_tt_rsrc[] __initconst = {
 };
 #endif
 
+/*
+ * Falcon IDE interface
+ */
+
+#define FALCON_IDE_BASE	0xfff00000
+
+static const struct resource atari_falconide_rsrc[] __initconst = {
+	{
+		.flags = IORESOURCE_MEM,
+		.start = FALCON_IDE_BASE,
+		.end   = FALCON_IDE_BASE + 0x39,
+	},
+	{
+		.flags = IORESOURCE_IRQ,
+		.start = IRQ_MFP_FSCSI,
+		.end   = IRQ_MFP_FSCSI,
+	},
+};
+
 int __init atari_platform_init(void)
 {
+	struct platform_device *pdev;
 	int rv = 0;
 
 	if (!MACH_IS_ATARI)
@@ -912,6 +932,13 @@ int __init atari_platform_init(void)
 			atari_scsi_tt_rsrc, ARRAY_SIZE(atari_scsi_tt_rsrc));
 #endif
 
+	if (ATARIHW_PRESENT(IDE)) {
+		pdev = platform_device_register_simple("atari-falcon-ide", -1,
+			atari_falconide_rsrc, ARRAY_SIZE(atari_falconide_rsrc));
+		if (IS_ERR(pdev))
+			rv = PTR_ERR(pdev);
+	}
+
 	return rv;
 }
 
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 9a33c1c006a1..619d30d663a2 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -355,6 +355,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -420,11 +421,15 @@ CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=m
+CONFIG_I2C_CHARDEV=m
+CONFIG_I2C_ICY=m
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
-# CONFIG_HWMON is not set
+CONFIG_HWMON=m
+CONFIG_SENSORS_LTC2990=m
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -432,8 +437,6 @@ CONFIG_FB_AMIGA_OCS=y
 CONFIG_FB_AMIGA_ECS=y
 CONFIG_FB_AMIGA_AGA=y
 CONFIG_FB_FM2=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -490,6 +493,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -560,10 +564,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 7fdbc797a05d..caa0558abcdb 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -334,6 +334,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -393,8 +394,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_VGA16 is not set
@@ -450,6 +449,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -520,10 +520,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index f1763405a539..2551c7e9ac54 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -350,6 +350,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -417,8 +418,6 @@ CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ATARI=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -472,6 +471,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -542,10 +542,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 91154d6acb31..4ffc1e5646d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index c398c4a94d95..806da3d97ca4 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -333,6 +333,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -395,8 +396,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -452,6 +451,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -522,10 +522,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 350d004559be..250da20e291c 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -342,6 +342,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -419,8 +420,6 @@ CONFIG_PTP_1588_CLOCK=m
 CONFIG_FB=y
 CONFIG_FB_VALKYRIE=y
 CONFIG_FB_MAC=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -474,6 +473,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -544,10 +544,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index b838dd820348..b764a0368a56 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -386,6 +386,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -480,11 +481,15 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y
 CONFIG_SERIAL_PMACZILOG_CONSOLE=y
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=m
+CONFIG_I2C_CHARDEV=m
+CONFIG_I2C_ICY=m
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
-# CONFIG_HWMON is not set
+CONFIG_HWMON=m
+CONFIG_SENSORS_LTC2990=m
 CONFIG_FB=y
 CONFIG_FB_CIRRUS=y
 CONFIG_FB_AMIGA=y
@@ -495,8 +500,6 @@ CONFIG_FB_FM2=y
 CONFIG_FB_ATARI=y
 CONFIG_FB_VALKYRIE=y
 CONFIG_FB_MAC=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -556,6 +559,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -626,10 +630,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 3f8dd61559cf..7800d3a8d46e 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -331,6 +331,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -389,8 +390,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -442,6 +441,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -512,10 +512,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ae3b2d4f636c..c32dc2d2058d 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
@@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index cd61ef14b582..bf0a65ce57e0 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -339,6 +339,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -404,8 +405,6 @@ CONFIG_PPS_CLIENT_PARPORT=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
@@ -461,6 +460,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -531,10 +531,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 151f5371cd3d..5f3cfa2926d2 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -390,8 +391,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -445,6 +444,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -515,10 +515,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 1dcb0ee1fe98..58354d2018d5 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
@@ -389,8 +390,6 @@ CONFIG_PPS_CLIENT_LDISC=m
 CONFIG_PTP_1588_CLOCK=m
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_HID=m
@@ -444,6 +443,7 @@ CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
+CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -514,10 +514,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index e63eb5f06999..f31890078197 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -264,6 +264,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll)
 {
 	int tmp = Q40_RTC_CTRL;
 
+	pll->pll_ctrl = 0;
 	pll->pll_value = tmp & Q40_RTC_PLL_MASK;
 	if (tmp & Q40_RTC_PLL_SIGN)
 		pll->pll_value = -pll->pll_value;
diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h
index 195314732233..00d41b94ba31 100644
--- a/arch/mips/include/asm/vdso/vsyscall.h
+++ b/arch/mips/include/asm/vdso/vsyscall.h
@@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk)
 }
 #define __arch_get_clock_mode __mips_get_clock_mode
 
-static __always_inline
-int __mips_use_vsyscall(struct vdso_data *vdata)
-{
-	return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE);
-}
-#define __arch_use_vsyscall __mips_use_vsyscall
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/mips/sgi-ip27/Kconfig b/arch/mips/sgi-ip27/Kconfig
index ef3847e7aee0..e5b6cadbec85 100644
--- a/arch/mips/sgi-ip27/Kconfig
+++ b/arch/mips/sgi-ip27/Kconfig
@@ -38,10 +38,3 @@ config REPLICATE_KTEXT
 	  Say Y here to enable replicating the kernel text across multiple
 	  nodes in a NUMA cluster.  This trades memory for speed.
 
-config REPLICATE_EXHANDLERS
-	bool "Exception handler replication support"
-	depends on SGI_IP27
-	help
-	  Say Y here to enable replicating the kernel exception handlers
-	  across multiple nodes in a NUMA cluster. This trades memory for
-	  speed.
diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c
index 8fd3505e2b9c..f597e1ee2df7 100644
--- a/arch/mips/sgi-ip27/ip27-init.c
+++ b/arch/mips/sgi-ip27/ip27-init.c
@@ -64,23 +64,14 @@ static void per_hub_init(nasid_t nasid)
 
 	hub_rtc_init(nasid);
 
-#ifdef CONFIG_REPLICATE_EXHANDLERS
-	/*
-	 * If this is not a headless node initialization,
-	 * copy over the caliased exception handlers.
-	 */
-	if (get_nasid() == nasid) {
-		extern char except_vec2_generic, except_vec3_generic;
-		extern void build_tlb_refill_handler(void);
-
-		memcpy((void *)(CKSEG0 + 0x100), &except_vec2_generic, 0x80);
-		memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x80);
-		build_tlb_refill_handler();
-		memcpy((void *)(CKSEG0 + 0x100), (void *) CKSEG0, 0x80);
-		memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x100);
+	if (nasid) {
+		/* copy exception handlers from first node to current node */
+		memcpy((void *)NODE_OFFSET_TO_K0(nasid, 0),
+		       (void *)CKSEG0, 0x200);
 		__flush_cache_all();
+		/* switch to node local exception handlers */
+		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K);
 	}
-#endif
 }
 
 void per_cpu_init(void)
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index f610fff592a6..563aad5e6398 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -311,11 +311,7 @@ static void __init mlreset(void)
 		 * thinks it is a node 0 address.
 		 */
 		REMOTE_HUB_S(nasid, PI_REGION_PRESENT, (region_mask | 1));
-#ifdef CONFIG_REPLICATE_EXHANDLERS
-		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K);
-#else
 		REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_0);
-#endif
 
 #ifdef LATER
 		/*
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 36b834f1c933..dca8f2de8cf5 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -60,7 +60,6 @@ KBUILD_CFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY=1 \
 		 -DFTRACE_PATCHABLE_FUNCTION_SIZE=$(NOP_COUNT)
 
 CC_FLAGS_FTRACE := -fpatchable-function-entry=$(NOP_COUNT),$(shell echo $$(($(NOP_COUNT)-1)))
-KBUILD_LDS_MODULE += $(srctree)/arch/parisc/kernel/module.lds
 endif
 
 OBJCOPY_FLAGS =-O binary -R .note -R .comment -S
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index 73ca89a47f49..e5de3f897633 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -22,7 +22,7 @@
 
 #define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(.data..read_mostly)
 
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index 3eb4bfc1fb36..e080143e79a3 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -52,7 +52,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __attribute__((__section__(".data..lock_aligned")))
+# define __lock_aligned __section(.data..lock_aligned)
 #endif
 
 #endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 1d1d748c227f..b96d74496977 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -2125,7 +2125,7 @@ ftrace_regs_caller:
 	copy	%rp, %r26
 	LDREG	-FTRACE_FRAME_SIZE-PT_SZ_ALGN(%sp), %r25
 	ldo	-8(%r25), %r25
-	copy	%r3, %arg2
+	ldo	-FTRACE_FRAME_SIZE(%r1), %arg2
 	b,l	ftrace_function_trampoline, %rp
 	copy	%r1, %arg3 /* struct pt_regs */
 
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index ac5f34993b53..1c50093e2ebe 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -43,6 +43,7 @@
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <linux/ftrace.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/bug.h>
@@ -862,7 +863,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const char *strtab = NULL;
 	const Elf_Shdr *s;
 	char *secstrings;
-	int err, symindex = -1;
+	int symindex = -1;
 	Elf_Sym *newptr, *oldptr;
 	Elf_Shdr *symhdr = NULL;
 #ifdef DEBUG
@@ -946,11 +947,13 @@ int module_finalize(const Elf_Ehdr *hdr,
 			/* patch .altinstructions */
 			apply_alternatives(aseg, aseg + s->sh_size, me->name);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 		/* For 32 bit kernels we're compiling modules with
 		 * -ffunction-sections so we must relocate the addresses in the
-		 *__mcount_loc section.
+		 *  ftrace callsite section.
 		 */
-		if (symindex != -1 && !strcmp(secname, "__mcount_loc")) {
+		if (symindex != -1 && !strcmp(secname, FTRACE_CALLSITE_SECTION)) {
+			int err;
 			if (s->sh_type == SHT_REL)
 				err = apply_relocate((Elf_Shdr *)sechdrs,
 							strtab, symindex,
@@ -962,6 +965,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 			if (err)
 				return err;
 		}
+#endif
 	}
 	return 0;
 }
diff --git a/arch/parisc/kernel/module.lds b/arch/parisc/kernel/module.lds
deleted file mode 100644
index 1a9a92aca5c8..000000000000
--- a/arch/parisc/kernel/module.lds
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-SECTIONS {
-	__mcount_loc : {
-		*(__patchable_function_entries)
-	}
-}
diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c
index 92a9b5f12f98..f29f682352f0 100644
--- a/arch/parisc/mm/ioremap.c
+++ b/arch/parisc/mm/ioremap.c
@@ -3,7 +3,7 @@
  * arch/parisc/mm/ioremap.c
  *
  * (C) Copyright 1995 1996 Linus Torvalds
- * (C) Copyright 2001-2006 Helge Deller <deller@gmx.de>
+ * (C) Copyright 2001-2019 Helge Deller <deller@gmx.de>
  * (C) Copyright 2005 Kyle McMartin <kyle@parisc-linux.org>
  */
 
@@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	addr = (void __iomem *) area->addr;
 	if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
 			       phys_addr, pgprot)) {
-		vfree(addr);
+		vunmap(addr);
 		return NULL;
 	}
 
@@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 }
 EXPORT_SYMBOL(__ioremap);
 
-void iounmap(const volatile void __iomem *addr)
+void iounmap(const volatile void __iomem *io_addr)
 {
-	if (addr > high_memory)
-		return vfree((void *) (PAGE_MASK & (unsigned long __force) addr));
+	unsigned long addr = (unsigned long)io_addr & PAGE_MASK;
+
+	if (is_vmalloc_addr((void *)addr))
+		vunmap((void *)addr);
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 677e9babef80..f9dc597b0b86 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -91,6 +91,7 @@
 
 static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 {
+	addr &= 0xf0000000;	/* align addr to start of segment */
 	barrier();	/* make sure thread.kuap is updated before playing with SRs */
 	while (addr < end) {
 		mtsrin(sr, addr);
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 409c9bfb43d9..57c229a86f08 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -175,4 +175,7 @@ do {									\
 	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index c8bb14ff4713..f6c562acc3f8 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -329,13 +329,4 @@ struct vm_area_struct;
 #endif /* __ASSEMBLY__ */
 #include <asm/slice.h>
 
-/*
- * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks.
- */
-#ifdef CONFIG_PPC32
-#define ARCH_ZONE_DMA_BITS 30
-#else
-#define ARCH_ZONE_DMA_BITS 31
-#endif
-
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a4e7762dd286..100f1b57ec2f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
 	/* Switch to secure mode. */
 	prom_printf("Switching to secure mode.\n");
 
+	/*
+	 * The ultravisor will do an integrity check of the kernel image but we
+	 * relocated it so the check will fail. Restore the original image by
+	 * relocating it back to the kernel virtual base address.
+	 */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(KERNELBASE);
+
 	ret = enter_secure_mode(kbase, fdt);
+
+	/* Relocate the kernel again. */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(kbase);
+
 	if (ret != U_SUCCESS) {
 		prom_printf("Returned %d from switching to secure mode.\n", ret);
 		prom_rtas_os_term("Switch to secure mode failed.\n");
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 78bab17b1396..b183ab9c5107 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 logo_linux_clut224 btext_prepare_BAT
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
+relocate"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 591bfb4bfd0f..a3f9c665bb5b 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1217,6 +1217,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc;
 	int i, r = -EBUSY;
+	u32 vp_id;
 
 	pr_devel("connect_vcpu(cpu=%d)\n", cpu);
 
@@ -1228,25 +1229,32 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
-		pr_devel("Duplicate !\n");
-		return -EEXIST;
-	}
 	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
-	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
-	if (!xc)
-		return -ENOMEM;
 
 	/* We need to synchronize with queue provisioning */
 	mutex_lock(&xive->lock);
+
+	vp_id = kvmppc_xive_vp(xive, cpu);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		r = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		r = -ENOMEM;
+		goto bail;
+	}
+
 	vcpu->arch.xive_vcpu = xc;
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = kvmppc_xive_vp(xive, cpu);
+	xc->vp_id = vp_id;
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 955b820ffd6d..fe3ed50e0818 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -220,6 +220,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
 	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
 }
 
+static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id)
+			return true;
+	}
+	return false;
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 248c1ea9e788..78b906ffa0d2 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc = NULL;
 	int rc;
+	u32 vp_id;
 
 	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
 
@@ -124,7 +125,8 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 
 	mutex_lock(&xive->lock);
 
-	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
+	vp_id = kvmppc_xive_vp(xive, server_num);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
 		pr_devel("Duplicate !\n");
 		rc = -EEXIST;
 		goto bail;
@@ -141,7 +143,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	xc->vcpu = vcpu;
 	xc->server_num = server_num;
 
-	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->vp_id = vp_id;
 	xc->valid = true;
 	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index be941d382c8d..c95b7fe9f298 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/memremap.h>
+#include <linux/dma-direct.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void)
  * everything else. GFP_DMA32 page allocations automatically fall back to
  * ZONE_DMA.
  *
- * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to
- * inform the generic DMA mapping code.  32-bit only devices (if not handled
- * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get
- * otherwise served by ZONE_DMA.
+ * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * generic DMA mapping code.  32-bit only devices (if not handled by an IOMMU
+ * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
+ * ZONE_DMA.
  */
 static unsigned long max_zone_pfns[MAX_NR_ZONES];
 
@@ -237,9 +238,18 @@ void __init paging_init(void)
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
 
+	/*
+	 * Allow 30-bit DMA for very limited Broadcom wifi chips on many
+	 * powerbooks.
+	 */
+	if (IS_ENABLED(CONFIG_PPC32))
+		zone_dma_bits = 30;
+	else
+		zone_dma_bits = 31;
+
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
-				      1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
+				      1UL << (zone_dma_bits - PAGE_SHIFT));
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 02a59946a78a..be3517ef0574 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	/*
+	 * If we have seen a tail call, we need a second pass.
+	 * This is because bpf_jit_emit_common_epilogue() is called
+	 * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
+	 */
+	if (cgctx.seen & SEEN_TAILCALL) {
+		cgctx.idx = 0;
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
+	}
+
+	/*
 	 * Pretend to build prologue, given the features we've seen.  This will
 	 * update ctgtx.idx as it pretends to output instructions, then we can
 	 * calculate total size from idx.
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 6bc24a47e9ef..6f300ab7f0e9 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
+	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fbd6e6b7bbf2..13e251699346 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void)
 	return 0;
 }
 
+static void pnv_flush_interrupts(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (xive_enabled())
+			xive_flush_interrupt();
+		else
+			icp_opal_flush_interrupt();
+	} else {
+		icp_native_flush_interrupt();
+	}
+}
+
 static void pnv_smp_cpu_kill_self(void)
 {
+	unsigned long srr1, unexpected_mask, wmask;
 	unsigned int cpu;
-	unsigned long srr1, wmask;
 	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
-	/*
-	 * This hard disables local interurpts, ensuring we have no lazy
-	 * irqs pending.
-	 */
-	WARN_ON(irqs_disabled());
-	hard_irq_disable();
-	WARN_ON(lazy_irq_pending());
 
 	idle_task_exit();
 	current->active_mm = NULL; /* for sanity */
@@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void)
 		wmask = SRR1_WAKEMASK_P8;
 
 	/*
+	 * This turns the irq soft-disabled state we're called with, into a
+	 * hard-disabled state with pending irq_happened interrupts cleared.
+	 *
+	 * PACA_IRQ_DEC   - Decrementer should be ignored.
+	 * PACA_IRQ_HMI   - Can be ignored, processing is done in real mode.
+	 * PACA_IRQ_DBELL, EE, PMI - Unexpected.
+	 */
+	hard_irq_disable();
+	if (generic_check_cpu_restart(cpu))
+		goto out;
+
+	unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS);
+	if (local_paca->irq_happened & unexpected_mask) {
+		if (local_paca->irq_happened & PACA_IRQ_EE)
+			pnv_flush_interrupts();
+		DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n",
+				cpu, local_paca->irq_happened);
+	}
+	local_paca->irq_happened = PACA_IRQ_HARD_DIS;
+
+	/*
 	 * We don't want to take decrementer interrupts while we are
 	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
 	 * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in.
@@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void)
 
 		srr1 = pnv_cpu_offline(cpu);
 
+		WARN_ON_ONCE(!irqs_disabled());
 		WARN_ON(lazy_irq_pending());
 
 		/*
@@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void)
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
 		    ((srr1 & wmask) == SRR1_WAKEHVI)) {
-			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-				if (xive_enabled())
-					xive_flush_interrupt();
-				else
-					icp_opal_flush_interrupt();
-			} else
-				icp_native_flush_interrupt();
+			pnv_flush_interrupts();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
 	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
+out:
 	DBG("CPU%d coming online...\n", cpu);
 }
 
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 104d334511cd..88cfcb96bf23 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -13,6 +13,7 @@
 	compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000";
 
 	chosen {
+		stdout-path = "serial0";
 	};
 
 	cpus {
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
index 07ceee8b1747..75604fec1b1b 100644
--- a/arch/riscv/include/asm/bug.h
+++ b/arch/riscv/include/asm/bug.h
@@ -12,7 +12,6 @@
 
 #include <asm/asm.h>
 
-#ifdef CONFIG_GENERIC_BUG
 #define __INSN_LENGTH_MASK  _UL(0x3)
 #define __INSN_LENGTH_32    _UL(0x3)
 #define __COMPRESSED_INSN_MASK	_UL(0xffff)
@@ -20,7 +19,6 @@
 #define __BUG_INSN_32	_UL(0x00100073) /* ebreak */
 #define __BUG_INSN_16	_UL(0x9002) /* c.ebreak */
 
-#ifndef __ASSEMBLY__
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
@@ -43,6 +41,7 @@ typedef u32 bug_insn_t;
 	RISCV_SHORT " %2"
 #endif
 
+#ifdef CONFIG_GENERIC_BUG
 #define __BUG_FLAGS(flags)					\
 do {								\
 	__asm__ __volatile__ (					\
@@ -58,14 +57,10 @@ do {								\
 		  "i" (flags),					\
 		  "i" (sizeof(struct bug_entry)));              \
 } while (0)
-
-#endif /* !__ASSEMBLY__ */
 #else /* CONFIG_GENERIC_BUG */
-#ifndef __ASSEMBLY__
 #define __BUG_FLAGS(flags) do {					\
 	__asm__ __volatile__ ("ebreak\n");			\
 } while (0)
-#endif /* !__ASSEMBLY__ */
 #endif /* CONFIG_GENERIC_BUG */
 
 #define BUG() do {						\
@@ -79,15 +74,10 @@ do {								\
 
 #include <asm-generic/bug.h>
 
-#ifndef __ASSEMBLY__
-
 struct pt_regs;
 struct task_struct;
 
-extern void die(struct pt_regs *regs, const char *str);
-extern void do_trap(struct pt_regs *regs, int signo, int code,
-	unsigned long addr);
-
-#endif /* !__ASSEMBLY__ */
+void die(struct pt_regs *regs, const char *str);
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr);
 
 #endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index fc1189ad3777..3ba4d93721d3 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <asm/mmiowb.h>
+#include <asm/pgtable.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -162,6 +163,12 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
+ *  I/O port access constants.
+ */
+#define IO_SPACE_LIMIT		(PCI_IO_SIZE - 1)
+#define PCI_IOBASE		((void __iomem *)PCI_IO_START)
+
+/*
  * Emulation routines for the port-mapped IO space used by some PCI drivers.
  * These are defined as being "fully synchronous", but also "not guaranteed to
  * be fully ordered with respect to other memory and I/O operations".  We're
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index 75576424c0f7..6e1b0e0325eb 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -7,6 +7,9 @@
 #ifndef _ASM_RISCV_IRQ_H
 #define _ASM_RISCV_IRQ_H
 
+#include <linux/interrupt.h>
+#include <linux/linkage.h>
+
 #define NR_IRQS         0
 
 void riscv_timer_interrupt(void);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 7255f2d8395b..d3221017194d 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -7,6 +7,7 @@
 #define _ASM_RISCV_PGTABLE_H
 
 #include <linux/mmzone.h>
+#include <linux/sizes.h>
 
 #include <asm/pgtable-bits.h>
 
@@ -86,14 +87,7 @@ extern pgd_t swapper_pg_dir[];
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
-
-#define FIXADDR_TOP      VMALLOC_START
-#ifdef CONFIG_64BIT
-#define FIXADDR_SIZE     PMD_SIZE
-#else
-#define FIXADDR_SIZE     PGDIR_SIZE
-#endif
-#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)
+#define PCI_IO_SIZE      SZ_16M
 
 /*
  * Roughly size the vmemmap space to be large enough to fit enough
@@ -108,6 +102,17 @@ extern pgd_t swapper_pg_dir[];
 
 #define vmemmap		((struct page *)VMEMMAP_START)
 
+#define PCI_IO_END       VMEMMAP_START
+#define PCI_IO_START     (PCI_IO_END - PCI_IO_SIZE)
+#define FIXADDR_TOP      PCI_IO_START
+
+#ifdef CONFIG_64BIT
+#define FIXADDR_SIZE     PMD_SIZE
+#else
+#define FIXADDR_SIZE     PGDIR_SIZE
+#endif
+#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)
+
 /*
  * ZERO_PAGE is a global shared page that is always zero,
  * used for zero-mapped memory areas, etc.
@@ -184,10 +189,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 	return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
 }
 
-static inline pte_t mk_pte(struct page *page, pgprot_t prot)
-{
-	return pfn_pte(page_to_pfn(page), prot);
-}
+#define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
 
 #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -428,9 +430,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-#ifdef CONFIG_FLATMEM
 #define kern_addr_valid(addr)   (1) /* FIXME */
-#endif
 
 extern void *dtb_early_va;
 extern void setup_bootmem(void);
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f0227bdce0f0..ee4f0ac62c9d 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_RISCV_SWITCH_TO_H
 #define _ASM_RISCV_SWITCH_TO_H
 
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 37ae4e367ad2..f02188a5b0f4 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -10,10 +10,6 @@
 #include <linux/mm_types.h>
 #include <asm/smp.h>
 
-/*
- * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
- * cache as well, so a 'fence.i' is not necessary.
- */
 static inline void local_flush_tlb_all(void)
 {
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b1ade9a49347..a5ad00043104 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -10,6 +10,7 @@
 #include <asm/processor.h>
 #include <asm/hwcap.h>
 #include <asm/smp.h>
+#include <asm/switch_to.h>
 
 unsigned long elf_hwcap __read_mostly;
 #ifdef CONFIG_FPU
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
new file mode 100644
index 000000000000..105fb0496b24
--- /dev/null
+++ b/arch/riscv/kernel/head.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive, Inc.
+ */
+#ifndef __ASM_HEAD_H
+#define __ASM_HEAD_H
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+extern atomic_t hart_lottery;
+
+asmlinkage void do_page_fault(struct pt_regs *regs);
+asmlinkage void __init setup_vm(uintptr_t dtb_pa);
+
+extern void *__cpu_up_stack_pointer[];
+extern void *__cpu_up_task_pointer[];
+
+void __init parse_dtb(void);
+
+#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index 6d8659388c49..fffac6ddb0e0 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -24,7 +24,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs)
+asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index c9ae48333114..e264e59e596e 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -8,6 +8,7 @@
 #include <linux/elf.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/moduleloader.h>
 
 unsigned long module_emit_got_entry(struct module *mod, unsigned long val)
 {
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index fb3a082362eb..85e3c39bb60b 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
@@ -19,6 +20,7 @@
 #include <asm/csr.h>
 #include <asm/string.h>
 #include <asm/switch_to.h>
+#include <asm/thread_info.h>
 
 extern asmlinkage void ret_from_fork(void);
 extern asmlinkage void ret_from_kernel_thread(void);
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 368751438366..1252113ef8b2 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -148,7 +148,7 @@ long arch_ptrace(struct task_struct *child, long request,
  * Allows PTRACE_SYSCALL to work.  These are called from entry.S in
  * {handle,ret_from}_syscall.
  */
-void do_syscall_trace_enter(struct pt_regs *regs)
+__visible void do_syscall_trace_enter(struct pt_regs *regs)
 {
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		if (tracehook_report_syscall_entry(regs))
@@ -162,7 +162,7 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 	audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
 }
 
-void do_syscall_trace_exit(struct pt_regs *regs)
+__visible void do_syscall_trace_exit(struct pt_regs *regs)
 {
 	audit_syscall_exit(regs);
 
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
index d0fe623bfb8f..aa56bb135ec4 100644
--- a/arch/riscv/kernel/reset.c
+++ b/arch/riscv/kernel/reset.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/reboot.h>
+#include <linux/pm.h>
 #include <asm/sbi.h>
 
 static void default_power_off(void)
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index a990a6cb184f..845ae0e12115 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -24,6 +24,8 @@
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
 
+#include "head.h"
+
 #ifdef CONFIG_DUMMY_CONSOLE
 struct screen_info screen_info = {
 	.orig_video_lines	= 30,
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index b14d7647d800..d0f6f212f5df 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -26,7 +26,7 @@ struct rt_sigframe {
 
 #ifdef CONFIG_FPU
 static long restore_fp_state(struct pt_regs *regs,
-			     union __riscv_fp_state *sc_fpregs)
+			     union __riscv_fp_state __user *sc_fpregs)
 {
 	long err;
 	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
@@ -53,7 +53,7 @@ static long restore_fp_state(struct pt_regs *regs,
 }
 
 static long save_fp_state(struct pt_regs *regs,
-			  union __riscv_fp_state *sc_fpregs)
+			  union __riscv_fp_state __user *sc_fpregs)
 {
 	long err;
 	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
@@ -292,8 +292,8 @@ static void do_signal(struct pt_regs *regs)
  * notification of userspace execution resumption
  * - triggered by the _TIF_WORK_MASK flags
  */
-asmlinkage void do_notify_resume(struct pt_regs *regs,
-	unsigned long thread_info_flags)
+asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
+					   unsigned long thread_info_flags)
 {
 	/* Handle pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index b18cd6c8e8fb..5c9ec78422c2 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -8,7 +8,9 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 18ae6da5115e..261f4087cc39 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -29,6 +29,9 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/sbi.h>
+#include <asm/smp.h>
+
+#include "head.h"
 
 void *__cpu_up_stack_pointer[NR_CPUS];
 void *__cpu_up_task_pointer[NR_CPUS];
@@ -130,7 +133,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 /*
  * C entry point for a secondary processor.
  */
-asmlinkage void __init smp_callin(void)
+asmlinkage __visible void __init smp_callin(void)
 {
 	struct mm_struct *mm = &init_mm;
 
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index e5dd52d8f633..f1ead9df96ca 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
 #include <asm/vdso.h>
+#include <asm/syscall.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call)	[nr] = (call),
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 9dd1f2e64db1..6a53c02e9c73 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -7,6 +7,7 @@
 #include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <asm/sbi.h>
+#include <asm/processor.h>
 
 unsigned long riscv_timebase;
 EXPORT_SYMBOL_GPL(riscv_timebase);
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 93742df9067f..473de3ae8bb7 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2012 Regents of the University of California
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -83,7 +84,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code,
 }
 
 #define DO_ERROR_INFO(name, signo, code, str)				\
-asmlinkage void name(struct pt_regs *regs)				\
+asmlinkage __visible void name(struct pt_regs *regs)			\
 {									\
 	do_trap_error(regs, signo, code, regs->sepc, "Oops - " str);	\
 }
@@ -111,7 +112,6 @@ DO_ERROR_INFO(do_trap_ecall_s,
 DO_ERROR_INFO(do_trap_ecall_m,
 	SIGILL, ILL_ILLTRP, "environment call from M-mode");
 
-#ifdef CONFIG_GENERIC_BUG
 static inline unsigned long get_break_insn_length(unsigned long pc)
 {
 	bug_insn_t insn;
@@ -120,28 +120,15 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 		return 0;
 	return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL);
 }
-#endif /* CONFIG_GENERIC_BUG */
 
-asmlinkage void do_trap_break(struct pt_regs *regs)
+asmlinkage __visible void do_trap_break(struct pt_regs *regs)
 {
-	if (!user_mode(regs)) {
-		enum bug_trap_type type;
-
-		type = report_bug(regs->sepc, regs);
-		switch (type) {
-#ifdef CONFIG_GENERIC_BUG
-		case BUG_TRAP_TYPE_WARN:
-			regs->sepc += get_break_insn_length(regs->sepc);
-			return;
-		case BUG_TRAP_TYPE_BUG:
-#endif /* CONFIG_GENERIC_BUG */
-		default:
-			die(regs, "Kernel BUG");
-		}
-	} else {
-		force_sig_fault(SIGTRAP, TRAP_BRKPT,
-				(void __user *)(regs->sepc));
-	}
+	if (user_mode(regs))
+		force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->sepc);
+	else if (report_bug(regs->sepc, regs) == BUG_TRAP_TYPE_WARN)
+		regs->sepc += get_break_insn_length(regs->sepc);
+	else
+		die(regs, "Kernel BUG");
 }
 
 #ifdef CONFIG_GENERIC_BUG
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index c9c21e0d5641..484d95a70907 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2015 Regents of the University of California
  */
 
+#include <linux/elf.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/binfmts.h>
@@ -25,7 +26,7 @@ static union {
 	struct vdso_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static struct vdso_data *vdso_data = &vdso_data_store.data;
 
 static int __init vdso_init(void)
 {
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index beeb5d7f92ea..ca66d44156b6 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 
 /*
  * When necessary, performs a deferred icache flush for the given MM context,
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 96add1427a75..247b8c859c44 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -18,6 +18,8 @@
 #include <asm/ptrace.h>
 #include <asm/tlbflush.h>
 
+#include "../kernel/head.h"
+
 /*
  * This routine handles page faults.  It determines the address and the
  * problem, and then passes it off to one of the appropriate routines.
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 83f7d12042fb..573463d1c799 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -19,6 +19,8 @@
 #include <asm/pgtable.h>
 #include <asm/io.h>
 
+#include "../kernel/head.h"
+
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 							__page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
@@ -337,8 +339,7 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
  */
 
 #ifndef __riscv_cmodel_medany
-#error "setup_vm() is called from head.S before relocate so it should "
-	"not use absolute addressing."
+#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
 #endif
 
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
@@ -458,7 +459,7 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
diff --git a/arch/riscv/mm/sifive_l2_cache.c b/arch/riscv/mm/sifive_l2_cache.c
index 2e637ad71c05..a9ffff3277c7 100644
--- a/arch/riscv/mm/sifive_l2_cache.c
+++ b/arch/riscv/mm/sifive_l2_cache.c
@@ -142,7 +142,7 @@ static irqreturn_t l2_int_handler(int irq, void *device)
 	return IRQ_HANDLED;
 }
 
-int __init sifive_l2_init(void)
+static int __init sifive_l2_init(void)
 {
 	struct device_node *np;
 	struct resource res;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 43a81d0ad507..f0df9e48e651 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -246,8 +246,8 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
+	depends on $(cc-option,-march=z900)
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
 	  2066 series). This will enable some optimizations that are not
@@ -255,8 +255,8 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
+	depends on $(cc-option,-march=z990)
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
 	  2086 series). The kernel will be slightly faster but will not work
@@ -264,8 +264,8 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
+	depends on $(cc-option,-march=z9-109)
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
 	  2096 series). The kernel will be slightly faster but will not work
@@ -274,6 +274,7 @@ config MARCH_Z9_109
 config MARCH_Z10
 	bool "IBM System z10"
 	select HAVE_MARCH_Z10_FEATURES
+	depends on $(cc-option,-march=z10)
 	help
 	  Select this to enable optimizations for IBM System z10 (2097 and
 	  2098 series). The kernel will be slightly faster but will not work
@@ -282,6 +283,7 @@ config MARCH_Z10
 config MARCH_Z196
 	bool "IBM zEnterprise 114 and 196"
 	select HAVE_MARCH_Z196_FEATURES
+	depends on $(cc-option,-march=z196)
 	help
 	  Select this to enable optimizations for IBM zEnterprise 114 and 196
 	  (2818 and 2817 series). The kernel will be slightly faster but will
@@ -290,6 +292,7 @@ config MARCH_Z196
 config MARCH_ZEC12
 	bool "IBM zBC12 and zEC12"
 	select HAVE_MARCH_ZEC12_FEATURES
+	depends on $(cc-option,-march=zEC12)
 	help
 	  Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
 	  2827 series). The kernel will be slightly faster but will not work on
@@ -298,6 +301,7 @@ config MARCH_ZEC12
 config MARCH_Z13
 	bool "IBM z13s and z13"
 	select HAVE_MARCH_Z13_FEATURES
+	depends on $(cc-option,-march=z13)
 	help
 	  Select this to enable optimizations for IBM z13s and z13 (2965 and
 	  2964 series). The kernel will be slightly faster but will not work on
@@ -306,6 +310,7 @@ config MARCH_Z13
 config MARCH_Z14
 	bool "IBM z14 ZR1 and z14"
 	select HAVE_MARCH_Z14_FEATURES
+	depends on $(cc-option,-march=z14)
 	help
 	  Select this to enable optimizations for IBM z14 ZR1 and z14 (3907
 	  and 3906 series). The kernel will be slightly faster but will not
@@ -314,6 +319,7 @@ config MARCH_Z14
 config MARCH_Z15
 	bool "IBM z15"
 	select HAVE_MARCH_Z15_FEATURES
+	depends on $(cc-option,-march=z15)
 	help
 	  Select this to enable optimizations for IBM z15 (8562
 	  and 8561 series). The kernel will be slightly faster but will not
@@ -367,33 +373,39 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z900)
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z990)
 
 config TUNE_Z9_109
 	bool "IBM System z9"
-	depends on !CC_IS_CLANG
+	depends on $(cc-option,-mtune=z9-109)
 
 config TUNE_Z10
 	bool "IBM System z10"
+	depends on $(cc-option,-mtune=z10)
 
 config TUNE_Z196
 	bool "IBM zEnterprise 114 and 196"
+	depends on $(cc-option,-mtune=z196)
 
 config TUNE_ZEC12
 	bool "IBM zBC12 and zEC12"
+	depends on $(cc-option,-mtune=zEC12)
 
 config TUNE_Z13
-	bool "IBM z13"
+	bool "IBM z13s and z13"
+	depends on $(cc-option,-mtune=z13)
 
 config TUNE_Z14
-	bool "IBM z14"
+	bool "IBM z14 ZR1 and z14"
+	depends on $(cc-option,-mtune=z14)
 
 config TUNE_Z15
 	bool "IBM z15"
+	depends on $(cc-option,-mtune=z15)
 
 endchoice
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 596ca7cc4d7b..fbd341ea03b8 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 	.diag0c = _diag0c_dma,
 	.diag308_reset = _diag308_reset_dma
 };
-static struct diag210 _diag210_tmp_dma __section(".dma.data");
+static struct diag210 _diag210_tmp_dma __section(.dma.data);
 struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
 void _swsusp_reset_dma(void);
 unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
@@ -101,10 +101,18 @@ static void handle_relocs(unsigned long offset)
 	dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
 	for (rela = rela_start; rela < rela_end; rela++) {
 		loc = rela->r_offset + offset;
-		val = rela->r_addend + offset;
+		val = rela->r_addend;
 		r_sym = ELF64_R_SYM(rela->r_info);
-		if (r_sym)
-			val += dynsym[r_sym].st_value;
+		if (r_sym) {
+			if (dynsym[r_sym].st_shndx != SHN_UNDEF)
+				val += dynsym[r_sym].st_value + offset;
+		} else {
+			/*
+			 * 0 == undefined symbol table index (STN_UNDEF),
+			 * used for R_390_RELATIVE, only add KASLR offset
+			 */
+			val += offset;
+		}
 		r_type = ELF64_R_TYPE(rela->r_info);
 		rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
 		if (rc)
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index d39e0f079217..686fe7aa192f 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
 	u64 bits;
-	unsigned int n, mbl_offset;
+	unsigned int n;
+	int mbl_offset;
 
 	n = ctx->count % bsize;
 	bits = ctx->count * 8;
-	mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
 		return -EINVAL;
 
+	mbl_offset = mbl_offset / sizeof(u32);
+
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
 	case CPACF_KLMD_SHA_1:
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index c2cf7bcdef9b..1c8a38f762a3 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, altinstr, facility)			\
-	asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
+	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
 
 #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,	    \
+	asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,   \
 				   altinstr2, facility2) ::: "memory")
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 713fc9735ffb..a2b11ac00f60 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
@@ -28,7 +28,7 @@
 #else /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define __EMIT_BUG(x) do {					\
-	asm volatile(						\
+	asm_inline volatile(					\
 		"0:	j	0b+2\n"				\
 		"1:\n"						\
 		".section __bug_table,\"awM\",@progbits,%1\n"	\
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 60f907516335..ed5efbb531c4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -11,6 +11,7 @@
 #include <linux/bits.h>
 
 #define CR0_CLOCK_COMPARATOR_SIGN	BIT(63 - 10)
+#define CR0_LOW_ADDRESS_PROTECTION	BIT(63 - 35)
 #define CR0_EMERGENCY_SIGNAL_SUBMASK	BIT(63 - 49)
 #define CR0_EXTERNAL_CALL_SUBMASK	BIT(63 - 50)
 #define CR0_CLOCK_COMPARATOR_SUBMASK	BIT(63 - 52)
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c6b9e2..a4d38092530a 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn)
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define ARCH_ZONE_DMA_BITS	31
-
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index bccb8f4a63e2..77606c4acd58 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION2_ENTRY_EMPTY);
 	return (p4d_t *) table;
 }
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		crst_table_free(mm, (unsigned long *) p4d);
+}
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
@@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
 }
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!mm_pud_folded(mm))
+		crst_table_free(mm, (unsigned long *) pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
@@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ff98d76a66c..7b03037a8475 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -266,11 +266,9 @@ static inline int is_module_addr(void *addr)
 #endif
 
 #define _REGION_ENTRY_BITS	 0xfffffffffffff22fUL
-#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
 #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
@@ -699,10 +697,8 @@ static inline int pmd_large(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd))
 		return 1;
-	if (pmd_large(pmd))
-		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
@@ -710,12 +706,10 @@ static inline int pud_bad(pud_t pud)
 {
 	unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
 
-	if (type > _REGION_ENTRY_TYPE_R3)
+	if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud))
 		return 1;
 	if (type < _REGION_ENTRY_TYPE_R3)
 		return 0;
-	if (pud_large(pud))
-		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
 	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
 }
 
@@ -758,18 +752,12 @@ static inline int pmd_write(pmd_t pmd)
 
 static inline int pmd_dirty(pmd_t pmd)
 {
-	int dirty = 1;
-	if (pmd_large(pmd))
-		dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
-	return dirty;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
 }
 
 static inline int pmd_young(pmd_t pmd)
 {
-	int young = 1;
-	if (pmd_large(pmd))
-		young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
-	return young;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
 }
 
 static inline int pte_present(pte_t pte)
@@ -1173,8 +1161,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (pte_present(entry))
 		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
@@ -1191,6 +1177,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
+	if (!MACHINE_HAS_NX)
+		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);
 }
 
@@ -1297,29 +1285,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
 	pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE;
-	if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-		return pmd;
-	pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkclean(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkdirty(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY |
-				_SEGMENT_ENTRY_SOFT_DIRTY;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
@@ -1333,29 +1315,23 @@ static inline pud_t pud_wrprotect(pud_t pud)
 static inline pud_t pud_mkwrite(pud_t pud)
 {
 	pud_val(pud) |= _REGION3_ENTRY_WRITE;
-	if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY))
-		return pud;
-	pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+	if (pud_val(pud) & _REGION3_ENTRY_DIRTY)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkclean(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
-		pud_val(pud) |= _REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
+	pud_val(pud) |= _REGION_ENTRY_PROTECT;
 	return pud;
 }
 
 static inline pud_t pud_mkdirty(pud_t pud)
 {
-	if (pud_large(pud)) {
-		pud_val(pud) |= _REGION3_ENTRY_DIRTY |
-				_REGION3_ENTRY_SOFT_DIRTY;
-		if (pud_val(pud) & _REGION3_ENTRY_WRITE)
-			pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
-	}
+	pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY;
+	if (pud_val(pud) & _REGION3_ENTRY_WRITE)
+		pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
 	return pud;
 }
 
@@ -1379,38 +1355,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
-		if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
-			pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+	if (pmd_val(pmd) & _SEGMENT_ENTRY_READ)
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
-		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-	}
+	pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
+	pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	if (pmd_large(pmd)) {
-		pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
-			_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
-			_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
-		pmd_val(pmd) |= massage_pgprot_pmd(newprot);
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
-		if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
-			pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
-		return pmd;
-	}
-	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN;
+	pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE |
+		_SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG |
+		_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY;
 	pmd_val(pmd) |= massage_pgprot_pmd(newprot);
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
 	return pmd;
 }
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 51a0e4a2dc96..881fc37c11c6 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p);
 /* Has task runtime instrumentation enabled ? */
 #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
 
-static inline unsigned long current_stack_pointer(void)
+static __always_inline unsigned long current_stack_pointer(void)
 {
 	unsigned long sp;
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e3f238e8c611..71e3f0146cda 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -276,6 +276,7 @@ struct qdio_outbuf_state {
 #define CHSC_AC2_MULTI_BUFFER_AVAILABLE	0x0080
 #define CHSC_AC2_MULTI_BUFFER_ENABLED	0x0040
 #define CHSC_AC2_DATA_DIV_AVAILABLE	0x0010
+#define CHSC_AC2_SNIFFER_AVAILABLE	0x0008
 #define CHSC_AC2_DATA_DIV_ENABLED	0x0002
 
 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE	0x8000
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index c02bff33f6c7..3a37172d5398 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
 	typecheck(int, lp->lock);
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0070", 49)	/* NIAI 7 */
 		"	sth	%1,%0\n"
 		: "=Q" (((unsigned short *) &lp->lock)[1])
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 0ae4bbf7779c..fee40212af11 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -38,7 +38,7 @@ static inline unsigned long get_stack_pointer(struct task_struct *task,
 {
 	if (regs)
 		return (unsigned long) kernel_stack_pointer(regs);
-	if (task == current)
+	if (!task || task == current)
 		return current_stack_pointer();
 	return (unsigned long) task->thread.ksp;
 }
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 64539c221672..6da8885251d6 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,8 +10,9 @@
 #ifndef _ASM_S390_TIMEX_H
 #define _ASM_S390_TIMEX_H
 
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
 #include <linux/time64.h>
+#include <asm/lowcore.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void)
 
 int get_phys_clock(unsigned long *clock);
 void init_cpu_timer(void);
-unsigned long long monotonic_clock(void);
 
 extern unsigned char tod_clock_base[16] __aligned(8);
 
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
- * The caller must ensure that preemption is disabled.
  * The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
  */
 static inline unsigned long long get_tod_clock_monotonic(void)
 {
-	return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	unsigned long long tod;
+
+	preempt_disable();
+	tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	preempt_enable();
+	return tod;
 }
 
 /**
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
index d827b5b9a32c..eaaefeceef6f 100644
--- a/arch/s390/include/asm/unwind.h
+++ b/arch/s390/include/asm/unwind.h
@@ -35,6 +35,7 @@ struct unwind_state {
 	struct task_struct *task;
 	struct pt_regs *regs;
 	unsigned long sp, ip;
+	bool reuse_sp;
 	int graph_idx;
 	bool reliable;
 	bool error;
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 7abe6ae261b4..f304802ecf7b 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
 				ptr += sprintf(ptr, "%%v%i", value);
-			else if (operand->flags & OPERAND_PCREL)
-				ptr += sprintf(ptr, "%lx", (signed int) value
-								      + addr);
-			else if (operand->flags & OPERAND_SIGNED)
+			else if (operand->flags & OPERAND_PCREL) {
+				void *pcrel = (void *)((int)value + addr);
+
+				ptr += sprintf(ptr, "%px", pcrel);
+			} else if (operand->flags & OPERAND_SIGNED)
 				ptr += sprintf(ptr, "%i", value);
 			else
 				ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs)
 		else
 			*ptr++ = ' ';
 		addr = regs->psw.addr + start - 32;
-		ptr += sprintf(ptr, "%016lx: ", addr);
+		ptr += sprintf(ptr, "%px: ", (void *)addr);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
@@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		opsize = insn_length(*code);
 		if (opsize > len)
 			break;
-		ptr += sprintf(ptr, "%p: ", code);
+		ptr += sprintf(ptr, "%px: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
 		*ptr++ = '\t';
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63d0b37..db32a55daaec 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,6 +30,7 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 static void __init reset_tod_clock(void)
@@ -238,7 +239,7 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 		__ctl_set_bit(0, 17);
 	}
-	if (test_facility(130)) {
+	if (test_facility(130) && !noexec_disabled) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_NX;
 		__ctl_set_bit(0, 20);
 	}
@@ -260,6 +261,24 @@ static inline void save_vector_registers(void)
 #endif
 }
 
+static inline void setup_control_registers(void)
+{
+	unsigned long reg;
+
+	__ctl_store(reg, 0, 0);
+	reg |= CR0_LOW_ADDRESS_PROTECTION;
+	reg |= CR0_EMERGENCY_SIGNAL_SUBMASK;
+	reg |= CR0_EXTERNAL_CALL_SUBMASK;
+	__ctl_load(reg, 0, 0);
+}
+
+static inline void setup_access_registers(void)
+{
+	unsigned int acrs[NUM_ACRS] = { 0 };
+
+	restore_access_regs(acrs);
+}
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
@@ -268,21 +287,6 @@ static int __init disable_vector_extension(char *str)
 }
 early_param("novx", disable_vector_extension);
 
-static int __init noexec_setup(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (!rc && !enabled) {
-		/* Disable no-execute support */
-		S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX;
-		__ctl_clear_bit(0, 20);
-	}
-	return rc;
-}
-early_param("noexec", noexec_setup);
-
 static int __init cad_setup(char *str)
 {
 	bool enabled;
@@ -332,5 +336,7 @@ void __init startup_init(void)
 	save_vector_registers();
 	setup_topology();
 	sclp_early_detect();
+	setup_control_registers();
+	setup_access_registers();
 	lockdep_on();
 }
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 0d9ee198f4eb..b9e585f528a6 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -26,8 +26,6 @@ ENTRY(startup_continue)
 0:	larl	%r1,tod_clock_base
 	mvc	0(16,%r1),__LC_BOOT_CLOCK
 	larl	%r13,.LPG1		# get base
-	larl	%r0,boot_vdso_data
-	stg	%r0,__LC_VDSO_PER_CPU
 #
 # Setup stack
 #
@@ -37,19 +35,8 @@ ENTRY(startup_continue)
 #ifdef CONFIG_KASAN
 	brasl	%r14,kasan_early_init
 #endif
-#
-# Early machine initialization and detection functions.
-#
-	brasl	%r14,startup_init
-
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel		# go to C code
+	brasl	%r14,startup_init		# s390 specific early init
+	brasl	%r14,start_kernel		# common init code
 #
 # We returned from start_kernel ?!? PANIK
 #
@@ -59,4 +46,3 @@ ENTRY(startup_continue)
 	.align	16
 .LPG1:
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
-.Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index b9d8fe45737a..8f8456816d83 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
+	unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long now, idle_time, idle_enter, idle_exit;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_time = READ_ONCE(idle->idle_time);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	idle_time += in_idle;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
@@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit;
+	unsigned long long now, idle_enter, idle_exit, in_idle;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-
-	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	return cputime_to_nsecs(in_idle);
 }
 
 void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index 3b664cb3ec4d..d5035de9020e 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 		*(u32 *)loc = val;
 		break;
 	case R_390_64:		/* Direct 64 bit.  */
+	case R_390_GLOB_DAT:
 		*(u64 *)loc = val;
 		break;
 	case R_390_PC16:	/* PC relative 16 bit.	*/
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 48d48b6187c0..0eb1d1cc53a8 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = {
 	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
 };
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	int err = 0;
 	u64 ev;
 
-	switch (attr->type) {
+	switch (type) {
 	case PERF_TYPE_RAW:
 		/* Raw events are used to access counters directly,
 		 * hence do not permit excludes */
@@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
+	unsigned int type = event->attr.type;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-	case PERF_TYPE_RAW:
-		err = __hw_perf_event_init(event);
-		break;
-	default:
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+		err = __hw_perf_event_init(event, type);
+	else if (event->pmu->type == type)
+		/* Registered as unknown PMU */
+		err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+	else
 		return -ENOENT;
-	}
 
 	if (unlikely(err) && event->destroy)
 		event->destroy(event);
@@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void)
 		return -ENODEV;
 
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
-	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
 	if (rc)
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
 	return rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2654e348801a..e949ab832ed7 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event)
 	int err = -ENOENT;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d config %#llx "
+			    "%s event %p cpu %d config %#llx type:%u "
 			    "sample_type %#llx cf_diag_events %d\n", __func__,
-			    event, event->cpu, attr->config, attr->sample_type,
-			    atomic_read(&cf_diag_events));
+			    event, event->cpu, attr->config, event->pmu->type,
+			    attr->sample_type, atomic_read(&cf_diag_events));
 
 	if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
-	    event->attr.type != PERF_TYPE_RAW)
+	    event->attr.type != event->pmu->type)
 		goto out;
 
 	/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@ static int __init cf_diag_init(void)
 	}
 	debug_register_view(cf_diag_dbg, &debug_sprintf_view);
 
-	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
 	if (rc) {
 		debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
 		debug_unregister(cf_diag_dbg);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8b12a9a6ff..69506fdbd9a1 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
 		}
 	}
 
-	debug_sprintf_event(sfdbg, 5,
-			    "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
+	debug_sprintf_event(sfdbg, 5, "%s freed sdbt %p\n", __func__,
+			    sfb->sdbt);
 	memset(sfb, 0, sizeof(*sfb));
 }
 
@@ -212,10 +212,10 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	 * the sampling buffer origin.
 	 */
 	if (sfb->sdbt != get_next_sdbt(tail)) {
-		debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
-				    "sampling buffer is not linked: origin=%p"
-				    "tail=%p\n",
-				    (void *) sfb->sdbt, (void *) tail);
+		debug_sprintf_event(sfdbg, 3, "%s: "
+				    "sampling buffer is not linked: origin %p"
+				    " tail %p\n", __func__,
+				    (void *)sfb->sdbt, (void *)tail);
 		return -EINVAL;
 	}
 
@@ -252,7 +252,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 	sfb->tail = tail;
 
 	debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
-			    " settings: sdbt=%lu sdb=%lu\n",
+			    " settings: sdbt %lu sdb %lu\n",
 			    sfb->num_sdbt, sfb->num_sdb);
 	return rc;
 }
@@ -293,11 +293,11 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
 	if (rc) {
 		free_sampling_buffer(sfb);
 		debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
-			"realloc_sampling_buffer failed with rc=%i\n", rc);
+			"realloc_sampling_buffer failed with rc %i\n", rc);
 	} else
 		debug_sprintf_event(sfdbg, 4,
-			"alloc_sampling_buffer: tear=%p dear=%p\n",
-			sfb->sdbt, (void *) *sfb->sdbt);
+			"alloc_sampling_buffer: tear %p dear %p\n",
+			sfb->sdbt, (void *)*sfb->sdbt);
 	return rc;
 }
 
@@ -404,8 +404,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 		return 0;
 
 	debug_sprintf_event(sfdbg, 3,
-			    "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
-			    " sample_size=%lu cpuhw=%p\n",
+			    "%s: rate %lu f %lu sdb %lu/%lu"
+			    " sample_size %lu cpuhw %p\n", __func__,
 			    SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
 			    sample_size, cpuhw);
 
@@ -465,8 +465,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
 	if (num)
 		sfb_account_allocs(num, hwc);
 
-	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
-			    " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow %llu ratio %lu"
+			    " num %lu\n", OVERFLOW_REG(hwc), ratio, num);
 	OVERFLOW_REG(hwc) = 0;
 }
 
@@ -505,11 +505,11 @@ static void extend_sampling_buffer(struct sf_buffer *sfb,
 	rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
 	if (rc)
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
-				    "failed with rc=%i\n", rc);
+				    "failed with rc %i\n", rc);
 
 	if (sfb_has_pending_allocs(sfb, hwc))
 		debug_sprintf_event(sfdbg, 5, "sfb: extend: "
-				    "req=%lu alloc=%lu remaining=%lu\n",
+				    "req %lu alloc %lu remaining %lu\n",
 				    num, sfb->num_sdb - num_old,
 				    sfb_pending_allocs(sfb, hwc));
 }
@@ -538,20 +538,22 @@ static void setup_pmc_cpu(void *flags)
 		err = sf_disable();
 		if (err)
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+				    "%s: initialized: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	case PMC_RELEASE:
 		cpusf->flags &= ~PMU_F_RESERVED;
 		err = sf_disable();
 		if (err) {
 			pr_err("Switching off the sampling facility failed "
-			       "with rc=%i\n", err);
+			       "with rc %i\n", err);
 		} else
 			deallocate_buffers(cpusf);
 		debug_sprintf_event(sfdbg, 5,
-				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+				    "%s: released: cpuhw %p\n", __func__,
+				    cpusf);
 		break;
 	}
 	if (err)
@@ -744,7 +746,7 @@ static int __hw_perf_event_init_rate(struct perf_event *event,
 	SAMPL_RATE(hwc) = rate;
 	hw_init_period(hwc, SAMPL_RATE(hwc));
 	debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:"
-			    "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu,
+			    "cpu:%d period:%#llx freq:%d,%#lx\n", event->cpu,
 			    event->attr.sample_period, event->attr.freq,
 			    SAMPLE_FREQ_MODE(hwc));
 	return 0;
@@ -963,7 +965,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	err = lsctl(&cpuhw->lsctl);
 	if (err) {
 		cpuhw->flags &= ~PMU_F_ENABLED;
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			1, err);
 		return;
 	}
@@ -971,8 +973,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	/* Load current program parameter */
 	lpp(&S390_lowcore.lpp);
 
-	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
-			    "interval:%lx tear=%p dear=%p\n",
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es %i cs %i ed %i cd %i "
+			    "interval %#lx tear %p dear %p\n",
 			    cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed,
 			    cpuhw->lsctl.cd, cpuhw->lsctl.interval,
 			    (void *) cpuhw->lsctl.tear,
@@ -999,13 +1001,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 
 	err = lsctl(&inactive);
 	if (err) {
-		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+		pr_err("Loading sampling controls failed: op %i err %i\n",
 			2, err);
 		return;
 	}
 
 	/* Save state of TEAR and DEAR register contents */
-	if (!qsi(&si)) {
+	err = qsi(&si);
+	if (!err) {
 		/* TEAR/DEAR values are valid only if the sampling facility is
 		 * enabled.  Note that cpumsf_pmu_disable() might be called even
 		 * for a disabled sampling facility because cpumsf_pmu_enable()
@@ -1017,7 +1020,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 		}
 	} else
 		debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
-				    "qsi() failed with err=%i\n", err);
+				    "qsi() failed with err %i\n", err);
 
 	cpuhw->flags &= ~PMU_F_ENABLED;
 }
@@ -1130,15 +1133,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count)
 	local64_add(count, &event->count);
 }
 
-static void debug_sample_entry(struct hws_basic_entry *sample,
-			       struct hws_trailer_entry *te)
-{
-	debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
-			    "sampling data entry: te->f=%i basic.def=%04x "
-			    "(%p)\n",
-			    te->f, sample->def, sample);
-}
-
 /* hw_collect_samples() - Walk through a sample-data-block and collect samples
  * @event:	The perf event
  * @sdbt:	Sample-data-block table
@@ -1192,7 +1186,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 				/* Count discarded samples */
 				*overflow += 1;
 		} else {
-			debug_sample_entry(sample, te);
+			debug_sprintf_event(sfdbg, 4,
+					    "%s: Found unknown"
+					    " sampling data entry: te->f %i"
+					    " basic.def %#4x (%p)\n", __func__,
+					    te->f, sample->def, sample);
 			/* Sample slot is not yet written or other record.
 			 *
 			 * This condition can occur if the buffer was reused
@@ -1267,9 +1265,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 			sampl_overflow += te->overflow;
 
 		/* Timestamps are valid for full sample-data-blocks only */
-		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
-				    "overflow=%llu timestamp=%#llx\n",
-				    sdbt, te->overflow,
+		debug_sprintf_event(sfdbg, 6, "%s: sdbt %p "
+				    "overflow %llu timestamp %#llx\n",
+				    __func__, sdbt, te->overflow,
 				    (te->f) ? trailer_timestamp(te) : 0ULL);
 
 		/* Collect all samples from a single sample-data-block and
@@ -1313,9 +1311,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
 	if (sampl_overflow || event_overflow)
-		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
-				    "overflow stats: sample=%llu event=%llu\n",
-				    sampl_overflow, event_overflow);
+		debug_sprintf_event(sfdbg, 4, "%s: "
+				    "overflow stats: sample %llu event %llu\n",
+				    __func__, sampl_overflow, event_overflow);
 }
 
 #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb)
@@ -1368,7 +1366,7 @@ static void aux_output_end(struct perf_output_handle *handle)
 	te = aux_sdb_trailer(aux, aux->alert_mark);
 	te->flags &= ~SDB_TE_ALERT_REQ_MASK;
 
-	debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i);
+	debug_sprintf_event(sfdbg, 6, "%s: collect %#lx SDBs\n", __func__, i);
 }
 
 /*
@@ -1428,8 +1426,8 @@ static int aux_output_begin(struct perf_output_handle *handle,
 
 	debug_sprintf_event(sfdbg, 6, "aux_output_begin: "
 			    "head->alert_mark->empty_mark (num_alert, range)"
-			    "[%lx -> %lx -> %lx] (%lx, %lx) "
-			    "tear index %lx, tear %lx dear %lx\n",
+			    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx) "
+			    "tear index %#lx, tear %#lx dear %#lx\n",
 			    aux->head, aux->alert_mark, aux->empty_mark,
 			    AUX_SDB_NUM_ALERT(aux), range,
 			    head / CPUM_SF_SDB_PER_TABLE,
@@ -1596,13 +1594,13 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 			perf_aux_output_end(&cpuhw->handle, size);
 			pr_err("Sample data caused the AUX buffer with %lu "
 			       "pages to overflow\n", num_sdb);
-			debug_sprintf_event(sfdbg, 1, "head %lx range %lx "
-					    "overflow %llx\n",
+			debug_sprintf_event(sfdbg, 1, "head %#lx range %#lx "
+					    "overflow %#llx\n",
 					    aux->head, range, overflow);
 		} else {
 			size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT;
 			perf_aux_output_end(&cpuhw->handle, size);
-			debug_sprintf_event(sfdbg, 6, "head %lx alert %lx "
+			debug_sprintf_event(sfdbg, 6, "head %#lx alert %#lx "
 					    "already full, try another\n",
 					    aux->head, aux->alert_mark);
 		}
@@ -1610,7 +1608,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw)
 
 	if (done)
 		debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: "
-				    "[%lx -> %lx -> %lx] (%lx, %lx)\n",
+				    "[%#lx -> %#lx -> %#lx] (%#lx, %#lx)\n",
 				    aux->head, aux->alert_mark, aux->empty_mark,
 				    AUX_SDB_NUM_ALERT(aux), range);
 }
@@ -1800,7 +1798,7 @@ static int cpumsf_pmu_check_period(struct perf_event *event, u64 value)
 	SAMPL_RATE(&event->hw) = rate;
 	hw_init_period(&event->hw, SAMPL_RATE(&event->hw));
 	debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:"
-			    "cpu:%d value:%llx period:%llx freq:%d\n",
+			    "cpu:%d value:%#llx period:%#llx freq:%d\n",
 			    event->cpu, value,
 			    event->attr.sample_period, do_freq);
 	return 0;
@@ -2111,7 +2109,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
 
 	sfb_set_limits(min, max);
 	pr_info("The sampling buffer limits have changed to: "
-		"min=%lu max=%lu (diag=x%lu)\n",
+		"min %lu max %lu (diag %lu)\n",
 		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
 	return 0;
 }
@@ -2129,7 +2127,7 @@ static const struct kernel_param_ops param_ops_sfb_size = {
 static void __init pr_cpumsf_err(unsigned int reason)
 {
 	pr_err("Sampling facility support for perf is not available: "
-	       "reason=%04x\n", reason);
+	       "reason %#x\n", reason);
 }
 
 static int __init init_cpum_sampling_pmu(void)
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index fcb6c2e92b07..1e75cc983546 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct unwind_state state;
+	unsigned long addr;
 
-	unwind_for_each_frame(&state, current, regs, 0)
-		perf_callchain_store(entry, state.ip);
+	unwind_for_each_frame(&state, current, regs, 0) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 /* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b0afec673f77..6ccef5f29761 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -40,6 +40,7 @@
 #include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
+#include <asm/unwind.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
@@ -178,9 +179,8 @@ EXPORT_SYMBOL(dump_fpu);
 
 unsigned long get_wchan(struct task_struct *p)
 {
-	struct stack_frame *sf, *low, *high;
-	unsigned long return_address;
-	int count;
+	struct unwind_state state;
+	unsigned long ip = 0;
 
 	if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
 		return 0;
@@ -188,26 +188,22 @@ unsigned long get_wchan(struct task_struct *p)
 	if (!try_get_task_stack(p))
 		return 0;
 
-	low = task_stack_page(p);
-	high = (struct stack_frame *) task_pt_regs(p);
-	sf = (struct stack_frame *) p->thread.ksp;
-	if (sf <= low || sf > high) {
-		return_address = 0;
-		goto out;
-	}
-	for (count = 0; count < 16; count++) {
-		sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain);
-		if (sf <= low || sf > high) {
-			return_address = 0;
-			goto out;
+	unwind_for_each_frame(&state, p, NULL, 0) {
+		if (state.stack_info.type != STACK_TYPE_TASK) {
+			ip = 0;
+			break;
 		}
-		return_address = READ_ONCE_NOCHECK(sf->gprs[8]);
-		if (!in_sched_functions(return_address))
-			goto out;
+
+		ip = unwind_get_return_address(&state);
+		if (!ip)
+			break;
+
+		if (!in_sched_functions(ip))
+			break;
 	}
-out:
+
 	put_task_stack(p);
-	return return_address;
+	return ip;
 }
 
 unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 44974654cbd0..6acdcf1d4074 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -805,7 +833,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	memblock_free_early((unsigned long)info, sizeof(*info));
 }
@@ -1148,7 +1176,7 @@ int __ref smp_rescan_cpus(void)
 	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766beee5ad..f9d070d016e3 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void)
 }
 NOKPROBE_SYMBOL(sched_clock);
 
-/*
- * Monotonic_clock - returns # of nanoseconds passed since time_init()
- */
-unsigned long long monotonic_clock(void)
-{
-	return sched_clock();
-}
-EXPORT_SYMBOL(monotonic_clock);
-
 static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt)
 {
 	unsigned long long high, low, rem, sec, nsec;
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index 8fc9daae47a2..fa111d3d378f 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	regs = state->regs;
 	if (unlikely(regs)) {
-		sp = READ_ONCE_NOCHECK(regs->gprs[15]);
-		if (unlikely(outside_of_stack(state, sp))) {
-			if (!update_stack_info(state, sp))
-				goto out_err;
+		if (state->reuse_sp) {
+			sp = state->sp;
+			state->reuse_sp = false;
+		} else {
+			sp = READ_ONCE_NOCHECK(regs->gprs[15]);
+			if (unlikely(outside_of_stack(state, sp))) {
+				if (!update_stack_info(state, sp))
+					goto out_err;
+			}
 		}
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
@@ -80,12 +85,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, (void *) sp);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp);
 
 	/* Update unwind state */
 	state->sp = sp;
@@ -107,9 +107,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 {
 	struct stack_info *info = &state->stack_info;
 	unsigned long *mask = &state->stack_mask;
+	bool reliable, reuse_sp;
 	struct stack_frame *sf;
 	unsigned long ip;
-	bool reliable;
 
 	memset(state, 0, sizeof(*state));
 	state->task = task;
@@ -134,22 +134,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	if (regs) {
 		ip = READ_ONCE_NOCHECK(regs->psw.addr);
 		reliable = true;
+		reuse_sp = true;
 	} else {
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
+		reuse_sp = false;
 	}
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Decode any ftrace redirection */
-	if (ip == (unsigned long) return_to_handler)
-		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
-					   ip, NULL);
-#endif
+	ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL);
 
 	/* Update unwind state */
 	state->sp = sp;
 	state->ip = ip;
 	state->reliable = reliable;
+	state->reuse_sp = reuse_sp;
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 30a7c8c29964..ce1e4bbe53aa 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock)
 {
 	int owner;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0040", 49)	/* NIAI 4 */
 		"	l	%0,%1\n"
 		: "=d" (owner) : "Q" (*lock) : "memory");
@@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new)
 {
 	int expected = old;
 
-	asm volatile(
+	asm_inline volatile(
 		ALTERNATIVE("", ".long 0xb2fa0080", 49)	/* NIAI 8 */
 		"	cs	%0,%3,%1\n"
 		: "=d" (old), "=Q" (*lock)
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 510a18299196..a51c892f14f3 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write,
 	}
 
 	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
+		len = min(*lenp, sizeof(buf));
+		if (copy_from_user(buf, buffer, len))
 			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
+		buf[len - 1] = '\0';
 		cmm_skip_blanks(buf, &p);
 		nr = simple_strtoul(p, &p, 0);
 		cmm_skip_blanks(p, &p);
 		seconds = simple_strtoul(p, &p, 0);
 		cmm_set_timeout(nr, seconds);
+		*ppos += *lenp;
 	} else {
 		len = sprintf(buf, "%ld %ld\n",
 			      cmm_timeout_pages, cmm_timeout_seconds);
@@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write,
 			len = *lenp;
 		if (copy_to_user(buffer, buf, len))
 			return -EFAULT;
+		*lenp = len;
+		*ppos += len;
 	}
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index a124f19f7b3c..f0ce22220565 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -118,6 +118,7 @@ void __init paging_init(void)
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
+	zone_dma_bits = 31;
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1864a8bb9622..59ad7997fed1 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size)
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 }
 
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count)
 	return rc;
 }
 
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
-				  unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+							unsigned long src,
+							unsigned long count)
 {
 	int irqs_disabled, rc;
 	unsigned long flags;
 
 	if (!count)
 		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
+	flags = arch_local_irq_save();
 	irqs_disabled = arch_irqs_disabled_flags(flags);
 	if (!irqs_disabled)
 		trace_hardirqs_off();
+	__arch_local_irq_stnsm(0xf8); // disable DAT
 	rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+	if (flags & PSW_MASK_DAT)
+		__arch_local_irq_stosm(0x04); // enable DAT
 	if (!irqs_disabled)
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(flags);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index fbc1aecf0f94..eb24cb1afc11 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -29,7 +29,6 @@ config SPARC
 	select RTC_DRV_M48T59
 	select RTC_SYSTOHC
 	select HAVE_ARCH_JUMP_LABEL if SPARC64
-	select HAVE_FAST_GUP if SPARC64
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_PCI_IOMAP
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index 324a23947585..997ffe46e953 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -65,14 +65,14 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
 #
-CFLAGS_REMOVE_vdso-note.o = -pg
 CFLAGS_REMOVE_vclock_gettime.o = -pg
+CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
 $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
-CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
+CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf32_sparc -soname linux-gate.so.1
 
 #This makes sure the $(obj) subdirectory exists even though vdso32/
diff --git a/arch/um/configs/kunit_defconfig b/arch/um/configs/kunit_defconfig
new file mode 100644
index 000000000000..9235b7d42d38
--- /dev/null
+++ b/arch/um/configs/kunit_defconfig
@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_KUNIT_TEST=y
+CONFIG_KUNIT_EXAMPLE_TEST=y
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 612535cd9706..6627d7c30f37 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	spin_unlock_irq(&ubd_dev->lock);
 
-	if (ret < 0)
-		blk_mq_requeue_request(req, true);
+	if (ret < 0) {
+		if (ret == -ENOMEM)
+			res = BLK_STS_RESOURCE;
+		else
+			res = BLK_STS_DEV_RESOURCE;
+	}
 
 	return res;
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d6e1faa28c58..8ef85139553f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
 
 	  If unsure, say y.
 
+choice
+	prompt "TSX enable mode"
+	depends on CPU_SUP_INTEL
+	default X86_INTEL_TSX_MODE_OFF
+	help
+	  Intel's TSX (Transactional Synchronization Extensions) feature
+	  allows to optimize locking protocols through lock elision which
+	  can lead to a noticeable performance boost.
+
+	  On the other hand it has been shown that TSX can be exploited
+	  to form side channel attacks (e.g. TAA) and chances are there
+	  will be more of those attacks discovered in the future.
+
+	  Therefore TSX is not enabled by default (aka tsx=off). An admin
+	  might override this decision by tsx=on the command line parameter.
+	  Even with TSX enabled, the kernel will attempt to enable the best
+	  possible TAA mitigation setting depending on the microcode available
+	  for the particular machine.
+
+	  This option allows to set the default tsx mode between tsx=on, =off
+	  and =auto. See Documentation/admin-guide/kernel-parameters.txt for more
+	  details.
+
+	  Say off if not sure, auto if TSX is in use but it should be used on safe
+	  platforms or on if TSX is in use and the security aspect of tsx is not
+	  relevant.
+
+config X86_INTEL_TSX_MODE_OFF
+	bool "off"
+	help
+	  TSX is disabled if possible - equals to tsx=off command line parameter.
+
+config X86_INTEL_TSX_MODE_ON
+	bool "on"
+	help
+	  TSX is always enabled on TSX capable HW - equals the tsx=on command
+	  line parameter.
+
+config X86_INTEL_TSX_MODE_AUTO
+	bool "auto"
+	help
+	  TSX is enabled on TSX capable HW that is believed to be safe against
+	  side channel attacks- equals the tsx=auto command line parameter.
+endchoice
+
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 149795c369f2..25019d42ae93 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -21,30 +21,6 @@
 struct mem_vector immovable_mem[MAX_NUMNODES*2];
 
 /*
- * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex
- * digits, and '\0' for termination.
- */
-#define MAX_ADDR_LEN 19
-
-static acpi_physical_address get_cmdline_acpi_rsdp(void)
-{
-	acpi_physical_address addr = 0;
-
-#ifdef CONFIG_KEXEC
-	char val[MAX_ADDR_LEN] = { };
-	int ret;
-
-	ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN);
-	if (ret < 0)
-		return 0;
-
-	if (kstrtoull(val, 16, &addr))
-		return 0;
-#endif
-	return addr;
-}
-
-/*
  * Search EFI system tables for RSDP.  If both ACPI_20_TABLE_GUID and
  * ACPI_TABLE_GUID are found, take the former, which has more features.
  */
@@ -298,6 +274,30 @@ acpi_physical_address get_rsdp_addr(void)
 }
 
 #if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE)
+/*
+ * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex
+ * digits, and '\0' for termination.
+ */
+#define MAX_ADDR_LEN 19
+
+static acpi_physical_address get_cmdline_acpi_rsdp(void)
+{
+	acpi_physical_address addr = 0;
+
+#ifdef CONFIG_KEXEC
+	char val[MAX_ADDR_LEN] = { };
+	int ret;
+
+	ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN);
+	if (ret < 0)
+		return 0;
+
+	if (kstrtoull(val, 16, &addr))
+		return 0;
+#endif
+	return addr;
+}
+
 /* Compute SRAT address from RSDP. */
 static unsigned long get_acpi_srat_table(void)
 {
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d6662fdef300..82bc60c8acb2 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -13,6 +13,7 @@
 #include <asm/e820/types.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
+#include <asm/boot.h>
 
 #include "../string.h"
 #include "eboot.h"
@@ -813,7 +814,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 		status = efi_relocate_kernel(sys_table, &bzimage_addr,
 					     hdr->init_size, hdr->init_size,
 					     hdr->pref_address,
-					     hdr->kernel_alignment);
+					     hdr->kernel_alignment,
+					     LOAD_PHYSICAL_ADDR);
 		if (status != EFI_SUCCESS) {
 			efi_printk(sys_table, "efi_relocate_kernel() failed!\n");
 			goto fail;
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 53ac0cb2396d..9652d5c2afda 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -345,6 +345,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 {
 	const unsigned long kernel_total_size = VO__end - VO__text;
 	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
+	unsigned long needed_size;
 
 	/* Retain x86 boot parameters pointer passed from startup_32/64. */
 	boot_params = rmode;
@@ -379,26 +380,38 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 *
+	 * On X86_64, the memory is mapped with PMD pages. Round the
+	 * size up so that the full extent of PMD pages mapped is
+	 * included in the check against the valid memory table
+	 * entries. This ensures the full mapped area is usable RAM
+	 * and doesn't include any reserved areas.
+	 */
+	needed_size = max(output_len, kernel_total_size);
+#ifdef CONFIG_X86_64
+	needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN);
+#endif
+
 	/* Report initial kernel position details. */
 	debug_putaddr(input_data);
 	debug_putaddr(input_len);
 	debug_putaddr(output);
 	debug_putaddr(output_len);
 	debug_putaddr(kernel_total_size);
+	debug_putaddr(needed_size);
 
 #ifdef CONFIG_X86_64
 	/* Report address of 32-bit trampoline */
 	debug_putaddr(trampoline_32bit);
 #endif
 
-	/*
-	 * The memory hole needed for the kernel is the larger of either
-	 * the entire decompressed kernel plus relocation table, or the
-	 * entire decompressed kernel plus .bss and .brk sections.
-	 */
 	choose_random_location((unsigned long)input_data, input_len,
 				(unsigned long *)&output,
-				max(output_len, kernel_total_size),
+				needed_size,
 				&virt_addr);
 
 	/* Validate memory location choices. */
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 5b35b7ea5d72..26c36357c4c9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
 					  struct hw_perf_event *hwc, u64 config)
 {
 	config &= ~perf_ibs->cnt_mask;
-	wrmsrl(hwc->config_base, config);
+	if (boot_cpu_data.x86 == 0x10)
+		wrmsrl(hwc->config_base, config);
 	config &= ~perf_ibs->enable_mask;
 	wrmsrl(hwc->config_base, config);
 }
@@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = {
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
-	.cnt_mask		= IBS_OP_MAX_CNT,
+	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
+				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
 	.max_period		= IBS_OP_MAX_CNT << 4,
@@ -614,7 +616,7 @@ fail:
 	if (event->attr.sample_type & PERF_SAMPLE_RAW)
 		offset_max = perf_ibs->offset_max;
 	else if (check_rip)
-		offset_max = 2;
+		offset_max = 3;
 	else
 		offset_max = 1;
 	do {
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 74e80ed9c6c4..05e43d0f430b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -627,7 +627,7 @@ static struct topa *topa_alloc(int cpu, gfp_t gfp)
 	 * link as the 2nd entry in the table
 	 */
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) {
-		TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p);
+		TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT;
 		TOPA_ENTRY(&tp->topa, 1)->end = 1;
 	}
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6fc2e06ab4c6..86467f85c383 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags)
 	local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
 	uncore_enable_event(box, event);
 
-	if (box->n_active == 1) {
-		uncore_enable_box(box);
+	if (box->n_active == 1)
 		uncore_pmu_start_hrtimer(box);
-	}
 }
 
 void uncore_pmu_event_stop(struct perf_event *event, int flags)
@@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags)
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
 
-		if (box->n_active == 0) {
-			uncore_disable_box(box);
+		if (box->n_active == 0)
 			uncore_pmu_cancel_hrtimer(box);
-		}
 	}
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
@@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	return ret;
 }
 
+static void uncore_pmu_enable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->enable_box)
+		uncore_pmu->type->ops->enable_box(box);
+}
+
+static void uncore_pmu_disable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->disable_box)
+		uncore_pmu->type->ops->disable_box(box);
+}
+
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 		pmu->pmu = (struct pmu) {
 			.attr_groups	= pmu->type->attr_groups,
 			.task_ctx_nr	= perf_invalid_context,
+			.pmu_enable	= uncore_pmu_enable,
+			.pmu_disable	= uncore_pmu_disable,
 			.event_init	= uncore_pmu_event_init,
 			.add		= uncore_pmu_event_add,
 			.del		= uncore_pmu_event_del,
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index f36f7bebbc1b..bbfdaa720b45 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
 	return -EINVAL;
 }
 
-static inline void uncore_disable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->disable_box)
-		box->pmu->type->ops->disable_box(box);
-}
-
-static inline void uncore_enable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->enable_box)
-		box->pmu->type->ops->enable_box(box);
-}
-
 static inline void uncore_disable_event(struct intel_uncore_box *box,
 				struct perf_event *event)
 {
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5c056b8aebef..e01078e93dd3 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -260,11 +260,21 @@ void __init hv_apic_init(void)
 	}
 
 	if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
-		pr_info("Hyper-V: Using MSR based APIC access\n");
+		pr_info("Hyper-V: Using enlightened APIC (%s mode)",
+			x2apic_enabled() ? "x2apic" : "xapic");
+		/*
+		 * With x2apic, architectural x2apic MSRs are equivalent to the
+		 * respective synthetic MSRs, so there's no need to override
+		 * the apic accessors.  The only exception is
+		 * hv_apic_eoi_write, because it benefits from lazy EOI when
+		 * available, but it works for both xapic and x2apic modes.
+		 */
 		apic_set_eoi_write(hv_apic_eoi_write);
-		apic->read      = hv_apic_read;
-		apic->write     = hv_apic_write;
-		apic->icr_write = hv_apic_icr_write;
-		apic->icr_read  = hv_apic_icr_read;
+		if (!x2apic_enabled()) {
+			apic->read      = hv_apic_read;
+			apic->write     = hv_apic_write;
+			apic->icr_write = hv_apic_icr_write;
+			apic->icr_read  = hv_apic_icr_read;
+		}
 	}
 }
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0652d3eed9bd..c4fbe379cc0b 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -399,5 +399,7 @@
 #define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
 #define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 50eb430b0ad8..4fc61483919a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -312,9 +312,12 @@ struct kvm_rmap_head {
 struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
+	struct list_head lpage_disallowed_link;
+
 	bool unsync;
 	u8 mmu_valid_gen;
 	bool mmio_cached;
+	bool lpage_disallowed; /* Can't be replaced by an equiv large page */
 
 	/*
 	 * The following two entries are used to key the shadow page in the
@@ -859,6 +862,7 @@ struct kvm_arch {
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;
+	struct list_head lpage_disallowed_mmu_pages;
 	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 
@@ -933,6 +937,7 @@ struct kvm_arch {
 	bool exception_payload_enabled;
 
 	struct kvm_pmu_event_filter *pmu_event_filter;
+	struct task_struct *nx_lpage_recovery_thread;
 };
 
 struct kvm_vm_stat {
@@ -946,6 +951,7 @@ struct kvm_vm_stat {
 	ulong mmu_unsync;
 	ulong remote_tlb_flush;
 	ulong lpages;
+	ulong nx_lpage_splits;
 	ulong max_mmu_page_hash_collisions;
 };
 
@@ -1189,7 +1195,7 @@ struct kvm_x86_ops {
 	int (*set_nested_state)(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				struct kvm_nested_state *kvm_state);
-	void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
 
 	int (*smi_allowed)(struct kvm_vcpu *vcpu);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 20ce682a2540..6a3124664289 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -93,6 +93,18 @@
 						  * Microarchitectural Data
 						  * Sampling (MDS) vulnerabilities.
 						  */
+#define ARCH_CAP_PSCHANGE_MC_NO		BIT(6)	 /*
+						  * The processor is not susceptible to a
+						  * machine check error due to modifying the
+						  * code page size along with either the
+						  * physical address or cache type
+						  * without TLB invalidation.
+						  */
+#define ARCH_CAP_TSX_CTRL_MSR		BIT(7)	/* MSR for TSX control is available. */
+#define ARCH_CAP_TAA_NO			BIT(8)	/*
+						 * Not susceptible to
+						 * TSX Async Abort (TAA) vulnerabilities.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -103,6 +115,10 @@
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
+#define MSR_IA32_TSX_CTRL		0x00000122
+#define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
+#define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 80bc209c0708..5c24a7b35166 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 #include <asm/segment.h>
 
 /**
- * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
  *
  * This uses the otherwise unused and obsolete VERW instruction in
  * combination with microcode which triggers a CPU buffer flush when the
@@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0bc530c4eb13..ad97dc155195 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1463,6 +1463,12 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
+#define arch_faults_on_old_pte arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	return false;
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6e0a3b43d027..54f5d54280f6 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -988,4 +988,11 @@ enum mds_mitigations {
 	MDS_MITIGATION_VMWERV,
 };
 
+enum taa_mitigations {
+	TAA_MITIGATION_OFF,
+	TAA_MITIGATION_UCODE_NEEDED,
+	TAA_MITIGATION_VERW,
+	TAA_MITIGATION_TSX_DISABLED,
+};
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index e00c9e875933..ac9fc51e2b18 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
+#include <linux/stringify.h>
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
@@ -20,8 +21,8 @@
  */
 
 /* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT    "0x5658"
-#define VMWARE_HYPERVISOR_PORT_HB "0x5659"
+#define VMWARE_HYPERVISOR_PORT    0x5658
+#define VMWARE_HYPERVISOR_PORT_HB 0x5659
 
 /* Current vmcall / vmmcall version */
 #define VMWARE_HYPERVISOR_HB   BIT(0)
@@ -29,7 +30,8 @@
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT ", %%dx; inl (%%dx)", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
+		      "inl (%%dx), %%eax",				\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
@@ -38,7 +40,8 @@
  * HB and OUT bits set.
  */
 #define VMWARE_HYPERCALL_HB_OUT						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep outsb", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
+		      "rep outsb",					\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
@@ -47,7 +50,8 @@
  * HB bit set.
  */
 #define VMWARE_HYPERCALL_HB_IN						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep insb", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
+		      "rep insb",					\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 #endif
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 9e2dd2b296cd..2b0faf86da1b 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1586,9 +1586,6 @@ static void setup_local_APIC(void)
 {
 	int cpu = smp_processor_id();
 	unsigned int value;
-#ifdef CONFIG_X86_32
-	int logical_apicid, ldr_apicid;
-#endif
 
 	if (disable_apic) {
 		disable_ioapic_support();
@@ -1626,16 +1623,21 @@ static void setup_local_APIC(void)
 	apic->init_apic_ldr();
 
 #ifdef CONFIG_X86_32
-	/*
-	 * APIC LDR is initialized.  If logical_apicid mapping was
-	 * initialized during get_smp_config(), make sure it matches the
-	 * actual value.
-	 */
-	logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-	ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
-	WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid);
-	/* always use the value from LDR */
-	early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+	if (apic->dest_logical) {
+		int logical_apicid, ldr_apicid;
+
+		/*
+		 * APIC LDR is initialized.  If logical_apicid mapping was
+		 * initialized during get_smp_config(), make sure it matches
+		 * the actual value.
+		 */
+		logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+		ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+		if (logical_apicid != BAD_APICID)
+			WARN_ON(logical_apicid != ldr_apicid);
+		/* Always use the value from LDR. */
+		early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+	}
 #endif
 
 	/*
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 45e92cba92f5..b0889c48a2ac 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -156,7 +156,8 @@ static int x2apic_dead_cpu(unsigned int dead_cpu)
 {
 	struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
 
-	cpumask_clear_cpu(dead_cpu, &cmsk->mask);
+	if (cmsk)
+		cpumask_clear_cpu(dead_cpu, &cmsk->mask);
 	free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index d7a1e5a9331c..890f60083eca 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
 
 ifdef CONFIG_CPU_SUP_INTEL
-obj-y			+= intel.o intel_pconfig.o
+obj-y			+= intel.o intel_pconfig.o tsx.o
 obj-$(CONFIG_PM)	+= intel_epb.o
 endif
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 91c2561b905f..4c7b0fa15a19 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
+static void __init taa_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -105,6 +106,7 @@ void __init check_bugs(void)
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
 	mds_select_mitigation();
+	taa_select_mitigation();
 
 	arch_smt_update();
 
@@ -269,6 +271,100 @@ static int __init mds_cmdline(char *str)
 early_param("mds", mds_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"TAA: " fmt
+
+/* Default mitigation for TAA-affected CPUs */
+static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW;
+static bool taa_nosmt __ro_after_init;
+
+static const char * const taa_strings[] = {
+	[TAA_MITIGATION_OFF]		= "Vulnerable",
+	[TAA_MITIGATION_UCODE_NEEDED]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+	[TAA_MITIGATION_VERW]		= "Mitigation: Clear CPU buffers",
+	[TAA_MITIGATION_TSX_DISABLED]	= "Mitigation: TSX disabled",
+};
+
+static void __init taa_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_TAA)) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+		return;
+	}
+
+	/* TSX previously disabled by tsx=off */
+	if (!boot_cpu_has(X86_FEATURE_RTM)) {
+		taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
+		goto out;
+	}
+
+	if (cpu_mitigations_off()) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+		return;
+	}
+
+	/* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
+	if (taa_mitigation == TAA_MITIGATION_OFF)
+		goto out;
+
+	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
+		taa_mitigation = TAA_MITIGATION_VERW;
+	else
+		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+
+	/*
+	 * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
+	 * A microcode update fixes this behavior to clear CPU buffers. It also
+	 * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
+	 * ARCH_CAP_TSX_CTRL_MSR bit.
+	 *
+	 * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
+	 * update is required.
+	 */
+	ia32_cap = x86_read_arch_cap_msr();
+	if ( (ia32_cap & ARCH_CAP_MDS_NO) &&
+	    !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR))
+		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+
+	/*
+	 * TSX is enabled, select alternate mitigation for TAA which is
+	 * the same as MDS. Enable MDS static branch to clear CPU buffers.
+	 *
+	 * For guests that can't determine whether the correct microcode is
+	 * present on host, enable the mitigation for UCODE_NEEDED as well.
+	 */
+	static_branch_enable(&mds_user_clear);
+
+	if (taa_nosmt || cpu_mitigations_auto_nosmt())
+		cpu_smt_disable(false);
+
+out:
+	pr_info("%s\n", taa_strings[taa_mitigation]);
+}
+
+static int __init tsx_async_abort_parse_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_TAA))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off")) {
+		taa_mitigation = TAA_MITIGATION_OFF;
+	} else if (!strcmp(str, "full")) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+	} else if (!strcmp(str, "full,nosmt")) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+		taa_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -786,13 +882,10 @@ static void update_mds_branch_idle(void)
 }
 
 #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
 
 void cpu_bugs_smt_update(void)
 {
-	/* Enhanced IBRS implies STIBP. No update required. */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
-		return;
-
 	mutex_lock(&spec_ctrl_mutex);
 
 	switch (spectre_v2_user) {
@@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (taa_mitigation) {
+	case TAA_MITIGATION_VERW:
+	case TAA_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(TAA_MSG_SMT);
+		break;
+	case TAA_MITIGATION_TSX_DISABLED:
+	case TAA_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+bool itlb_multihit_kvm_mitigation;
+EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
+
 #undef pr_fmt
 #define pr_fmt(fmt)	"L1TF: " fmt
 
@@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf)
 		       l1tf_vmx_states[l1tf_vmx_mitigation],
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }
+
+static ssize_t itlb_multihit_show_state(char *buf)
+{
+	if (itlb_multihit_kvm_mitigation)
+		return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
+	else
+		return sprintf(buf, "KVM: Vulnerable\n");
+}
 #else
 static ssize_t l1tf_show_state(char *buf)
 {
 	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
 }
+
+static ssize_t itlb_multihit_show_state(char *buf)
+{
+	return sprintf(buf, "Processor vulnerable\n");
+}
 #endif
 
 static ssize_t mds_show_state(char *buf)
@@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf)
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }
 
+static ssize_t tsx_async_abort_show_state(char *buf)
+{
+	if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) ||
+	    (taa_mitigation == TAA_MITIGATION_OFF))
+		return sprintf(buf, "%s\n", taa_strings[taa_mitigation]);
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       taa_strings[taa_mitigation]);
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_MDS:
 		return mds_show_state(buf);
 
+	case X86_BUG_TAA:
+		return tsx_async_abort_show_state(buf);
+
+	case X86_BUG_ITLB_MULTIHIT:
+		return itlb_multihit_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
 }
+
+ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_TAA);
+}
+
+ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9ae7d1bcd4f4..fffe21945374 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define NO_SPECULATION	BIT(0)
-#define NO_MELTDOWN	BIT(1)
-#define NO_SSB		BIT(2)
-#define NO_L1TF		BIT(3)
-#define NO_MDS		BIT(4)
-#define MSBDS_ONLY	BIT(5)
-#define NO_SWAPGS	BIT(6)
+#define NO_SPECULATION		BIT(0)
+#define NO_MELTDOWN		BIT(1)
+#define NO_SSB			BIT(2)
+#define NO_L1TF			BIT(3)
+#define NO_MDS			BIT(4)
+#define MSBDS_ONLY		BIT(5)
+#define NO_SWAPGS		BIT(6)
+#define NO_ITLB_MULTIHIT	BIT(7)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
 
 	/* Intel Family 6 */
-	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION),
-	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION),
-	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION),
-	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
-	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
-
-	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_SILVERMONT_D,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
+
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_SILVERMONT_D,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	 * good enough for our purposes.
 	 */
 
+	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT),
+
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	{}
 };
 
@@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which)
 	return m && !!(m->driver_data & which);
 }
 
-static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
+u64 x86_read_arch_cap_msr(void)
 {
 	u64 ia32_cap = 0;
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+	return ia32_cap;
+}
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
+{
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
+	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
+	if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
+
 	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
-	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
-
 	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
@@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (!cpu_matches(NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
+	/*
+	 * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when:
+	 *	- TSX is supported or
+	 *	- TSX_CTRL is present
+	 *
+	 * TSX_CTRL check is needed for cases when TSX could be disabled before
+	 * the kernel boot e.g. kexec.
+	 * TSX_CTRL check alone is not sufficient for cases when the microcode
+	 * update is not present or running as guest that don't get TSX_CTRL.
+	 */
+	if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
+	    (cpu_has(c, X86_FEATURE_RTM) ||
+	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
+		setup_force_cpu_bug(X86_BUG_TAA);
+
 	if (cpu_matches(NO_MELTDOWN))
 		return;
 
@@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void)
 #endif
 	cpu_detect_tlb(&boot_cpu_data);
 	setup_cr_pinning();
+
+	tsx_init();
 }
 
 void identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index c0e2407abdd6..38ab6e115eac 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -44,6 +44,22 @@ struct _tlb_table {
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
+#ifdef CONFIG_CPU_SUP_INTEL
+enum tsx_ctrl_states {
+	TSX_CTRL_ENABLE,
+	TSX_CTRL_DISABLE,
+	TSX_CTRL_NOT_SUPPORTED,
+};
+
+extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
+
+extern void __init tsx_init(void);
+extern void tsx_enable(void);
+extern void tsx_disable(void);
+#else
+static inline void tsx_init(void) { }
+#endif /* CONFIG_CPU_SUP_INTEL */
+
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
@@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu);
 
 extern void x86_spec_ctrl_setup_ap(void);
 
+extern u64 x86_read_arch_cap_msr(void);
+
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c2fdc00df163..11d5c5950e2d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c)
 		detect_tme(c);
 
 	init_intel_misc_features(c);
+
+	if (tsx_ctrl_state == TSX_CTRL_ENABLE)
+		tsx_enable();
+	if (tsx_ctrl_state == TSX_CTRL_DISABLE)
+		tsx_disable();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6ea7fdc82f3c..5167bd2bb6b1 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -583,7 +583,7 @@ bool amd_filter_mce(struct mce *m)
  * - Prevent possible spurious interrupts from the IF bank on Family 0x17
  *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
+static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
 	int i, num_msrs;
 	u64 hwcr;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 743370ee4983..5f42f25bac8f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
-	if (m->cpuvendor == X86_VENDOR_AMD ||
-	    m->cpuvendor == X86_VENDOR_HYGON) {
+	switch (m->cpuvendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+
+	case X86_VENDOR_INTEL:
+	case X86_VENDOR_ZHAOXIN:
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m)
 		return (m->status & 0xef80) == BIT(7) ||
 		       (m->status & 0xef00) == BIT(8) ||
 		       (m->status & 0xeffc) == 0xc;
-	}
 
-	return false;
+	default:
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
@@ -1127,6 +1132,12 @@ static bool __mc_check_crashing_cpu(int cpu)
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
+			if (mcgstatus & MCG_STATUS_LMCES)
+				return false;
+		}
+
 		if (mcgstatus & MCG_STATUS_RIPV) {
 			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 			return true;
@@ -1277,9 +1288,10 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	/*
 	 * Check if this MCE is signaled to only this logical processor,
-	 * on Intel only.
+	 * on Intel, Zhaoxin only.
 	 */
-	if (m.cpuvendor == X86_VENDOR_INTEL)
+	if (m.cpuvendor == X86_VENDOR_INTEL ||
+	    m.cpuvendor == X86_VENDOR_ZHAOXIN)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
@@ -1697,6 +1709,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+			if (cfg->monarch_timeout < 0)
+				cfg->monarch_timeout = USEC_PER_SEC;
+		}
+	}
+
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
 	if (cfg->bootlog != 0)
@@ -1760,6 +1784,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
 	}
 }
 
+static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+
+	/*
+	 * These CPUs have MCA bank 8 which reports only one error type called
+	 * SVAD (System View Address Decoder). The reporting of that error is
+	 * controlled by IA32_MC8.CTL.0.
+	 *
+	 * If enabled, prefetching on these CPUs will cause SVAD MCE when
+	 * virtual machines start and result in a system  panic. Always disable
+	 * bank 8 SVAD error by default.
+	 */
+	if ((c->x86 == 7 && c->x86_model == 0x1b) ||
+	    (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (this_cpu_read(mce_num_banks) > 8)
+			mce_banks[8].ctl = 0;
+	}
+
+	intel_init_cmci();
+	intel_init_lmce();
+	mce_adjust_timer = cmci_intel_adjust_timer;
+}
+
+static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}
+
 static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
@@ -1781,6 +1834,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_centaur_feature_init(c);
 		break;
 
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_init(c);
+		break;
+
 	default:
 		break;
 	}
@@ -1792,6 +1849,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_INTEL:
 		mce_intel_feature_clear(c);
 		break;
+
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_clear(c);
+		break;
+
 	default:
 		break;
 	}
@@ -2014,15 +2076,16 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
-	 * are socket-wide.
-	 * Disabling them for just a single offlined CPU is bad, since it will
-	 * inhibit reporting for all shared resources on the socket like the
-	 * last level cache (LLC), the integrated memory controller (iMC), etc.
+	 * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+	 * MSRs are socket-wide. Disabling them for just a single offlined CPU
+	 * is bad, since it will inhibit reporting for all shared resources on
+	 * the socket like the last level cache (LLC), the integrated memory
+	 * controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
 		return;
 
 	mce_disable_error_reporting();
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 88cd9598fa57..e270d0770134 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -85,8 +85,10 @@ static int cmci_supported(int *banks)
 	 * initialization is vendor keyed and this
 	 * makes sure none of the backdoors are entered otherwise.
 	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 0;
+
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -423,7 +425,7 @@ void cmci_disable_bank(int bank)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static void intel_init_cmci(void)
+void intel_init_cmci(void)
 {
 	int banks;
 
@@ -442,7 +444,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-static void intel_init_lmce(void)
+void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -455,7 +457,7 @@ static void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
-static void intel_clear_lmce(void)
+void intel_clear_lmce(void)
 {
 	u64 val;
 
@@ -482,6 +484,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 43031db429d2..842b273bce31 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval);
 bool mce_intel_cmci_poll(void);
 void mce_intel_hcpu_update(unsigned long cpu);
 void cmci_disable_bank(int bank);
+void intel_init_cmci(void);
+void intel_init_lmce(void);
+void intel_clear_lmce(void);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
 static inline void mce_intel_hcpu_update(unsigned long cpu) { }
 static inline void cmci_disable_bank(int bank) { }
+static inline void intel_init_cmci(void) { }
+static inline void intel_init_lmce(void) { }
+static inline void intel_clear_lmce(void) { }
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 6e2becf547c5..d01e0da0163a 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -40,15 +40,58 @@
 #define THERMAL_THROTTLING_EVENT	0
 #define POWER_LIMIT_EVENT		1
 
-/*
- * Current thermal event state:
+/**
+ * struct _thermal_state - Represent the current thermal event state
+ * @next_check:			Stores the next timestamp, when it is allowed
+ *				to log the next warning message.
+ * @last_interrupt_time:	Stores the timestamp for the last threshold
+ *				high event.
+ * @therm_work:			Delayed workqueue structure
+ * @count:			Stores the current running count for thermal
+ *				or power threshold interrupts.
+ * @last_count:			Stores the previous running count for thermal
+ *				or power threshold interrupts.
+ * @max_time_ms:		This shows the maximum amount of time CPU was
+ *				in throttled state for a single thermal
+ *				threshold high to low state.
+ * @total_time_ms:		This is a cumulative time during which CPU was
+ *				in the throttled state.
+ * @rate_control_active:	Set when a throttling message is logged.
+ *				This is used for the purpose of rate-control.
+ * @new_event:			Stores the last high/low status of the
+ *				THERM_STATUS_PROCHOT or
+ *				THERM_STATUS_POWER_LIMIT.
+ * @level:			Stores whether this _thermal_state instance is
+ *				for a CORE level or for PACKAGE level.
+ * @sample_index:		Index for storing the next sample in the buffer
+ *				temp_samples[].
+ * @sample_count:		Total number of samples collected in the buffer
+ *				temp_samples[].
+ * @average:			The last moving average of temperature samples
+ * @baseline_temp:		Temperature at which thermal threshold high
+ *				interrupt was generated.
+ * @temp_samples:		Storage for temperature samples to calculate
+ *				moving average.
+ *
+ * This structure is used to represent data related to thermal state for a CPU.
+ * There is a separate storage for core and package level for each CPU.
  */
 struct _thermal_state {
-	bool			new_event;
-	int			event;
 	u64			next_check;
+	u64			last_interrupt_time;
+	struct delayed_work	therm_work;
 	unsigned long		count;
 	unsigned long		last_count;
+	unsigned long		max_time_ms;
+	unsigned long		total_time_ms;
+	bool			rate_control_active;
+	bool			new_event;
+	u8			level;
+	u8			sample_index;
+	u8			sample_count;
+	u8			average;
+	u8			baseline_temp;
+	u8			temp_samples[3];
 };
 
 struct thermal_state {
@@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count);
 define_therm_throt_device_show_func(package_power_limit, count);
 define_therm_throt_device_one_ro(package_power_limit_count);
 
+define_therm_throt_device_show_func(core_throttle, max_time_ms);
+define_therm_throt_device_one_ro(core_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, max_time_ms);
+define_therm_throt_device_one_ro(package_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(core_throttle, total_time_ms);
+define_therm_throt_device_one_ro(core_throttle_total_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, total_time_ms);
+define_therm_throt_device_one_ro(package_throttle_total_time_ms);
+
 static struct attribute *thermal_throttle_attrs[] = {
 	&dev_attr_core_throttle_count.attr,
+	&dev_attr_core_throttle_max_time_ms.attr,
+	&dev_attr_core_throttle_total_time_ms.attr,
 	NULL
 };
 
@@ -135,6 +192,105 @@ static const struct attribute_group thermal_attr_group = {
 #define CORE_LEVEL	0
 #define PACKAGE_LEVEL	1
 
+#define THERM_THROT_POLL_INTERVAL	HZ
+#define THERM_STATUS_PROCHOT_LOG	BIT(1)
+
+static void clear_therm_status_log(int level)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG);
+}
+
+static void get_therm_status(int level, bool *proc_hot, u8 *temp)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	if (msr_val & THERM_STATUS_PROCHOT_LOG)
+		*proc_hot = true;
+	else
+		*proc_hot = false;
+
+	*temp = (msr_val >> 16) & 0x7F;
+}
+
+static void throttle_active_work(struct work_struct *work)
+{
+	struct _thermal_state *state = container_of(to_delayed_work(work),
+						struct _thermal_state, therm_work);
+	unsigned int i, avg, this_cpu = smp_processor_id();
+	u64 now = get_jiffies_64();
+	bool hot;
+	u8 temp;
+
+	get_therm_status(state->level, &hot, &temp);
+	/* temperature value is offset from the max so lesser means hotter */
+	if (!hot && temp > state->baseline_temp) {
+		if (state->rate_control_active)
+			pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n",
+				this_cpu,
+				state->level == CORE_LEVEL ? "Core" : "Package",
+				state->count);
+
+		state->rate_control_active = false;
+		return;
+	}
+
+	if (time_before64(now, state->next_check) &&
+			  state->rate_control_active)
+		goto re_arm;
+
+	state->next_check = now + CHECK_INTERVAL;
+
+	if (state->count != state->last_count) {
+		/* There was one new thermal interrupt */
+		state->last_count = state->count;
+		state->average = 0;
+		state->sample_count = 0;
+		state->sample_index = 0;
+	}
+
+	state->temp_samples[state->sample_index] = temp;
+	state->sample_count++;
+	state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples);
+	if (state->sample_count < ARRAY_SIZE(state->temp_samples))
+		goto re_arm;
+
+	avg = 0;
+	for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i)
+		avg += state->temp_samples[i];
+
+	avg /= ARRAY_SIZE(state->temp_samples);
+
+	if (state->average > avg) {
+		pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n",
+			this_cpu,
+			state->level == CORE_LEVEL ? "Core" : "Package",
+			state->count);
+		state->rate_control_active = true;
+	}
+
+	state->average = avg;
+
+re_arm:
+	clear_therm_status_log(state->level);
+	schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+}
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -178,27 +334,33 @@ static void therm_throt_process(bool new_event, int event, int level)
 	if (new_event)
 		state->count++;
 
-	if (time_before64(now, state->next_check) &&
-			state->count != state->last_count)
+	if (event != THERMAL_THROTTLING_EVENT)
 		return;
 
-	state->next_check = now + CHECK_INTERVAL;
-	state->last_count = state->count;
+	if (new_event && !state->last_interrupt_time) {
+		bool hot;
+		u8 temp;
+
+		get_therm_status(state->level, &hot, &temp);
+		/*
+		 * Ignore short temperature spike as the system is not close
+		 * to PROCHOT. 10C offset is large enough to ignore. It is
+		 * already dropped from the high threshold temperature.
+		 */
+		if (temp > 10)
+			return;
 
-	/* if we just entered the thermal event */
-	if (new_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
-				this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package",
-				state->count);
-		return;
-	}
-	if (old_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package");
-		return;
+		state->baseline_temp = temp;
+		state->last_interrupt_time = now;
+		schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+	} else if (old_event && state->last_interrupt_time) {
+		unsigned long throttle_time;
+
+		throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time);
+		if (throttle_time > state->max_time_ms)
+			state->max_time_ms = throttle_time;
+		state->total_time_ms += throttle_time;
+		state->last_interrupt_time = 0;
 	}
 }
 
@@ -244,20 +406,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu)
 	if (err)
 		return err;
 
-	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+	}
+
 	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
-		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_max_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_total_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 			err = sysfs_add_file_to_group(&dev->kobj,
 					&dev_attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+			if (err)
+				goto del_group;
+		}
 	}
 
+	return 0;
+
+del_group:
+	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
+
 	return err;
 }
 
@@ -269,15 +458,29 @@ static void thermal_throttle_remove_dev(struct device *dev)
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
 static int thermal_throttle_online(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	state->package_throttle.level = PACKAGE_LEVEL;
+	state->core_throttle.level = CORE_LEVEL;
+
+	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
+	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
+
 	return thermal_throttle_add_dev(dev, cpu);
 }
 
 static int thermal_throttle_offline(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	cancel_delayed_work(&state->package_throttle.therm_work);
+	cancel_delayed_work(&state->core_throttle.therm_work);
+
+	state->package_throttle.rate_control_active = false;
+	state->core_throttle.rate_control_active = false;
+
 	thermal_throttle_remove_dev(dev);
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a0e52bd00ecc..3f6b137ef4e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 void reload_ucode_amd(void)
 {
 	struct microcode_amd *mc;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
 
@@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
 	enum ucode_state ret;
-	u32 rev, dummy;
+	u32 rev, dummy __always_unused;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index cb0fdcaf1415..7019d4b2df0c 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
-/*
- * Serialize late loading so that CPUs get updated one-by-one.
- */
-static DEFINE_RAW_SPINLOCK(update_lock);
-
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -566,11 +561,18 @@ static int __reload_late(void *info)
 	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
 		return -1;
 
-	raw_spin_lock(&update_lock);
-	apply_microcode_local(&err);
-	raw_spin_unlock(&update_lock);
+	/*
+	 * On an SMT system, it suffices to load the microcode on one sibling of
+	 * the core because the microcode engine is shared between the threads.
+	 * Synchronization still needs to take place so that no concurrent
+	 * loading attempts happen on multiple threads of an SMT core. See
+	 * below.
+	 */
+	if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
+		apply_microcode_local(&err);
+	else
+		goto wait_for_siblings;
 
-	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
 		ret = -1;
@@ -578,14 +580,18 @@ static int __reload_late(void *info)
 		ret = 1;
 	}
 
+wait_for_siblings:
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
+		panic("Timeout during microcode update!\n");
+
 	/*
-	 * Increase the wait timeout to a safe value here since we're
-	 * serializing the microcode update and that could take a while on a
-	 * large number of CPUs. And that is fine as the *actual* timeout will
-	 * be determined by the last CPU finished updating and thus cut short.
+	 * At least one thread has completed update on each core.
+	 * For others, simply call the update to make sure the
+	 * per-cpu cpuinfo can be updated with right microcode
+	 * revision.
 	 */
-	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
-		panic("Timeout during microcode update!\n");
+	if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
+		apply_microcode_local(&err);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce799cfe9434..6a99535d7f37 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	struct microcode_intel *mc;
 	enum ucode_state ret;
 	static int prev_rev;
@@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		return UCODE_ERROR;
 	}
 
-	if (rev != prev_rev) {
+	if (bsp && rev != prev_rev) {
 		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
 			rev,
 			mc->hdr.date & 0xffff,
@@ -852,7 +853,7 @@ out:
 	c->microcode	 = rev;
 
 	/* Update boot_cpu_data's revision too, if we're on the BSP: */
-	if (c->cpu_index == boot_cpu_data.cpu_index)
+	if (bsp)
 		boot_cpu_data.microcode = rev;
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 267daad8c036..c656d92cd708 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -216,6 +216,10 @@ static void __init ms_hyperv_init_platform(void)
 	int hv_host_info_ecx;
 	int hv_host_info_edx;
 
+#ifdef CONFIG_PARAVIRT
+	pv_info.name = "Hyper-V";
+#endif
+
 	/*
 	 * Extract the features and hints
 	 */
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index efbd54cc4e69..055c8613b531 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	md.priv = of->kn->priv;
 	resid = md.u.rid;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index a46dee8e78db..2e3b06d6bbc6 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	}
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	rdt_last_cmd_clear();
 	if (!rdtgrp) {
 		ret = -ENOENT;
-		rdt_last_cmd_puts("Directory was removed\n");
 		goto unlock;
 	}
 
@@ -2648,10 +2646,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	int ret;
 
 	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
-	rdt_last_cmd_clear();
 	if (!prdtgrp) {
 		ret = -ENODEV;
-		rdt_last_cmd_puts("Directory was removed\n");
 		goto out_unlock;
 	}
 
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
new file mode 100644
index 000000000000..3e20d322bc98
--- /dev/null
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Transactional Synchronization Extensions (TSX) control.
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author:
+ *	Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
+ */
+
+#include <linux/cpufeature.h>
+
+#include <asm/cmdline.h>
+
+#include "cpu.h"
+
+enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED;
+
+void tsx_disable(void)
+{
+	u64 tsx;
+
+	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+
+	/* Force all transactions to immediately abort */
+	tsx |= TSX_CTRL_RTM_DISABLE;
+
+	/*
+	 * Ensure TSX support is not enumerated in CPUID.
+	 * This is visible to userspace and will ensure they
+	 * do not waste resources trying TSX transactions that
+	 * will always abort.
+	 */
+	tsx |= TSX_CTRL_CPUID_CLEAR;
+
+	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+}
+
+void tsx_enable(void)
+{
+	u64 tsx;
+
+	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+
+	/* Enable the RTM feature in the cpu */
+	tsx &= ~TSX_CTRL_RTM_DISABLE;
+
+	/*
+	 * Ensure TSX support is enumerated in CPUID.
+	 * This is visible to userspace and will ensure they
+	 * can enumerate and use the TSX feature.
+	 */
+	tsx &= ~TSX_CTRL_CPUID_CLEAR;
+
+	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+}
+
+static bool __init tsx_ctrl_is_supported(void)
+{
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
+	/*
+	 * TSX is controlled via MSR_IA32_TSX_CTRL.  However, support for this
+	 * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES.
+	 *
+	 * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a
+	 * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES
+	 * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get
+	 * MSR_IA32_TSX_CTRL support even after a microcode update. Thus,
+	 * tsx= cmdline requests will do nothing on CPUs without
+	 * MSR_IA32_TSX_CTRL support.
+	 */
+	return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR);
+}
+
+static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_TAA))
+		return TSX_CTRL_DISABLE;
+
+	return TSX_CTRL_ENABLE;
+}
+
+void __init tsx_init(void)
+{
+	char arg[5] = {};
+	int ret;
+
+	if (!tsx_ctrl_is_supported())
+		return;
+
+	ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg));
+	if (ret >= 0) {
+		if (!strcmp(arg, "on")) {
+			tsx_ctrl_state = TSX_CTRL_ENABLE;
+		} else if (!strcmp(arg, "off")) {
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+		} else if (!strcmp(arg, "auto")) {
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
+		} else {
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+			pr_err("tsx: invalid option, defaulting to off\n");
+		}
+	} else {
+		/* tsx= not provided */
+		if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO))
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
+		else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF))
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+		else
+			tsx_ctrl_state = TSX_CTRL_ENABLE;
+	}
+
+	if (tsx_ctrl_state == TSX_CTRL_DISABLE) {
+		tsx_disable();
+
+		/*
+		 * tsx_disable() will change the state of the
+		 * RTM CPUID bit.  Clear it here since it is now
+		 * expected to be not set.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_RTM);
+	} else if (tsx_ctrl_state == TSX_CTRL_ENABLE) {
+
+		/*
+		 * HW defaults TSX to be enabled at bootup.
+		 * We may still need the TSX enable support
+		 * during init for special cases like
+		 * kexec after TSX is disabled.
+		 */
+		tsx_enable();
+
+		/*
+		 * tsx_enable() will change the state of the
+		 * RTM CPUID bit.  Force it here since it is now
+		 * expected to be set.
+		 */
+		setup_force_cpu_cap(X86_FEATURE_RTM);
+	}
+}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 753b8cfe8b8a..87b97897a881 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
+	/*
+	 * Handle the case where stack trace is collected _before_
+	 * cea_exception_stacks had been initialized.
+	 */
+	if (!begin)
+		return false;
+
 	end = begin + sizeof(struct cea_exception_stacks);
 	/* Bail if @stack is outside the exception stack area. */
 	if (stk < begin || stk >= end)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6f6b1d04dadf..4cba91ec8049 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 29ffa495bd1c..206a4b6144c2 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -222,13 +222,31 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * we might write invalid pmds, when the kernel is relocated
 	 * cleanup_highmap() fixes this up along with the mappings
 	 * beyond _end.
+	 *
+	 * Only the region occupied by the kernel image has so far
+	 * been checked against the table of usable memory regions
+	 * provided by the firmware, so invalidate pages outside that
+	 * region. A page table entry that maps to a reserved area of
+	 * memory would allow processor speculation into that area,
+	 * and on some hardware (particularly the UV platform) even
+	 * speculative access to some reserved areas is caught as an
+	 * error, causing the BIOS to halt the system.
 	 */
 
 	pmd = fixup_pointer(level2_kernel_pgt, physaddr);
-	for (i = 0; i < PTRS_PER_PMD; i++) {
+
+	/* invalidate pages before the kernel image */
+	for (i = 0; i < pmd_index((unsigned long)_text); i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	/* fixup pages that are part of the kernel image */
+	for (; i <= pmd_index((unsigned long)_end); i++)
 		if (pmd[i] & _PAGE_PRESENT)
 			pmd[i] += load_delta;
-	}
+
+	/* invalidate pages after the kernel image */
+	for (; i < PTRS_PER_PMD; i++)
+		pmd[i] &= ~_PAGE_PRESENT;
 
 	/*
 	 * Fixup phys_base - remove the memory encryption mask to obtain
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c59454c382fd..7e322e2daaf5 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1505,6 +1505,9 @@ void __init tsc_init(void)
 		return;
 	}
 
+	if (tsc_clocksource_reliable || no_tsc_watchdog)
+		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9c5029cf6f3f..f68c0c753c38 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 87b0fcc23ef8..b29d00b661ff 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -111,11 +111,6 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
-{
-	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
-}
-
 static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 {
 	return apic->vcpu->vcpu_id;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 2aad7e226fc0..1f5014852e20 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -242,4 +242,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
 	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 }
 
+static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
+{
+	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
+}
+
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 24c23c66b226..2ce9da58611e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
+#include <linux/kthread.h>
 
 #include <asm/page.h>
 #include <asm/pat.h>
@@ -47,6 +48,35 @@
 #include <asm/kvm_page_track.h>
 #include "trace.h"
 
+extern bool itlb_multihit_kvm_mitigation;
+
+static int __read_mostly nx_huge_pages = -1;
+#ifdef CONFIG_PREEMPT_RT
+/* Recovery can cause latency spikes, disable it for PREEMPT_RT.  */
+static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
+#else
+static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
+#endif
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);
+
+static struct kernel_param_ops nx_huge_pages_ops = {
+	.set = set_nx_huge_pages,
+	.get = param_get_bool,
+};
+
+static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
+	.set = set_nx_huge_pages_recovery_ratio,
+	.get = param_get_uint,
+};
+
+module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages, "bool");
+module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
+		&nx_huge_pages_recovery_ratio, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
+
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
  * where the hardware walks 2 page tables:
@@ -352,6 +382,11 @@ static inline bool spte_ad_need_write_protect(u64 spte)
 	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
 }
 
+static bool is_nx_huge_page_enabled(void)
+{
+	return READ_ONCE(nx_huge_pages);
+}
+
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
 	MMU_WARN_ON(is_mmio_spte(spte));
@@ -1190,6 +1225,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 }
 
+static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	if (sp->lpage_disallowed)
+		return;
+
+	++kvm->stat.nx_lpage_splits;
+	list_add_tail(&sp->lpage_disallowed_link,
+		      &kvm->arch.lpage_disallowed_mmu_pages);
+	sp->lpage_disallowed = true;
+}
+
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
@@ -1207,6 +1253,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
+static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	--kvm->stat.nx_lpage_splits;
+	sp->lpage_disallowed = false;
+	list_del(&sp->lpage_disallowed_link);
+}
+
 static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
 					  struct kvm_memory_slot *slot)
 {
@@ -2792,6 +2845,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 			kvm_reload_remote_mmus(kvm);
 	}
 
+	if (sp->lpage_disallowed)
+		unaccount_huge_nx_page(kvm, sp);
+
 	sp->role.invalid = 1;
 	return list_unstable;
 }
@@ -3013,6 +3069,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (!speculative)
 		spte |= spte_shadow_accessed_mask(spte);
 
+	if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
+	    is_nx_huge_page_enabled()) {
+		pte_access &= ~ACC_EXEC_MASK;
+	}
+
 	if (pte_access & ACC_EXEC_MASK)
 		spte |= shadow_x_mask;
 	else
@@ -3233,9 +3294,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
+static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
+				       gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
+{
+	int level = *levelp;
+	u64 spte = *it.sptep;
+
+	if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
+	    is_nx_huge_page_enabled() &&
+	    is_shadow_present_pte(spte) &&
+	    !is_large_pte(spte)) {
+		/*
+		 * A small SPTE exists for this pfn, but FNAME(fetch)
+		 * and __direct_map would like to create a large PTE
+		 * instead: just force them to go down another level,
+		 * patching back for them into pfn the next 9 bits of
+		 * the address.
+		 */
+		u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
+		*pfnp |= gfn & page_mask;
+		(*levelp)--;
+	}
+}
+
 static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 			int map_writable, int level, kvm_pfn_t pfn,
-			bool prefault)
+			bool prefault, bool lpage_disallowed)
 {
 	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
@@ -3248,6 +3332,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 
 	trace_kvm_mmu_spte_requested(gpa, level, pfn);
 	for_each_shadow_entry(vcpu, gpa, it) {
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &level);
+
 		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == level)
 			break;
@@ -3258,6 +3348,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 					      it.level - 1, true, ACC_ALL);
 
 			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
@@ -3306,7 +3398,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * here.
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
-	    level == PT_PAGE_TABLE_LEVEL &&
+	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompoundMap(pfn_to_page(pfn)) &&
 	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
@@ -3550,11 +3642,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 {
 	int r;
 	int level;
-	bool force_pt_level = false;
+	bool force_pt_level;
 	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, write = error_code & PFERR_WRITE_MASK;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
+	force_pt_level = lpage_disallowed;
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		/*
@@ -3588,7 +3683,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault);
+	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
@@ -4174,6 +4270,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	unsigned long mmu_seq;
 	int write = error_code & PFERR_WRITE_MASK;
 	bool map_writable;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
@@ -4184,8 +4282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	if (r)
 		return r;
 
-	force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
-							   PT_DIRECTORY_LEVEL);
+	force_pt_level =
+		lpage_disallowed ||
+		!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		if (level > PT_DIRECTORY_LEVEL &&
@@ -4214,7 +4313,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault);
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
+			 prefault, lpage_disallowed);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
@@ -5914,9 +6014,9 @@ restart:
 		 * the guest, and the guest page table is using 4K page size
 		 * mapping if the indirect sp has level = 1.
 		 */
-		if (sp->role.direct &&
-			!kvm_is_reserved_pfn(pfn) &&
-			PageTransCompoundMap(pfn_to_page(pfn))) {
+		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
+		    !kvm_is_zone_device_pfn(pfn) &&
+		    PageTransCompoundMap(pfn_to_page(pfn))) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
@@ -6155,10 +6255,59 @@ static void kvm_set_mmio_spte_mask(void)
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
 }
 
+static bool get_nx_auto_mode(void)
+{
+	/* Return true when CPU has the bug, and mitigations are ON */
+	return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
+}
+
+static void __set_nx_huge_pages(bool val)
+{
+	nx_huge_pages = itlb_multihit_kvm_mitigation = val;
+}
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
+{
+	bool old_val = nx_huge_pages;
+	bool new_val;
+
+	/* In "auto" mode deploy workaround only if CPU has the bug. */
+	if (sysfs_streq(val, "off"))
+		new_val = 0;
+	else if (sysfs_streq(val, "force"))
+		new_val = 1;
+	else if (sysfs_streq(val, "auto"))
+		new_val = get_nx_auto_mode();
+	else if (strtobool(val, &new_val) < 0)
+		return -EINVAL;
+
+	__set_nx_huge_pages(new_val);
+
+	if (new_val != old_val) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list) {
+			mutex_lock(&kvm->slots_lock);
+			kvm_mmu_zap_all_fast(kvm);
+			mutex_unlock(&kvm->slots_lock);
+
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+		}
+		mutex_unlock(&kvm_lock);
+	}
+
+	return 0;
+}
+
 int kvm_mmu_module_init(void)
 {
 	int ret = -ENOMEM;
 
+	if (nx_huge_pages == -1)
+		__set_nx_huge_pages(get_nx_auto_mode());
+
 	/*
 	 * MMU roles use union aliasing which is, generally speaking, an
 	 * undefined behavior. However, we supposedly know how compilers behave
@@ -6238,3 +6387,116 @@ void kvm_mmu_module_exit(void)
 	unregister_shrinker(&mmu_shrinker);
 	mmu_audit_disable();
 }
+
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
+{
+	unsigned int old_val;
+	int err;
+
+	old_val = nx_huge_pages_recovery_ratio;
+	err = param_set_uint(val, kp);
+	if (err)
+		return err;
+
+	if (READ_ONCE(nx_huge_pages) &&
+	    !old_val && nx_huge_pages_recovery_ratio) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list)
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+
+		mutex_unlock(&kvm_lock);
+	}
+
+	return err;
+}
+
+static void kvm_recover_nx_lpages(struct kvm *kvm)
+{
+	int rcu_idx;
+	struct kvm_mmu_page *sp;
+	unsigned int ratio;
+	LIST_HEAD(invalid_list);
+	ulong to_zap;
+
+	rcu_idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+	to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
+	while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
+		/*
+		 * We use a separate list instead of just using active_mmu_pages
+		 * because the number of lpage_disallowed pages is expected to
+		 * be relatively small compared to the total.
+		 */
+		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+				      struct kvm_mmu_page,
+				      lpage_disallowed_link);
+		WARN_ON_ONCE(!sp->lpage_disallowed);
+		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+		WARN_ON_ONCE(sp->lpage_disallowed);
+
+		if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			if (to_zap)
+				cond_resched_lock(&kvm->mmu_lock);
+		}
+	}
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, rcu_idx);
+}
+
+static long get_nx_lpage_recovery_timeout(u64 start_time)
+{
+	return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
+		? start_time + 60 * HZ - get_jiffies_64()
+		: MAX_SCHEDULE_TIMEOUT;
+}
+
+static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+{
+	u64 start_time;
+	long remaining_time;
+
+	while (true) {
+		start_time = get_jiffies_64();
+		remaining_time = get_nx_lpage_recovery_timeout(start_time);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		while (!kthread_should_stop() && remaining_time > 0) {
+			schedule_timeout(remaining_time);
+			remaining_time = get_nx_lpage_recovery_timeout(start_time);
+			set_current_state(TASK_INTERRUPTIBLE);
+		}
+
+		set_current_state(TASK_RUNNING);
+
+		if (kthread_should_stop())
+			return 0;
+
+		kvm_recover_nx_lpages(kvm);
+	}
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+	int err;
+
+	err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+					  "kvm-nx-lpage-recovery",
+					  &kvm->arch.nx_lpage_recovery_thread);
+	if (!err)
+		kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+
+	return err;
+}
+
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
+{
+	if (kvm->arch.nx_lpage_recovery_thread)
+		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 11f8ec89433b..d55674f44a18 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
 int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+
+int kvm_mmu_post_init_vm(struct kvm *kvm);
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
+
 #endif
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7d5cdb3af594..97b21e7fd013 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault)
+			 kvm_pfn_t pfn, bool map_writable, bool prefault,
+			 bool lpage_disallowed)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
 	int top_level, ret;
-	gfn_t base_gfn;
+	gfn_t gfn, base_gfn;
 
 	direct_access = gw->pte_access;
 
@@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	base_gfn = gw->gfn;
+	/*
+	 * FNAME(page_fault) might have clobbered the bottom bits of
+	 * gw->gfn, restore them from the virtual address.
+	 */
+	gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
+	base_gfn = gfn;
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
 	for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
 		clear_sp_write_flooding_count(it.sptep);
-		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+
+		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == hlevel)
 			break;
 
@@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
 					      it.level - 1, true, direct_access);
 			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
@@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int r;
 	kvm_pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
+	bool force_pt_level = lpage_disallowed;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
 	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault);
+			 level, pfn, map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f8ecb6df5106..c5673bda4b66 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -734,8 +734,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu)
 static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	vcpu->arch.efer = efer;
-	if (!npt_enabled && !(efer & EFER_LMA))
-		efer &= ~EFER_LME;
+
+	if (!npt_enabled) {
+		/* Shadow paging assumes NX to be available.  */
+		efer |= EFER_NX;
+
+		if (!(efer & EFER_LMA))
+			efer &= ~EFER_LME;
+	}
 
 	to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
 	mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
@@ -4591,6 +4597,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (ldr == svm->ldr_reg)
 		return 0;
@@ -4598,7 +4605,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	avic_invalidate_logical_id_entry(vcpu);
 
 	if (ldr)
-		ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr);
+		ret = avic_ldr_write(vcpu, id, ldr);
 
 	if (!ret)
 		svm->ldr_reg = ldr;
@@ -4610,8 +4617,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
 {
 	u64 *old, *new;
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID);
-	u32 id = (apic_id_reg >> 24) & 0xff;
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (vcpu->vcpu_id == id)
 		return 0;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index e76eb4f07f6c..0e7c9301fe86 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2917,7 +2917,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 						 struct vmcs12 *vmcs12);
 
-static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2937,19 +2937,18 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
-		/*
-		 * If translation failed, no matter: This feature asks
-		 * to exit when accessing the given address, and if it
-		 * can never be accessed, this feature won't do
-		 * anything anyway.
-		 */
 		if (!is_error_page(page)) {
 			vmx->nested.apic_access_page = page;
 			hpa = page_to_phys(vmx->nested.apic_access_page);
 			vmcs_write64(APIC_ACCESS_ADDR, hpa);
 		} else {
-			secondary_exec_controls_clearbit(vmx,
-				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+			pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n",
+					     __func__);
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+				KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return false;
 		}
 	}
 
@@ -2994,6 +2993,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
 	else
 		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+	return true;
 }
 
 /*
@@ -3032,13 +3032,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 /*
  * If from_vmentry is false, this is being called from state restore (either RSM
  * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
-+ *
-+ * Returns:
-+ *   0 - success, i.e. proceed with actual VMEnter
-+ *   1 - consistency check VMExit
-+ *  -1 - consistency check VMFail
+ *
+ * Returns:
+ *	NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
+ *	NVMX_ENTRY_VMFAIL:  Consistency check VMFail
+ *	NVMX_ENTRY_VMEXIT:  Consistency check VMExit
+ *	NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
  */
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+							bool from_vmentry)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -3081,11 +3083,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	prepare_vmcs02_early(vmx, vmcs12);
 
 	if (from_vmentry) {
-		nested_get_vmcs12_pages(vcpu);
+		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
 
 		if (nested_vmx_check_vmentry_hw(vcpu)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-			return -1;
+			return NVMX_VMENTRY_VMFAIL;
 		}
 
 		if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
@@ -3149,7 +3152,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * returned as far as L1 is concerned. It will only return (and set
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
-	return 0;
+	return NVMX_VMENTRY_SUCCESS;
 
 	/*
 	 * A failed consistency check that leads to a VMExit during L1's
@@ -3165,14 +3168,14 @@ vmentry_fail_vmexit:
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
 	if (!from_vmentry)
-		return 1;
+		return NVMX_VMENTRY_VMEXIT;
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
 	vmcs12->exit_qualification = exit_qual;
 	if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
-	return 1;
+	return NVMX_VMENTRY_VMEXIT;
 }
 
 /*
@@ -3182,9 +3185,9 @@ vmentry_fail_vmexit:
 static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 {
 	struct vmcs12 *vmcs12;
+	enum nvmx_vmentry_status status;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
-	int ret;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -3244,13 +3247,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 	vmx->nested.nested_run_pending = 1;
-	ret = nested_vmx_enter_non_root_mode(vcpu, true);
-	vmx->nested.nested_run_pending = !ret;
-	if (ret > 0)
-		return 1;
-	else if (ret)
-		return nested_vmx_failValid(vcpu,
-			VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+	status = nested_vmx_enter_non_root_mode(vcpu, true);
+	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
+		goto vmentry_failed;
 
 	/* Hide L1D cache contents from the nested guest.  */
 	vmx->vcpu.arch.l1tf_flush_l1d = true;
@@ -3281,6 +3280,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return kvm_vcpu_halt(vcpu);
 	}
 	return 1;
+
+vmentry_failed:
+	vmx->nested.nested_run_pending = 0;
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+		return 0;
+	if (status == NVMX_VMENTRY_VMEXIT)
+		return 1;
+	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
+	return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 187d39bf0bf1..6280f33e5fa6 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -6,6 +6,16 @@
 #include "vmcs12.h"
 #include "vmx.h"
 
+/*
+ * Status returned by nested_vmx_enter_non_root_mode():
+ */
+enum nvmx_vmentry_status {
+	NVMX_VMENTRY_SUCCESS,		/* Entered VMX non-root mode */
+	NVMX_VMENTRY_VMFAIL,		/* Consistency check VMFail */
+	NVMX_VMENTRY_VMEXIT,		/* Consistency check VMExit */
+	NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */
+};
+
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
 void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
@@ -13,7 +23,8 @@ void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_vcpu_setup(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry);
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+						     bool from_vmentry);
 bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason);
 void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		       u32 exit_intr_info, unsigned long exit_qualification);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e7970a2e8eae..04a8212704c1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -969,17 +969,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	u64 guest_efer = vmx->vcpu.arch.efer;
 	u64 ignore_bits = 0;
 
-	if (!enable_ept) {
-		/*
-		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
-		 * host CPUID is more efficient than testing guest CPUID
-		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
-		 */
-		if (boot_cpu_has(X86_FEATURE_SMEP))
-			guest_efer |= EFER_NX;
-		else if (!(guest_efer & EFER_NX))
-			ignore_bits |= EFER_NX;
-	}
+	/* Shadow paging assumes NX to be available.  */
+	if (!enable_ept)
+		guest_efer |= EFER_NX;
 
 	/*
 	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
@@ -1276,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
+	/*
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
+	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
+	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
+	 * correctly.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		goto after_clear_sn;
+	}
+
 	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
@@ -1291,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	} while (cmpxchg64(&pi_desc->control, old.control,
 			   new.control) != old.control);
 
+after_clear_sn:
+
 	/*
 	 * Clear SN before reading the bitmap.  The VT-d firmware
 	 * writes the bitmap and reads SN atomically (5.2.3 in the
@@ -1299,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	smp_mb__after_atomic();
 
-	if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS))
+	if (!pi_is_pir_empty(pi_desc))
 		pi_set_on(pi_desc);
 }
 
@@ -5543,14 +5549,6 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x",
-		vmcs_read32(VM_EXIT_REASON));
-	return 1;
-}
-
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5602,15 +5600,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
 	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
 	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
-	[EXIT_REASON_XSAVES]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_XRSTORS]                 = handle_unexpected_vmexit,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
 	[EXIT_REASON_INVPCID]                 = handle_invpcid,
 	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 	[EXIT_REASON_ENCLS]		      = handle_encls,
-	[EXIT_REASON_UMWAIT]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_TPAUSE]                  = handle_unexpected_vmexit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6157,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	if (pi_test_on(&vmx->pi_desc)) {
 		pi_clear_on(&vmx->pi_desc);
 		/*
-		 * IOMMU can write to PIR.ON, so the barrier matters even on UP.
+		 * IOMMU can write to PID.ON, so the barrier matters even on UP.
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
@@ -6187,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 
 static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
 {
-	return pi_test_on(vcpu_to_pi_desc(vcpu));
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	return pi_test_on(pi_desc) ||
+		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
 }
 
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index bee16687dc0b..5a0f34b1e226 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
 	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
 }
 
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+	return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
 static inline void pi_set_sn(struct pi_desc *pi_desc)
 {
 	set_bit(POSTED_INTR_SN,
@@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc)
 		(unsigned long *)&pi_desc->control);
 }
 
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
 static inline int pi_test_on(struct pi_desc *pi_desc)
 {
 	return test_bit(POSTED_INTR_ON,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 661e2bf38526..5d530521f11d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -213,6 +213,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages, .mode = 0444) },
+	{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -360,8 +361,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	if (!kvm_rebooting)
-		BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -1133,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
  * may depend on host virtualization features rather than host cpu features.
  */
 
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1180,9 +1182,10 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
 };
 
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1221,7 +1224,7 @@ static u32 emulated_msrs[] = {
 	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
 	 * We always support the "true" VMX control MSRs, even if the host
 	 * processor does not, so I am putting these registers here rather
-	 * than in msrs_to_save.
+	 * than in msrs_to_save_all.
 	 */
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@@ -1240,13 +1243,14 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_POLL_CONTROL,
 };
 
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
 static unsigned num_emulated_msrs;
 
 /*
  * List of msr numbers which are used to expose MSR-based features that
  * can be used by a hypervisor to validate requested CPU features.
  */
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
 	MSR_IA32_VMX_PINBASED_CTLS,
@@ -1271,6 +1275,7 @@ static u32 msr_based_features[] = {
 	MSR_IA32_ARCH_CAPABILITIES,
 };
 
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
 static u64 kvm_get_arch_capabilities(void)
@@ -1281,6 +1286,14 @@ static u64 kvm_get_arch_capabilities(void)
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
 
 	/*
+	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+	 * the nested hypervisor runs with NX huge pages.  If it is not,
+	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+	 * L1 guests, so it need not worry about its own (L2) guests.
+	 */
+	data |= ARCH_CAP_PSCHANGE_MC_NO;
+
+	/*
 	 * If we're doing cache flushes (either "always" or "cond")
 	 * we will do one whenever the guest does a vmlaunch/vmresume.
 	 * If an outer hypervisor is doing the cache flush for us
@@ -1299,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void)
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
 
+	/*
+	 * On TAA affected systems, export MDS_NO=0 when:
+	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+	 *	- Updated microcode is present. This is detected by
+	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+	 *	  that VERW clears CPU buffers.
+	 *
+	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+	 * mitigation and don't complain:
+	 *
+	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
+	 *
+	 * If TSX is disabled on the system, guests are also mitigated against
+	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
+	    (data & ARCH_CAP_TSX_CTRL_MSR))
+		data &= ~ARCH_CAP_MDS_NO;
+
 	return data;
 }
 
@@ -2537,6 +2569,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2702,8 +2735,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2717,14 +2748,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -5093,22 +5123,26 @@ static void kvm_init_msr_list(void)
 {
 	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
-	unsigned i, j;
+	unsigned i;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
-			 "Please update the fixed PMCs in msrs_to_save[]");
+			 "Please update the fixed PMCs in msrs_to_saved_all[]");
 
 	perf_get_x86_pmu_capability(&x86_pmu);
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
-		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+	num_msrs_to_save = 0;
+	num_emulated_msrs = 0;
+	num_msr_based_features = 0;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
 		 * to the guests in some cases.
 		 */
-		switch (msrs_to_save[i]) {
+		switch (msrs_to_save_all[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_mpx_supported())
 				continue;
@@ -5136,17 +5170,17 @@ static void kvm_init_msr_list(void)
 			break;
 		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
 			if (!kvm_x86_ops->pt_supported() ||
-				msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 			break;
 		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
-			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 		}
@@ -5154,34 +5188,25 @@ static void kvm_init_msr_list(void)
 			break;
 		}
 
-		if (j < i)
-			msrs_to_save[j] = msrs_to_save[i];
-		j++;
+		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
 	}
-	num_msrs_to_save = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
 			continue;
 
-		if (j < i)
-			emulated_msrs[j] = emulated_msrs[i];
-		j++;
+		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
 	}
-	num_emulated_msrs = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
 		struct kvm_msr_entry msr;
 
-		msr.index = msr_based_features[i];
+		msr.index = msr_based_features_all[i];
 		if (kvm_get_msr_feature(&msr))
 			continue;
 
-		if (j < i)
-			msr_based_features[j] = msr_based_features[i];
-		j++;
+		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
 	}
-	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -7941,8 +7966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -9427,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
@@ -9455,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return kvm_x86_ops->vm_init(kvm);
 }
 
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return kvm_mmu_post_init_vm(kvm);
+}
+
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
@@ -9556,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 }
 EXPORT_SYMBOL_GPL(x86_set_memory_region);
 
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+	kvm_mmu_pre_destroy_vm(kvm);
+}
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 58f79ab32358..5bfea374a160 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -117,6 +117,14 @@ static void __init xen_banner(void)
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
+
+#ifdef CONFIG_X86_32
+	pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"
+		"Support for running as 32-bit PV-guest under Xen will soon be removed\n"
+		"from the Linux kernel!\n"
+		"Please use either a 64-bit kernel or switch to HVM or PVH mode!\n"
+		"WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n");
+#endif
 }
 
 static void __init xen_pv_init_platform(void)
diff --git a/arch/xtensa/boot/dts/virt.dts b/arch/xtensa/boot/dts/virt.dts
index a9dcd87b6eb1..611b98a02a65 100644
--- a/arch/xtensa/boot/dts/virt.dts
+++ b/arch/xtensa/boot/dts/virt.dts
@@ -56,7 +56,7 @@
 		reg = <0xf0100000 0x03f00000>;
 
 		     // BUS_ADDRESS(3)  CPU_PHYSICAL(1)  SIZE(2)
-		ranges = <0x01000000 0x0 0xf0000000  0xf0000000  0x0 0x00010000>,
+		ranges = <0x01000000 0x0 0x00000000  0xf0000000  0x0 0x00010000>,
 			 <0x02000000 0x0 0xf4000000  0xf4000000  0x0 0x08000000>;
 
 		     // PCI_DEVICE(3)  INT#(1)  CONTROLLER(PHANDLE)  CONTROLLER_DATA(2)
diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h
index aeb15f4c755b..be8b2be5a98b 100644
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -148,7 +148,7 @@ static inline void change_bit(unsigned int bit, volatile unsigned long *p)
 			"       getex   %0\n"
 			"       beqz    %0, 1b\n"
 			: "=&a" (tmp)
-			: "a" (~mask), "a" (p)
+			: "a" (mask), "a" (p)
 			: "memory");
 }
 
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index 6792928ba84a..3f80386f1883 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -100,7 +100,7 @@ do {									\
 	case 4: __put_user_asm(x, ptr, retval, 4, "s32i", __cb); break;	\
 	case 8: {							\
 		     __typeof__(*ptr) __v64 = x;			\
-		     retval = __copy_to_user(ptr, &__v64, 8);		\
+		     retval = __copy_to_user(ptr, &__v64, 8) ? -EFAULT : 0;	\
 		     break;						\
 	        }							\
 	default: __put_user_bad();					\
@@ -132,14 +132,14 @@ do {									\
 #define __check_align_1  ""
 
 #define __check_align_2				\
-	"   _bbci.l %3,  0, 1f		\n"	\
-	"   movi    %0, %4		\n"	\
+	"   _bbci.l %[addr], 0, 1f	\n"	\
+	"   movi    %[err], %[efault]	\n"	\
 	"   _j      2f			\n"
 
 #define __check_align_4				\
-	"   _bbsi.l %3,  0, 0f		\n"	\
-	"   _bbci.l %3,  1, 1f		\n"	\
-	"0: movi    %0, %4		\n"	\
+	"   _bbsi.l %[addr], 0, 0f	\n"	\
+	"   _bbci.l %[addr], 1, 1f	\n"	\
+	"0: movi    %[err], %[efault]	\n"	\
 	"   _j      2f			\n"
 
 
@@ -151,40 +151,40 @@ do {									\
  * WARNING: If you modify this macro at all, verify that the
  * __check_align_* macros still work.
  */
-#define __put_user_asm(x, addr, err, align, insn, cb)	\
+#define __put_user_asm(x_, addr_, err_, align, insn, cb)\
 __asm__ __volatile__(					\
 	__check_align_##align				\
-	"1: "insn"  %2, %3, 0		\n"		\
+	"1: "insn"  %[x], %[addr], 0	\n"		\
 	"2:				\n"		\
 	"   .section  .fixup,\"ax\"	\n"		\
 	"   .align 4			\n"		\
 	"   .literal_position		\n"		\
 	"5:				\n"		\
-	"   movi   %1, 2b		\n"		\
-	"   movi   %0, %4		\n"		\
-	"   jx     %1			\n"		\
+	"   movi   %[tmp], 2b		\n"		\
+	"   movi   %[err], %[efault]	\n"		\
+	"   jx     %[tmp]		\n"		\
 	"   .previous			\n"		\
 	"   .section  __ex_table,\"a\"	\n"		\
 	"   .long	1b, 5b		\n"		\
 	"   .previous"					\
-	:"=r" (err), "=r" (cb)				\
-	:"r" ((int)(x)), "r" (addr), "i" (-EFAULT), "0" (err))
+	:[err] "+r"(err_), [tmp] "=r"(cb)		\
+	:[x] "r"(x_), [addr] "r"(addr_), [efault] "i"(-EFAULT))
 
 #define __get_user_nocheck(x, ptr, size)			\
 ({								\
-	long __gu_err, __gu_val;				\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;		\
+	long __gu_err;						\
+	__get_user_size((x), (ptr), (size), __gu_err);		\
 	__gu_err;						\
 })
 
 #define __get_user_check(x, ptr, size)					\
 ({									\
-	long __gu_err = -EFAULT, __gu_val = 0;				\
+	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) *__gu_addr = (ptr);			\
-	if (access_ok(__gu_addr, size))			\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	if (access_ok(__gu_addr, size))					\
+		__get_user_size((x), __gu_addr, (size), __gu_err);	\
+	else								\
+		(x) = 0;						\
 	__gu_err;							\
 })
 
@@ -198,8 +198,17 @@ do {									\
 	case 1: __get_user_asm(x, ptr, retval, 1, "l8ui", __cb);  break;\
 	case 2: __get_user_asm(x, ptr, retval, 2, "l16ui", __cb); break;\
 	case 4: __get_user_asm(x, ptr, retval, 4, "l32i", __cb);  break;\
-	case 8: retval = __copy_from_user(&x, ptr, 8);    break;	\
-	default: (x) = __get_user_bad();				\
+	case 8: {							\
+		u64 __x;						\
+		if (unlikely(__copy_from_user(&__x, ptr, 8))) {		\
+			retval = -EFAULT;				\
+			(x) = 0;					\
+		} else {						\
+			(x) = *(__force __typeof__((ptr)))&__x;		\
+		}							\
+		break;							\
+	}								\
+	default: (x) = 0; __get_user_bad();				\
 	}								\
 } while (0)
 
@@ -208,25 +217,28 @@ do {									\
  * WARNING: If you modify this macro at all, verify that the
  * __check_align_* macros still work.
  */
-#define __get_user_asm(x, addr, err, align, insn, cb) \
-__asm__ __volatile__(			\
-	__check_align_##align			\
-	"1: "insn"  %2, %3, 0		\n"	\
-	"2:				\n"	\
-	"   .section  .fixup,\"ax\"	\n"	\
-	"   .align 4			\n"	\
-	"   .literal_position		\n"	\
-	"5:				\n"	\
-	"   movi   %1, 2b		\n"	\
-	"   movi   %2, 0		\n"	\
-	"   movi   %0, %4		\n"	\
-	"   jx     %1			\n"	\
-	"   .previous			\n"	\
-	"   .section  __ex_table,\"a\"	\n"	\
-	"   .long	1b, 5b		\n"	\
-	"   .previous"				\
-	:"=r" (err), "=r" (cb), "=r" (x)	\
-	:"r" (addr), "i" (-EFAULT), "0" (err))
+#define __get_user_asm(x_, addr_, err_, align, insn, cb) \
+do {							\
+	u32 __x = 0;					\
+	__asm__ __volatile__(				\
+		__check_align_##align			\
+		"1: "insn"  %[x], %[addr], 0	\n"	\
+		"2:				\n"	\
+		"   .section  .fixup,\"ax\"	\n"	\
+		"   .align 4			\n"	\
+		"   .literal_position		\n"	\
+		"5:				\n"	\
+		"   movi   %[tmp], 2b		\n"	\
+		"   movi   %[err], %[efault]	\n"	\
+		"   jx     %[tmp]		\n"	\
+		"   .previous			\n"	\
+		"   .section  __ex_table,\"a\"	\n"	\
+		"   .long	1b, 5b		\n"	\
+		"   .previous"				\
+		:[err] "+r"(err_), [tmp] "=r"(cb), [x] "+r"(__x) \
+		:[addr] "r"(addr_), [efault] "i"(-EFAULT)); \
+	(x_) = (__force __typeof__(*(addr_)))__x;	\
+} while (0)
 
 
 /*
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 04f19de46700..4092555828b1 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -119,13 +119,6 @@ EXPORT_SYMBOL(__invalidate_icache_range);
 // FIXME EXPORT_SYMBOL(screen_info);
 #endif
 
-EXPORT_SYMBOL(outsb);
-EXPORT_SYMBOL(outsw);
-EXPORT_SYMBOL(outsl);
-EXPORT_SYMBOL(insb);
-EXPORT_SYMBOL(insw);
-EXPORT_SYMBOL(insl);
-
 extern long common_exception_return;
 EXPORT_SYMBOL(common_exception_return);
 
diff --git a/block/Kconfig b/block/Kconfig
index 41c0917ce622..c23094a14a2b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME
 config BLK_SCSI_REQUEST
 	bool
 
+config BLK_CGROUP_RWSTAT
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
@@ -86,6 +89,7 @@ config BLK_DEV_ZONED
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
+	select BLK_CGROUP_RWSTAT
 	---help---
 	Block layer bio throttling support. It can be used to limit
 	the IO rate to a device. IO rate policies are per cgroup and
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index b89310a022ad..7df14133adc8 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -31,6 +31,7 @@ config IOSCHED_BFQ
 config BFQ_GROUP_IOSCHED
        bool "BFQ hierarchical scheduling support"
        depends on IOSCHED_BFQ && BLK_CGROUP
+       select BLK_CGROUP_RWSTAT
        ---help---
 
        Enable hierarchical scheduling in BFQ, using the blkio
diff --git a/block/Makefile b/block/Makefile
index 9ef57ace90d4..205a5f2fef17 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
+obj-$(CONFIG_BLK_CGROUP_RWSTAT)	+= blk-cgroup-rwstat.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_BLK_CGROUP_IOCOST)	+= blk-iocost.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 86a607cf19a1..cea0ae12f937 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -347,6 +347,14 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg)
 	bfqg_put(bfqg);
 }
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq)
+{
+	struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg);
+
+	blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq));
+	blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1);
+}
+
 /* @stats = 0 */
 static void bfqg_stats_reset(struct bfqg_stats *stats)
 {
@@ -431,6 +439,8 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+	blkg_rwstat_exit(&stats->bytes);
+	blkg_rwstat_exit(&stats->ios);
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
@@ -448,6 +458,10 @@ static void bfqg_stats_exit(struct bfqg_stats *stats)
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+	if (blkg_rwstat_init(&stats->bytes, gfp) ||
+	    blkg_rwstat_init(&stats->ios, gfp))
+		return -ENOMEM;
+
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
@@ -1057,18 +1071,35 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	return bfq_io_set_device_weight(of, buf, nbytes, off);
 }
 
-#ifdef CONFIG_BFQ_CGROUP_DEBUG
-static int bfqg_print_stat(struct seq_file *sf, void *v)
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
 	return 0;
 }
 
-static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+					struct blkg_policy_data *pd, int off)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
+	struct blkg_rwstat_sample sum;
+
+	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
 	return 0;
 }
 
@@ -1097,15 +1128,6 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, sum);
 }
 
-static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
-					struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample sum;
-
-	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
-	return __blkg_prfill_rwstat(sf, pd, &sum);
-}
-
 static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
@@ -1114,18 +1136,11 @@ static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
-			  seq_cft(sf)->private, true);
-	return 0;
-}
-
 static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
 			       int off)
 {
-	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+	struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg);
+	u64 sum = blkg_rwstat_total(&bfqg->stats.bytes);
 
 	return __blkg_prfill_u64(sf, pd, sum >> 9);
 }
@@ -1142,8 +1157,8 @@ static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
 {
 	struct blkg_rwstat_sample tmp;
 
-	blkg_rwstat_recursive_sum(pd->blkg, NULL,
-			offsetof(struct blkcg_gq, stat_bytes), &tmp);
+	blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq,
+			offsetof(struct bfq_group, stats.bytes), &tmp);
 
 	return __blkg_prfill_u64(sf, pd,
 		(tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9);
@@ -1226,13 +1241,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* statistics, covers only the tasks in the bfqg */
 	{
 		.name = "bfq.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat,
 	},
 	{
 		.name = "bfq.io_serviced",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
@@ -1269,13 +1284,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* the same statistics which cover the bfqg and its descendants */
 	{
 		.name = "bfq.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "bfq.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 0319d6339822..ad4af4aaf2ce 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2713,6 +2713,28 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
+
+static
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * To prevent bfqq's service guarantees from being violated,
+	 * bfqq may be left busy, i.e., queued for service, even if
+	 * empty (see comments in __bfq_bfqq_expire() for
+	 * details). But, if no process will send requests to bfqq any
+	 * longer, then there is no point in keeping bfqq queued for
+	 * service. In addition, keeping bfqq queued for service, but
+	 * with no process ref any longer, may have caused bfqq to be
+	 * freed when dequeued from service. But this is assumed to
+	 * never happen.
+	 */
+	if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) &&
+	    bfqq != bfqd->in_service_queue)
+		bfq_del_bfqq_busy(bfqd, bfqq, false);
+
+	bfq_put_queue(bfqq);
+}
+
 static void
 bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
@@ -2783,8 +2805,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	 */
 	new_bfqq->pid = -1;
 	bfqq->bic = NULL;
-	/* release process reference to bfqq */
-	bfq_put_queue(bfqq);
+	bfq_release_process_ref(bfqd, bfqq);
 }
 
 static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
@@ -4899,7 +4920,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq); /* release process reference */
+	bfq_release_process_ref(bfqd, bfqq);
 }
 
 static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
@@ -5001,8 +5022,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
 
 	bfqq = bic_to_bfqq(bic, false);
 	if (bfqq) {
-		/* release process reference on this queue */
-		bfq_put_queue(bfqq);
+		bfq_release_process_ref(bfqd, bfqq);
 		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
 		bic_set_bfqq(bic, bfqq, false);
 	}
@@ -5464,6 +5484,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio)
+		bfqg_stats_update_legacy_io(q, rq);
+#endif
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
 		spin_unlock_irq(&bfqd->lock);
@@ -5963,7 +5987,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 
 	bfq_put_cooperator(bfqq);
 
-	bfq_put_queue(bfqq);
+	bfq_release_process_ref(bfqq->bfqd, bfqq);
 	return NULL;
 }
 
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 5d1a519640f6..8526f20c53bc 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -10,6 +10,8 @@
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
+#include "blk-cgroup-rwstat.h"
+
 #define BFQ_IOPRIO_CLASSES	3
 #define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
 
@@ -809,6 +811,9 @@ struct bfq_stat {
 };
 
 struct bfqg_stats {
+	/* basic stats */
+	struct blkg_rwstat		bytes;
+	struct blkg_rwstat		ios;
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
@@ -956,6 +961,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 
 /* ---------------- cgroups-support interface ---------------- */
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
 			      unsigned int op);
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
@@ -1062,6 +1068,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
 			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
@@ -1078,6 +1086,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do {	\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str,	\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
diff --git a/block/bio.c b/block/bio.c
index 8f0ed6228fc5..b1170ec18464 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -751,7 +751,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return false;
 
-	if (bio->bi_vcnt > 0) {
+	if (bio->bi_vcnt > 0 && !bio_full(bio, len)) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
new file mode 100644
index 000000000000..85d5790ac49b
--- /dev/null
+++ b/block/blk-cgroup-rwstat.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#include "blk-cgroup-rwstat.h"
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
+{
+	int i, ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
+		if (ret) {
+			while (--i >= 0)
+				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+			return ret;
+		}
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_init);
+
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
+
+/**
+ * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @rwstat: rwstat to print
+ *
+ * Print @rwstat to @sf for the device assocaited with @pd.
+ */
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat)
+{
+	static const char *rwstr[] = {
+		[BLKG_RWSTAT_READ]	= "Read",
+		[BLKG_RWSTAT_WRITE]	= "Write",
+		[BLKG_RWSTAT_SYNC]	= "Sync",
+		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
+	};
+	const char *dname = blkg_dev_name(pd->blkg);
+	u64 v;
+	int i;
+
+	if (!dname)
+		return 0;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
+			   rwstat->cnt[i]);
+
+	v = rwstat->cnt[BLKG_RWSTAT_READ] +
+		rwstat->cnt[BLKG_RWSTAT_WRITE] +
+		rwstat->cnt[BLKG_RWSTAT_DISCARD];
+	seq_printf(sf, "%s Total %llu\n", dname, v);
+	return v;
+}
+EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
+
+/**
+ * blkg_prfill_rwstat - prfill callback for blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @off: offset to the blkg_rwstat in @pd
+ *
+ * prfill callback for printing a blkg_rwstat.
+ */
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off)
+{
+	struct blkg_rwstat_sample rwstat = { };
+
+	blkg_rwstat_read((void *)pd + off, &rwstat);
+	return __blkg_prfill_rwstat(sf, pd, &rwstat);
+}
+EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
+
+/**
+ * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
+ * @blkg: blkg of interest
+ * @pol: blkcg_policy which contains the blkg_rwstat
+ * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
+ * @sum: blkg_rwstat_sample structure containing the results
+ *
+ * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
+ * online descendants and their aux counts.  The caller must be holding the
+ * queue lock for online tests.
+ *
+ * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
+ * is at @off bytes into @blkg's blkg_policy_data of the policy.
+ */
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum)
+{
+	struct blkcg_gq *pos_blkg;
+	struct cgroup_subsys_state *pos_css;
+	unsigned int i;
+
+	lockdep_assert_held(&blkg->q->queue_lock);
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+		struct blkg_rwstat *rwstat;
+
+		if (!pos_blkg->online)
+			continue;
+
+		if (pol)
+			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
+		else
+			rwstat = (void *)pos_blkg + off;
+
+		for (i = 0; i < BLKG_RWSTAT_NR; i++)
+			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h
new file mode 100644
index 000000000000..ee746919c41f
--- /dev/null
+++ b/block/blk-cgroup-rwstat.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#ifndef _BLK_CGROUP_RWSTAT_H
+#define _BLK_CGROUP_RWSTAT_H
+
+#include <linux/blk-cgroup.h>
+
+enum blkg_rwstat_type {
+	BLKG_RWSTAT_READ,
+	BLKG_RWSTAT_WRITE,
+	BLKG_RWSTAT_SYNC,
+	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
+
+	BLKG_RWSTAT_NR,
+	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+};
+
+/*
+ * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
+ * recursive.  Used to carry stats of dead children.
+ */
+struct blkg_rwstat {
+	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
+	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
+};
+
+struct blkg_rwstat_sample {
+	u64				cnt[BLKG_RWSTAT_NR];
+};
+
+static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
+		unsigned int idx)
+{
+	return atomic64_read(&rwstat->aux_cnt[idx]) +
+		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
+}
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp);
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat);
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat);
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off);
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum);
+
+
+/**
+ * blkg_rwstat_add - add a value to a blkg_rwstat
+ * @rwstat: target blkg_rwstat
+ * @op: REQ_OP and flags
+ * @val: value to add
+ *
+ * Add @val to @rwstat.  The counters are chosen according to @rw.  The
+ * caller is responsible for synchronizing calls to this function.
+ */
+static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
+				   unsigned int op, uint64_t val)
+{
+	struct percpu_counter *cnt;
+
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+
+	if (op_is_sync(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+}
+
+/**
+ * blkg_rwstat_read - read the current values of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Read the current snapshot of @rwstat and return it in the aux counts.
+ */
+static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
+		struct blkg_rwstat_sample *result)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		result->cnt[i] =
+			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
+}
+
+/**
+ * blkg_rwstat_total - read the total count of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Return the total count of @rwstat regardless of the IO direction.  This
+ * function can be called without synchronization and takes care of u64
+ * atomicity.
+ */
+static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
+{
+	struct blkg_rwstat_sample tmp = { };
+
+	blkg_rwstat_read(rwstat, &tmp);
+	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
+}
+
+/**
+ * blkg_rwstat_reset - reset a blkg_rwstat
+ * @rwstat: blkg_rwstat to reset
+ */
+static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+}
+
+/**
+ * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
+ * @to: the destination blkg_rwstat
+ * @from: the source
+ *
+ * Add @from's count including the aux one to @to's aux count.
+ */
+static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
+				       struct blkg_rwstat *from)
+{
+	u64 sum[BLKG_RWSTAT_NR];
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
+			     &to->aux_cnt[i]);
+}
+#endif	/* _BLK_CGROUP_RWSTAT_H */
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b6f20be0fc78..708dea92dac8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 
-	blkg_rwstat_exit(&blkg->stat_ios);
-	blkg_rwstat_exit(&blkg->stat_bytes);
+	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
 }
@@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 				   gfp_t gfp_mask)
 {
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	/* alloc and init base part */
 	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
@@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask))
 		goto err_free;
 
-	if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
-	    blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
+	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
+	if (!blkg->iostat_cpu)
 		goto err_free;
 
 	blkg->q = q;
@@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
 	blkg->blkcg = blkcg;
 
+	u64_stats_init(&blkg->iostat.sync);
+	for_each_possible_cpu(cpu)
+		u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync);
+
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
@@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
 	struct blkcg *blkcg = blkg->blkcg;
-	struct blkcg_gq *parent = blkg->parent;
 	int i;
 
 	lockdep_assert_held(&blkg->q->queue_lock);
@@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 			pol->pd_offline_fn(blkg->pd[i]);
 	}
 
-	if (parent) {
-		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
-		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
-	}
-
 	blkg->online = false;
 
 	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
@@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		blkg_rwstat_reset(&blkg->stat_bytes);
-		blkg_rwstat_reset(&blkg->stat_ios);
+		for_each_possible_cpu(cpu) {
+			struct blkg_iostat_set *bis =
+				per_cpu_ptr(blkg->iostat_cpu, cpu);
+			memset(bis, 0, sizeof(*bis));
+		}
+		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -560,186 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 }
 EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
 
-/**
- * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @rwstat: rwstat to print
- *
- * Print @rwstat to @sf for the device assocaited with @pd.
- */
-u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-			 const struct blkg_rwstat_sample *rwstat)
-{
-	static const char *rwstr[] = {
-		[BLKG_RWSTAT_READ]	= "Read",
-		[BLKG_RWSTAT_WRITE]	= "Write",
-		[BLKG_RWSTAT_SYNC]	= "Sync",
-		[BLKG_RWSTAT_ASYNC]	= "Async",
-		[BLKG_RWSTAT_DISCARD]	= "Discard",
-	};
-	const char *dname = blkg_dev_name(pd->blkg);
-	u64 v;
-	int i;
-
-	if (!dname)
-		return 0;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
-			   rwstat->cnt[i]);
-
-	v = rwstat->cnt[BLKG_RWSTAT_READ] +
-		rwstat->cnt[BLKG_RWSTAT_WRITE] +
-		rwstat->cnt[BLKG_RWSTAT_DISCARD];
-	seq_printf(sf, "%s Total %llu\n", dname, v);
-	return v;
-}
-EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
-
-/**
- * blkg_prfill_rwstat - prfill callback for blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @off: offset to the blkg_rwstat in @pd
- *
- * prfill callback for printing a blkg_rwstat.
- */
-u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-		       int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
-
-static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
-				    struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd->blkg + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_bytes.
- * cftype->private must be set to the blkcg_policy.
- */
-int blkg_print_stat_bytes(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_ios.  cftype->private
- * must be set to the blkcg_policy.
- */
-int blkg_print_stat_ios(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios);
-
-static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
-					      struct blkg_policy_data *pd,
-					      int off)
-{
-	struct blkg_rwstat_sample rwstat;
-
-	blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- */
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field_recursive,
-			  (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);
-
-/**
- * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
- * @sf: seq_file to print to
- * @v: unused
- */
-int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field_recursive,
-			  (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);
-
-/**
- * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
- * @blkg: blkg of interest
- * @pol: blkcg_policy which contains the blkg_rwstat
- * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
- * @sum: blkg_rwstat_sample structure containing the results
- *
- * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
- * online descendants and their aux counts.  The caller must be holding the
- * queue lock for online tests.
- *
- * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
- * is at @off bytes into @blkg's blkg_policy_data of the policy.
- */
-void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
-		int off, struct blkg_rwstat_sample *sum)
-{
-	struct blkcg_gq *pos_blkg;
-	struct cgroup_subsys_state *pos_css;
-	unsigned int i;
-
-	lockdep_assert_held(&blkg->q->queue_lock);
-
-	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
-		struct blkg_rwstat *rwstat;
-
-		if (!pos_blkg->online)
-			continue;
-
-		if (pol)
-			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
-		else
-			rwstat = (void *)pos_blkg + off;
-
-		for (i = 0; i < BLKG_RWSTAT_NR; i++)
-			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
-
 /* Performs queue bypass and policy enabled checks then looks up blkg. */
 static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 					  const struct blkcg_policy *pol,
@@ -923,20 +744,27 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct blkcg_gq *blkg;
 
+	cgroup_rstat_flush(blkcg->css.cgroup);
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkg_iostat_set *bis = &blkg->iostat;
 		const char *dname;
 		char *buf;
-		struct blkg_rwstat_sample rwstat;
 		u64 rbytes, wbytes, rios, wios, dbytes, dios;
 		size_t size = seq_get_buf(sf, &buf), off = 0;
 		int i;
 		bool has_stats = false;
+		unsigned seq;
+
+		spin_lock_irq(&blkg->q->queue_lock);
+
+		if (!blkg->online)
+			goto skip;
 
 		dname = blkg_dev_name(blkg);
 		if (!dname)
-			continue;
+			goto skip;
 
 		/*
 		 * Hooray string manipulation, count is the size written NOT
@@ -946,21 +774,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		 */
 		off += scnprintf(buf+off, size-off, "%s ", dname);
 
-		spin_lock_irq(&blkg->q->queue_lock);
-
-		blkg_rwstat_recursive_sum(blkg, NULL,
-				offsetof(struct blkcg_gq, stat_bytes), &rwstat);
-		rbytes = rwstat.cnt[BLKG_RWSTAT_READ];
-		wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD];
+		do {
+			seq = u64_stats_fetch_begin(&bis->sync);
 
-		blkg_rwstat_recursive_sum(blkg, NULL,
-					offsetof(struct blkcg_gq, stat_ios), &rwstat);
-		rios = rwstat.cnt[BLKG_RWSTAT_READ];
-		wios = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dios = rwstat.cnt[BLKG_RWSTAT_DISCARD];
-
-		spin_unlock_irq(&blkg->q->queue_lock);
+			rbytes = bis->cur.bytes[BLKG_IOSTAT_READ];
+			wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE];
+			dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD];
+			rios = bis->cur.ios[BLKG_IOSTAT_READ];
+			wios = bis->cur.ios[BLKG_IOSTAT_WRITE];
+			dios = bis->cur.ios[BLKG_IOSTAT_DISCARD];
+		} while (u64_stats_fetch_retry(&bis->sync, seq));
 
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
@@ -999,6 +822,8 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 				seq_commit(sf, -1);
 			}
 		}
+	skip:
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 
 	rcu_read_unlock();
@@ -1294,6 +1119,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset)
 	return ret;
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] += src->bytes[i];
+		dst->ios[i] += src->ios[i];
+	}
+}
+
+static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] -= src->bytes[i];
+		dst->ios[i] -= src->ios[i];
+	}
+}
+
+static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkcg_gq *parent = blkg->parent;
+		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		struct blkg_iostat cur, delta;
+		unsigned seq;
+
+		/* fetch the current per-cpu values */
+		do {
+			seq = u64_stats_fetch_begin(&bisc->sync);
+			blkg_iostat_set(&cur, &bisc->cur);
+		} while (u64_stats_fetch_retry(&bisc->sync, seq));
+
+		/* propagate percpu delta to global */
+		u64_stats_update_begin(&blkg->iostat.sync);
+		blkg_iostat_set(&delta, &cur);
+		blkg_iostat_sub(&delta, &bisc->last);
+		blkg_iostat_add(&blkg->iostat.cur, &delta);
+		blkg_iostat_add(&bisc->last, &delta);
+		u64_stats_update_end(&blkg->iostat.sync);
+
+		/* propagate global delta to parent */
+		if (parent) {
+			u64_stats_update_begin(&parent->iostat.sync);
+			blkg_iostat_set(&delta, &blkg->iostat.cur);
+			blkg_iostat_sub(&delta, &blkg->iostat.last);
+			blkg_iostat_add(&parent->iostat.cur, &delta);
+			blkg_iostat_add(&blkg->iostat.last, &delta);
+			u64_stats_update_end(&parent->iostat.sync);
+		}
+	}
+
+	rcu_read_unlock();
+}
+
 static void blkcg_bind(struct cgroup_subsys_state *root_css)
 {
 	int i;
@@ -1326,6 +1222,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
+	.css_rstat_flush = blkcg_rstat_flush,
 	.bind = blkcg_bind,
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
@@ -1362,7 +1259,7 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	struct blkg_policy_data *pd_prealloc = NULL;
-	struct blkcg_gq *blkg;
+	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1370,49 +1267,82 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
-pd_prealloc:
-	if (!pd_prealloc) {
-		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
-		if (!pd_prealloc) {
-			ret = -ENOMEM;
-			goto out_bypass_end;
-		}
-	}
-
+retry:
 	spin_lock_irq(&q->queue_lock);
 
-	/* blkg_list is pushed at the head, reverse walk to init parents first */
+	/* blkg_list is pushed at the head, reverse walk to allocate parents first */
 	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		struct blkg_policy_data *pd;
 
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
-		if (!pd)
-			swap(pd, pd_prealloc);
+		/* If prealloc matches, use it; otherwise try GFP_NOWAIT */
+		if (blkg == pinned_blkg) {
+			pd = pd_prealloc;
+			pd_prealloc = NULL;
+		} else {
+			pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q,
+					      blkg->blkcg);
+		}
+
 		if (!pd) {
+			/*
+			 * GFP_NOWAIT failed.  Free the existing one and
+			 * prealloc for @blkg w/ GFP_KERNEL.
+			 */
+			if (pinned_blkg)
+				blkg_put(pinned_blkg);
+			blkg_get(blkg);
+			pinned_blkg = blkg;
+
 			spin_unlock_irq(&q->queue_lock);
-			goto pd_prealloc;
+
+			if (pd_prealloc)
+				pol->pd_free_fn(pd_prealloc);
+			pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q,
+						       blkg->blkcg);
+			if (pd_prealloc)
+				goto retry;
+			else
+				goto enomem;
 		}
 
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
-		if (pol->pd_init_fn)
-			pol->pd_init_fn(pd);
 	}
 
+	/* all allocated, init in the same order */
+	if (pol->pd_init_fn)
+		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+			pol->pd_init_fn(blkg->pd[pol->plid]);
+
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
 	spin_unlock_irq(&q->queue_lock);
-out_bypass_end:
+out:
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
+	if (pinned_blkg)
+		blkg_put(pinned_blkg);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
+
+enomem:
+	/* alloc failed, nothing's initialized yet, free everything */
+	spin_lock_irq(&q->queue_lock);
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		if (blkg->pd[pol->plid]) {
+			pol->pd_free_fn(blkg->pd[pol->plid]);
+			blkg->pd[pol->plid] = NULL;
+		}
+	}
+	spin_unlock_irq(&q->queue_lock);
+	ret = -ENOMEM;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index d5e668ec751b..a1e228752083 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -132,6 +132,9 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(ZONE_RESET_ALL),
+	REQ_OP_NAME(ZONE_OPEN),
+	REQ_OP_NAME(ZONE_CLOSE),
+	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_registered(q));
+
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	mutex_lock(&q->sysfs_lock);
 	blk_set_queue_dying(q);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	mutex_unlock(&q->sysfs_lock);
 
 	/*
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
@@ -848,11 +851,7 @@ static inline int blk_partition_remap(struct bio *bio)
 	if (unlikely(bio_check_ro(bio, p)))
 		goto out;
 
-	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
-	 */
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) {
+	if (bio_sectors(bio)) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -936,6 +935,9 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 1db44ca0f4a6..e20a852ae432 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
+	blk_account_io_start(rq, true);
+
 	/*
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1eec9cbe5a0a..1777346baf06 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 	blk_mq_add_to_requeue_list(rq, add_front, true);
 }
 
+static void blk_account_io_flush(struct request *rq)
+{
+	struct hd_struct *part = &rq->rq_disk->part0;
+
+	part_stat_lock();
+	part_stat_inc(part, ios[STAT_FLUSH]);
+	part_stat_add(part, nsecs[STAT_FLUSH],
+		      ktime_get_ns() - rq->start_time_ns);
+	part_stat_unlock();
+}
+
 /**
  * blk_flush_complete_seq - complete flush sequence
  * @rq: PREFLUSH/FUA request being sequenced
@@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq,
 
 	case REQ_FSEQ_DONE:
 		/*
-		 * @rq was previously adjusted by blk_flush_issue() for
+		 * @rq was previously adjusted by blk_insert_flush() for
 		 * flush sequencing and may already have gone through the
 		 * flush data request completion path.  Restore @rq for
 		 * normal completion and end it.
@@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 	struct blk_mq_hw_ctx *hctx;
 
+	blk_account_io_flush(flush_rq);
+
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 2a3db80c1dce..e01267f99183 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1057,9 +1057,12 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 	atomic64_set(&iocg->active_period, cur_period);
 
 	/* already activated or breaking leaf-only constraint? */
-	for (i = iocg->level; i > 0; i--)
-		if (!list_empty(&iocg->active_list))
+	if (!list_empty(&iocg->active_list))
+		goto succeed_unlock;
+	for (i = iocg->level - 1; i > 0; i--)
+		if (!list_empty(&iocg->ancestors[i]->active_list))
 			goto fail_unlock;
+
 	if (iocg->child_active_sum)
 		goto fail_unlock;
 
@@ -1101,6 +1104,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 		ioc_start_period(ioc, now);
 	}
 
+succeed_unlock:
 	spin_unlock_irq(&ioc->lock);
 	return true;
 
@@ -2110,10 +2114,10 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
 			goto einval;
 	}
 
-	spin_lock_irq(&iocg->ioc->lock);
+	spin_lock(&iocg->ioc->lock);
 	iocg->cfg_weight = v;
 	weight_updated(iocg);
-	spin_unlock_irq(&iocg->ioc->lock);
+	spin_unlock(&iocg->ioc->lock);
 
 	blkg_conf_finish(&ctx);
 	return nbytes;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 48e6725b32ee..d783bdc4559b 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -293,7 +293,7 @@ split:
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
-	struct bio *split;
+	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
@@ -309,6 +309,21 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 				nr_segs);
 		break;
 	default:
+		/*
+		 * All drivers must accept single-segments bios that are <=
+		 * PAGE_SIZE.  This is a quick and dirty check that relies on
+		 * the fact that bi_io_vec[0] is always valid if a bio has data.
+		 * The check might lead to occasional false negatives when bios
+		 * are cloned, but compared to the performance impact of cloned
+		 * bios themselves the loop below doesn't matter anyway.
+		 */
+		if (!q->limits.chunk_sectors &&
+		    (*bio)->bi_vcnt == 1 &&
+		    ((*bio)->bi_io_vec[0].bv_len +
+		     (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) {
+			*nr_segs = 1;
+			break;
+		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a0d3ce30fa08..062229395a50 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(ctx, page);
+	res = entry->show(ctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(ctx, page, length);
+	res = entry->store(ctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(hctx, page);
+	res = entry->show(hctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(hctx, page, length);
+	res = entry->store(hctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 {
+	const size_t size = PAGE_SIZE - 1;
 	unsigned int i, first = 1;
-	ssize_t ret = 0;
+	int ret = 0, pos = 0;
 
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
-			ret += sprintf(ret + page, "%u", i);
+			ret = snprintf(pos + page, size - pos, "%u", i);
 		else
-			ret += sprintf(ret + page, ", %u", i);
+			ret = snprintf(pos + page, size - pos, ", %u", i);
+
+		if (ret >= size - pos)
+			break;
 
 		first = 0;
+		pos += ret;
 	}
 
-	ret += sprintf(ret + page, "\n");
-	return ret;
+	ret = snprintf(pos + page, size + 1 - pos, "\n");
+	return pos + ret;
 }
 
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 008388e82b5c..fbacde454718 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -15,14 +15,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
-{
-	if (!tags)
-		return true;
-
-	return sbitmap_any_bit_clear(&tags->bitmap_tags.sb);
-}
-
 /*
  * If a previously inactive queue goes active, bump the active user count.
  * We need to do this before try to allocate driver tag, then even if fail
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 61deab0b5a5a..15bc74acb57e 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
 			   struct blk_mq_ctx *ctx, unsigned int tag);
-extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..323c9cb28066 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 
 struct mq_inflight {
 	struct hd_struct *part;
-	unsigned int *inflight;
+	unsigned int inflight[2];
 };
 
 static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
@@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	/*
-	 * index[0] counts the specific partition that was asked for.
-	 */
 	if (rq->part == mi->part)
-		mi->inflight[0]++;
+		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
 }
 
 unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 {
-	unsigned inflight[2];
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 
-	return inflight[0];
-}
-
-static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
-				     struct request *rq, void *priv,
-				     bool reserved)
-{
-	struct mq_inflight *mi = priv;
-
-	if (rq->part == mi->part)
-		mi->inflight[rq_data_dir(rq)]++;
-
-	return true;
+	return mi.inflight[0] + mi.inflight[1];
 }
 
 void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 			 unsigned int inflight[2])
 {
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+	inflight[0] = mi.inflight[0];
+	inflight[1] = mi.inflight[1];
 }
 
 void blk_freeze_queue_start(struct request_queue *q)
@@ -276,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q)
 			blk_mq_tag_wakeup_all(hctx->tags, true);
 }
 
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
-{
-	return blk_mq_has_free_tags(hctx->tags);
-}
-EXPORT_SYMBOL(blk_mq_can_queue);
-
 /*
  * Only need start/end time stamping if we have iostat or
  * blk stats enabled, or using an IO scheduler.
@@ -663,18 +641,6 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-int blk_mq_request_started(struct request *rq)
-{
-	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_started);
-
-int blk_mq_request_completed(struct request *rq)
-{
-	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_completed);
-
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -1064,7 +1030,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	bool shared;
 
 	if (rq->tag != -1)
-		goto done;
+		return true;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
@@ -1079,7 +1045,6 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		data.hctx->tags->rqs[rq->tag] = rq;
 	}
 
-done:
 	return rq->tag != -1;
 }
 
@@ -1486,7 +1451,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	int srcu_idx;
 	bool need_run;
@@ -1504,12 +1469,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		blk_mq_hctx_has_pending(hctx);
 	hctx_unlock(hctx, srcu_idx);
 
-	if (need_run) {
+	if (need_run)
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
-		return true;
-	}
-
-	return false;
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2789,6 +2750,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	int i, j, end;
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
+	if (q->nr_hw_queues < set->nr_hw_queues) {
+		struct blk_mq_hw_ctx **new_hctxs;
+
+		new_hctxs = kcalloc_node(set->nr_hw_queues,
+				       sizeof(*new_hctxs), GFP_KERNEL,
+				       set->numa_node);
+		if (!new_hctxs)
+			return;
+		if (hctxs)
+			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+			       sizeof(*hctxs));
+		q->queue_hw_ctx = new_hctxs;
+		q->nr_hw_queues = set->nr_hw_queues;
+		kfree(hctxs);
+		hctxs = new_hctxs;
+	}
+
 	/* protect against switching io scheduler  */
 	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2844,19 +2822,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-/*
- * Maximum number of hardware queues we support. For single sets, we'll never
- * have more than the CPUs (software queues). For multiple sets, the tag_set
- * user may have set ->nr_hw_queues larger.
- */
-static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
-{
-	if (set->nr_maps == 1)
-		return nr_cpu_ids;
-
-	return max(set->nr_hw_queues, nr_cpu_ids);
-}
-
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q,
 						  bool elevator_init)
@@ -2876,12 +2841,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
 
-	q->nr_queues = nr_hw_queues(set);
-	q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
-						GFP_KERNEL, set->numa_node);
-	if (!q->queue_hw_ctx)
-		goto err_sys_init;
-
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
@@ -2929,7 +2888,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 err_hctxs:
 	kfree(q->queue_hw_ctx);
 	q->nr_hw_queues = 0;
-err_sys_init:
 	blk_mq_sysfs_deinit(q);
 err_poll:
 	blk_stat_free_callback(q->poll_cb);
@@ -3030,6 +2988,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
+static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
+				  int cur_nr_hw_queues, int new_nr_hw_queues)
+{
+	struct blk_mq_tags **new_tags;
+
+	if (cur_nr_hw_queues >= new_nr_hw_queues)
+		return 0;
+
+	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
+				GFP_KERNEL, set->numa_node);
+	if (!new_tags)
+		return -ENOMEM;
+
+	if (set->tags)
+		memcpy(new_tags, set->tags, cur_nr_hw_queues *
+		       sizeof(*set->tags));
+	kfree(set->tags);
+	set->tags = new_tags;
+	set->nr_hw_queues = new_nr_hw_queues;
+
+	return 0;
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -3083,9 +3064,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *),
-				 GFP_KERNEL, set->numa_node);
-	if (!set->tags)
+	if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
@@ -3126,7 +3105,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i, j;
 
-	for (i = 0; i < nr_hw_queues(set); i++)
+	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
 	for (j = 0; j < set->nr_maps; j++) {
@@ -3271,10 +3250,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
 	/*
-	 * Sync with blk_mq_queue_tag_busy_iter.
-	 */
-	synchronize_rcu();
-	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
 	 * updating the new sw to hw queue mappings.
@@ -3288,6 +3263,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister(q);
 	}
 
+	if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
+	    0)
+		goto reregister;
+
 	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -3304,6 +3283,7 @@ fallback:
 		blk_mq_map_swqueue(q);
 	}
 
+reregister:
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register(q);
 		blk_mq_debugfs_register_hctxs(q);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 32c62c64e6c2..eaaca8fc1c28 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_release(struct request_queue *q);
 
-/**
- * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
- * @rq: target request.
- */
-static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
-{
-	return READ_ONCE(rq->state);
-}
-
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index e8cb68f6958a..2bc43e94f4c4 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -108,16 +108,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
 {
-	struct rq_qos *cur, *prev = NULL;
-	for (cur = q->rq_qos; cur; cur = cur->next) {
-		if (cur == rqos) {
-			if (prev)
-				prev->next = rqos->next;
-			else
-				q->rq_qos = cur;
+	struct rq_qos **cur;
+
+	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
+		if (*cur == rqos) {
+			*cur = rqos->next;
 			break;
 		}
-		prev = cur;
 	}
 
 	blk_mq_debugfs_unregister_rqos(rqos);
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 457d9ba3eb20..6e7ec87d49fa 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h)
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
-	unsigned long flags;
 	struct list_head *list;
 
-	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
 	list_add_tail(&rq->ipi_list, list);
 
 	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
-	local_irq_restore(flags);
 }
 
 /*
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 940f15d600f8..7da302ff88d0 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	struct request_queue *q = rq->q;
 	struct blk_stat_callback *cb;
 	struct blk_rq_stat *stat;
-	int bucket;
+	int bucket, cpu;
 	u64 value;
 
 	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
@@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	blk_throtl_stat_add(rq, value);
 
 	rcu_read_lock();
+	cpu = get_cpu();
 	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
 		if (!blk_stat_is_active(cb))
 			continue;
@@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now)
 		if (bucket < 0)
 			continue;
 
-		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
+		stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
 		blk_rq_stat_add(stat, value);
-		put_cpu_ptr(cb->cpu_stat);
 	}
+	put_cpu();
 	rcu_read_unlock();
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 46f5198be017..fca9b158f4a0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->show(q, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
@@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->store(q, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 18f773e52dfb..98233c9c65a8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -12,6 +12,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-cgroup.h>
 #include "blk.h"
+#include "blk-cgroup-rwstat.h"
 
 /* Max dispatch from a group in 1 round */
 static int throtl_grp_quantum = 8;
@@ -176,6 +177,9 @@ struct throtl_grp {
 	unsigned int bio_cnt; /* total bios */
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
 	unsigned long bio_cnt_reset_time;
+
+	struct blkg_rwstat stat_bytes;
+	struct blkg_rwstat stat_ios;
 };
 
 /* We measure latency for request size from <= 4k to >= 1M */
@@ -489,6 +493,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	if (!tg)
 		return NULL;
 
+	if (blkg_rwstat_init(&tg->stat_bytes, gfp))
+		goto err_free_tg;
+
+	if (blkg_rwstat_init(&tg->stat_ios, gfp))
+		goto err_exit_stat_bytes;
+
 	throtl_service_queue_init(&tg->service_queue);
 
 	for (rw = READ; rw <= WRITE; rw++) {
@@ -513,6 +523,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
 
 	return &tg->pd;
+
+err_exit_stat_bytes:
+	blkg_rwstat_exit(&tg->stat_bytes);
+err_free_tg:
+	kfree(tg);
+	return NULL;
 }
 
 static void throtl_pd_init(struct blkg_policy_data *pd)
@@ -611,6 +627,8 @@ static void throtl_pd_free(struct blkg_policy_data *pd)
 	struct throtl_grp *tg = pd_to_tg(pd);
 
 	del_timer_sync(&tg->service_queue.pending_timer);
+	blkg_rwstat_exit(&tg->stat_bytes);
+	blkg_rwstat_exit(&tg->stat_ios);
 	kfree(tg);
 }
 
@@ -1464,6 +1482,32 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
+static int tg_print_rwstat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  blkg_prfill_rwstat, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 tg_prfill_rwstat_recursive(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat_sample sum;
+
+	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off,
+				  &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int tg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  tg_prfill_rwstat_recursive, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
@@ -1491,23 +1535,23 @@ static struct cftype throtl_legacy_files[] = {
 	},
 	{
 		.name = "throttle.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{
 		.name = "throttle.io_serviced",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{ }	/* terminate */
 };
@@ -2127,7 +2171,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw])
+	if (bio_flagged(bio, BIO_THROTTLED))
+		goto out;
+
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
+		blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
+				bio->bi_iter.bi_size);
+		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
+	}
+
+	if (!tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(&q->queue_lock);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 4bc5f260248a..6fad6f3f6980 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -93,172 +93,85 @@ unsigned int blkdev_nr_zones(struct block_device *bdev)
 	if (!blk_queue_is_zoned(q))
 		return 0;
 
-	return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
+	return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk));
 }
 EXPORT_SYMBOL_GPL(blkdev_nr_zones);
 
-/*
- * Check that a zone report belongs to this partition, and if yes, fix its start
- * sector and write pointer and return true. Return false otherwise.
- */
-static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
-{
-	sector_t offset = get_start_sect(bdev);
-
-	if (rep->start < offset)
-		return false;
-
-	rep->start -= offset;
-	if (rep->start + rep->len > bdev->bd_part->nr_sects)
-		return false;
-
-	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		rep->wp = rep->start + rep->len;
-	else
-		rep->wp -= offset;
-	return true;
-}
-
-static int blk_report_zones(struct gendisk *disk, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones)
-{
-	struct request_queue *q = disk->queue;
-	unsigned int z = 0, n, nrz = *nr_zones;
-	sector_t capacity = get_capacity(disk);
-	int ret;
-
-	while (z < nrz && sector < capacity) {
-		n = nrz - z;
-		ret = disk->fops->report_zones(disk, sector, &zones[z], &n);
-		if (ret)
-			return ret;
-		if (!n)
-			break;
-		sector += blk_queue_zone_sectors(q) * n;
-		z += n;
-	}
-
-	WARN_ON(z > *nr_zones);
-	*nr_zones = z;
-
-	return 0;
-}
-
 /**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
  * @sector:	Sector from which to report zones
- * @zones:	Array of zone structures where to return the zones information
- * @nr_zones:	Number of zone structures in the zone array
+ * @nr_zones:	Maximum number of zones to report
+ * @cb:		Callback function called for each reported zone
+ * @data:	Private data for the callback
  *
  * Description:
- *    Get zone information starting from the zone containing @sector.
- *    The number of zone information reported may be less than the number
- *    requested by @nr_zones. The number of zones actually reported is
- *    returned in @nr_zones.
- *    The caller must use memalloc_noXX_save/restore() calls to control
- *    memory allocations done within this function (zone array and command
- *    buffer allocation by the device driver).
+ *    Get zone information starting from the zone containing @sector for at most
+ *    @nr_zones, and call @cb for each zone reported by the device.
+ *    To report all zones in a device starting from @sector, the BLK_ALL_ZONES
+ *    constant can be passed to @nr_zones.
+ *    Returns the number of zones reported by the device, or a negative errno
+ *    value in case of failure.
+ *
+ *    Note: The caller must use memalloc_noXX_save/restore() calls to control
+ *    memory allocations done within this function.
  */
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones)
+			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int i, nrz;
-	int ret;
-
-	if (!blk_queue_is_zoned(q))
-		return -EOPNOTSUPP;
+	struct gendisk *disk = bdev->bd_disk;
+	sector_t capacity = get_capacity(disk);
 
-	/*
-	 * A block device that advertized itself as zoned must have a
-	 * report_zones method. If it does not have one defined, the device
-	 * driver has a bug. So warn about that.
-	 */
-	if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones))
+	if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
+	    WARN_ON_ONCE(!disk->fops->report_zones))
 		return -EOPNOTSUPP;
 
-	if (!*nr_zones || sector >= bdev->bd_part->nr_sects) {
-		*nr_zones = 0;
+	if (!nr_zones || sector >= capacity)
 		return 0;
-	}
-
-	nrz = min(*nr_zones,
-		  __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
-	ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
-			       zones, &nrz);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < nrz; i++) {
-		if (!blkdev_report_zone(bdev, zones))
-			break;
-		zones++;
-	}
 
-	*nr_zones = i;
-
-	return 0;
+	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-/*
- * Special case of zone reset operation to reset all zones in one command,
- * useful for applications like mkfs.
- */
-static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
-{
-	struct bio *bio = bio_alloc(gfp_mask, 0);
-	int ret;
-
-	/* across the zones operations, don't need any sectors */
-	bio_set_dev(bio, bdev);
-	bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
-
-	ret = submit_bio_wait(bio);
-	bio_put(bio);
-
-	return ret;
-}
-
 static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t sector,
 						sector_t nr_sectors)
 {
 	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
 		return false;
 
-	if (nr_sectors != part_nr_sects_read(bdev->bd_part))
-		return false;
 	/*
-	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
-	 * the entire disk, that is, if the blocks device start offset is 0 and
-	 * its capacity is the same as the entire disk.
+	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
+	 * of the applicable zone range is the entire disk.
 	 */
-	return get_start_sect(bdev) == 0 &&
-	       part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
+	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
 }
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(bdev->bd_disk);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	struct blk_plug plug;
 	int ret;
 
 	if (!blk_queue_is_zoned(q))
@@ -267,45 +180,62 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
+	if (!nr_sectors || end_sector > capacity)
 		/* Out of range */
 		return -EINVAL;
 
-	if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
-		return  __blkdev_reset_all_zones(bdev, gfp_mask);
-
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
-	if ((nr_sectors & (zone_sectors - 1)) &&
-	    end_sector != bdev->bd_part->nr_sects)
+	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
 		return -EINVAL;
 
-	blk_start_plug(&plug);
 	while (sector < end_sector) {
-
 		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
 
+		/*
+		 * Special case for the zone reset operation that reset all
+		 * zones, this is useful for applications like mkfs.
+		 */
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			break;
+		}
+
+		bio->bi_opf = op;
+		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
 		cond_resched();
-
 	}
 
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
-	blk_finish_plug(&plug);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
+
+struct zone_report_args {
+	struct blk_zone __user *zones;
+};
+
+static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
+				    void *data)
+{
+	struct zone_report_args *args = data;
+
+	if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
+		return -EFAULT;
+	return 0;
+}
 
 /*
  * BLKREPORTZONE ioctl processing.
@@ -315,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 			      unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
+	struct zone_report_args args;
 	struct request_queue *q;
 	struct blk_zone_report rep;
-	struct blk_zone *zones;
 	int ret;
 
 	if (!argp)
@@ -339,44 +269,29 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!rep.nr_zones)
 		return -EINVAL;
 
-	rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones);
-
-	zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone),
-			       GFP_KERNEL | __GFP_ZERO);
-	if (!zones)
-		return -ENOMEM;
-
-	ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones);
-	if (ret)
-		goto out;
-
-	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	if (rep.nr_zones) {
-		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
-				 sizeof(struct blk_zone) * rep.nr_zones))
-			ret = -EFAULT;
-	}
-
- out:
-	kvfree(zones);
+	args.zones = argp + sizeof(struct blk_zone_report);
+	ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
+				  blkdev_copy_zone_to_user, &args);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	rep.nr_zones = ret;
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+	return 0;
 }
 
 /*
- * BLKRESETZONE ioctl processing.
+ * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long arg)
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
+	enum req_opf op;
 
 	if (!argp)
 		return -EINVAL;
@@ -397,8 +312,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	switch (cmd) {
+	case BLKRESETZONE:
+		op = REQ_OP_ZONE_RESET;
+		break;
+	case BLKOPENZONE:
+		op = REQ_OP_ZONE_OPEN;
+		break;
+	case BLKCLOSEZONE:
+		op = REQ_OP_ZONE_CLOSE;
+		break;
+	case BLKFINISHZONE:
+		op = REQ_OP_ZONE_FINISH;
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+				GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,
@@ -408,37 +340,99 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
 			    GFP_NOIO, node);
 }
 
+void blk_queue_free_zone_bitmaps(struct request_queue *q)
+{
+	kfree(q->seq_zones_bitmap);
+	q->seq_zones_bitmap = NULL;
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+}
+
+struct blk_revalidate_zone_args {
+	struct gendisk	*disk;
+	unsigned long	*seq_zones_bitmap;
+	unsigned long	*seq_zones_wlock;
+	sector_t	sector;
+};
+
 /*
- * Allocate an array of struct blk_zone to get nr_zones zone information.
- * The allocated array may be smaller than nr_zones.
+ * Helper function to check the validity of zones of a zoned block device.
  */
-static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
+static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
+				  void *data)
 {
-	struct blk_zone *zones;
-	size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
+	struct blk_revalidate_zone_args *args = data;
+	struct gendisk *disk = args->disk;
+	struct request_queue *q = disk->queue;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(disk);
 
 	/*
-	 * GFP_KERNEL here is meaningless as the caller task context has
-	 * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
-	 * with memalloc_noio_save().
+	 * All zones must have the same size, with the exception on an eventual
+	 * smaller last zone.
 	 */
-	zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!zones) {
-		*nr_zones = 0;
-		return NULL;
+	if (zone->start + zone_sectors < capacity &&
+	    zone->len != zone_sectors) {
+		pr_warn("%s: Invalid zoned device with non constant zone size\n",
+			disk->disk_name);
+		return false;
 	}
 
-	*nr_zones = nrz;
+	if (zone->start + zone->len >= capacity &&
+	    zone->len > zone_sectors) {
+		pr_warn("%s: Invalid zoned device with larger last zone size\n",
+			disk->disk_name);
+		return -ENODEV;
+	}
+
+	/* Check for holes in the zone report */
+	if (zone->start != args->sector) {
+		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
+			disk->disk_name, args->sector, zone->start);
+		return -ENODEV;
+	}
 
-	return zones;
+	/* Check zone type */
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		break;
+	default:
+		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
+			disk->disk_name, (int)zone->type, zone->start);
+		return -ENODEV;
+	}
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
+		set_bit(idx, args->seq_zones_bitmap);
+
+	args->sector += zone->len;
+	return 0;
 }
 
-void blk_queue_free_zone_bitmaps(struct request_queue *q)
+static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones,
+				struct blk_revalidate_zone_args *args)
 {
-	kfree(q->seq_zones_bitmap);
-	q->seq_zones_bitmap = NULL;
-	kfree(q->seq_zones_wlock);
-	q->seq_zones_wlock = NULL;
+	/*
+	 * Ensure that all memory allocations in this context are done as
+	 * if GFP_NOIO was specified.
+	 */
+	unsigned int noio_flag = memalloc_noio_save();
+	struct request_queue *q = disk->queue;
+	int ret;
+
+	args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_wlock)
+		return -ENOMEM;
+	args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_bitmap)
+		return -ENOMEM;
+
+	ret = disk->fops->report_zones(disk, 0, nr_zones,
+				       blk_revalidate_zone_cb, args);
+	memalloc_noio_restore(noio_flag);
+	return ret;
 }
 
 /**
@@ -454,13 +448,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk));
-	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
-	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
-	struct blk_zone *zones = NULL;
-	unsigned int noio_flag;
-	sector_t sector = 0;
+	struct blk_revalidate_zone_args args = { .disk = disk };
 	int ret = 0;
 
+	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+		return -EIO;
+
 	/*
 	 * BIO based queues do not use a scheduler so only q->nr_zones
 	 * needs to be updated so that the sysfs exposed value is correct.
@@ -470,78 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		return 0;
 	}
 
-	/*
-	 * Ensure that all memory allocations in this context are done as
-	 * if GFP_NOIO was specified.
-	 */
-	noio_flag = memalloc_noio_save();
-
-	if (!blk_queue_is_zoned(q) || !nr_zones) {
-		nr_zones = 0;
-		goto update;
-	}
-
-	/* Allocate bitmaps */
-	ret = -ENOMEM;
-	seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
-	if (!seq_zones_wlock)
-		goto out;
-	seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
-	if (!seq_zones_bitmap)
-		goto out;
-
-	/* Get zone information and initialize seq_zones_bitmap */
-	rep_nr_zones = nr_zones;
-	zones = blk_alloc_zones(&rep_nr_zones);
-	if (!zones)
-		goto out;
-
-	while (z < nr_zones) {
-		nrz = min(nr_zones - z, rep_nr_zones);
-		ret = blk_report_zones(disk, sector, zones, &nrz);
-		if (ret)
-			goto out;
-		if (!nrz)
-			break;
-		for (i = 0; i < nrz; i++) {
-			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
-				set_bit(z, seq_zones_bitmap);
-			z++;
-		}
-		sector += nrz * blk_queue_zone_sectors(q);
-	}
-
-	if (WARN_ON(z != nr_zones)) {
-		ret = -EIO;
-		goto out;
-	}
+	if (nr_zones)
+		ret = blk_update_zone_info(disk, nr_zones, &args);
 
-update:
 	/*
 	 * Install the new bitmaps, making sure the queue is stopped and
 	 * all I/Os are completed (i.e. a scheduler is not referencing the
 	 * bitmaps).
 	 */
 	blk_mq_freeze_queue(q);
-	q->nr_zones = nr_zones;
-	swap(q->seq_zones_wlock, seq_zones_wlock);
-	swap(q->seq_zones_bitmap, seq_zones_bitmap);
-	blk_mq_unfreeze_queue(q);
-
-out:
-	memalloc_noio_restore(noio_flag);
-
-	kvfree(zones);
-	kfree(seq_zones_wlock);
-	kfree(seq_zones_bitmap);
-
-	if (ret) {
+	if (ret >= 0) {
+		q->nr_zones = nr_zones;
+		swap(q->seq_zones_wlock, args.seq_zones_wlock);
+		swap(q->seq_zones_bitmap, args.seq_zones_bitmap);
+		ret = 0;
+	} else {
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-		blk_mq_freeze_queue(q);
 		blk_queue_free_zone_bitmaps(q);
-		blk_mq_unfreeze_queue(q);
 	}
+	blk_mq_unfreeze_queue(q);
 
+	kfree(args.seq_zones_wlock);
+	kfree(args.seq_zones_bitmap);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
diff --git a/block/blk.h b/block/blk.h
index 47fba9362e60..2bea40180b6f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -242,14 +242,11 @@ int blk_dev_init(void);
  * Contribute to IO statistics IFF:
  *
  *	a) it's attached to a gendisk, and
- *	b) the queue had IO stats enabled when this request was started, and
- *	c) it's a file system request
+ *	b) the queue had IO stats enabled when this request was started
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk &&
-	       (rq->rq_flags & RQF_IO_STAT) &&
-		!blk_rq_is_passthrough(rq);
+	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
 }
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
diff --git a/block/elevator.c b/block/elevator.c
index 5437059c9261..4eab3d70e880 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -616,7 +616,8 @@ out:
 
 static inline bool elv_support_iosched(struct request_queue *q)
 {
-	if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
+	if (!q->mq_ops ||
+	    (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
 		return false;
 	return true;
 }
@@ -831,3 +832,12 @@ struct request *elv_rb_latter_request(struct request_queue *q,
 	return NULL;
 }
 EXPORT_SYMBOL(elv_rb_latter_request);
+
+static int __init elevator_setup(char *str)
+{
+	pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
+		"Please use sysfs to set IO scheduler for individual devices.\n");
+	return 1;
+}
+
+__setup("elevator=", elevator_setup);
diff --git a/block/genhd.c b/block/genhd.c
index 26b31fcae217..ff6268970ddc 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
 			   "%u %u %u "
-			   "%lu %lu %lu %u\n",
+			   "%lu %lu %lu %u "
+			   "%lu %u"
+			   "\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[STAT_READ]),
@@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, ios[STAT_DISCARD]),
 			   part_stat_read(hd, merges[STAT_DISCARD]),
 			   part_stat_read(hd, sectors[STAT_DISCARD]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
+			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
+			   part_stat_read(hd, ios[STAT_FLUSH]),
+			   (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/ioctl.c b/block/ioctl.c
index 15a0eb80ada9..7ac8a66c9787 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -155,48 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-/*
- * This is an exported API for the block driver, and will not
- * acquire bd_mutex. This API should be used in case that
- * caller has held bd_mutex already.
- */
-int __blkdev_reread_part(struct block_device *bdev)
+static int blkdev_reread_part(struct block_device *bdev)
 {
-	struct gendisk *disk = bdev->bd_disk;
+	int ret;
 
-	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	lockdep_assert_held(&bdev->bd_mutex);
-
-	return rescan_partitions(disk, bdev);
-}
-EXPORT_SYMBOL(__blkdev_reread_part);
-
-/*
- * This is an exported API for the block driver, and will
- * try to acquire bd_mutex. If bd_mutex has been held already
- * in current context, please call __blkdev_reread_part().
- *
- * Make sure the held locks in current context aren't required
- * in open()/close() handler and I/O path for avoiding ABBA deadlock:
- * - bd_mutex is held before calling block driver's open/close
- *   handler
- * - reading partition table may submit I/O to the block device
- */
-int blkdev_reread_part(struct block_device *bdev)
-{
-	int res;
-
 	mutex_lock(&bdev->bd_mutex);
-	res = __blkdev_reread_part(bdev);
+	ret = bdev_disk_changed(bdev, false);
 	mutex_unlock(&bdev->bd_mutex);
 
-	return res;
+	return ret;
 }
-EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 		unsigned long arg, unsigned long flags)
@@ -532,7 +505,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKREPORTZONE:
 		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
 	case BLKRESETZONE:
-		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKOPENZONE:
+	case BLKCLOSEZONE:
+	case BLKFINISHZONE:
+		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
 		return put_uint(arg, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
diff --git a/block/opal_proto.h b/block/opal_proto.h
index 5532412d567c..325cbba2465f 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -76,7 +76,6 @@ enum opal_response_token {
  * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Section: 6.3 Assigned UIDs
  */
-#define OPAL_UID_LENGTH 8
 #define OPAL_METHOD_LENGTH 8
 #define OPAL_MSID_KEYLEN 15
 #define OPAL_UID_LENGTH_HALF 4
@@ -108,6 +107,7 @@ enum opal_uid {
 	OPAL_C_PIN_TABLE,
 	OPAL_LOCKING_INFO_TABLE,
 	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	OPAL_DATASTORE,
 	/* C_PIN_TABLE object ID's */
 	OPAL_C_PIN_MSID,
 	OPAL_C_PIN_SID,
@@ -205,6 +205,10 @@ enum opal_lockingstate {
 	OPAL_LOCKING_LOCKED = 0x03,
 };
 
+enum opal_parameter {
+	OPAL_SUM_SET_LIST = 0x060000,
+};
+
 /* Packets derived from:
  * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Secion: 3.2.3 ComPackets, Packets & Subpackets
diff --git a/block/partition-generic.c b/block/partition-generic.c
index aee643ce13d1..1d20c9cf213f 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
 		"%8u %8u %8u "
-		"%8lu %8lu %8llu %8u"
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8u"
 		"\n",
 		part_stat_read(p, ios[STAT_READ]),
 		part_stat_read(p, merges[STAT_READ]),
@@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, ios[STAT_DISCARD]),
 		part_stat_read(p, merges[STAT_DISCARD]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
-		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
+		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD),
+		part_stat_read(p, ios[STAT_FLUSH]),
+		(unsigned int)part_stat_read_msecs(p, STAT_FLUSH));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
@@ -439,12 +442,14 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
+int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev)
 {
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 	int res;
 
+	if (!disk_part_scan_enabled(disk))
+		return 0;
 	if (bdev->bd_part_count || bdev->bd_super)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
@@ -459,204 +464,124 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-static bool part_zone_aligned(struct gendisk *disk,
-			      struct block_device *bdev,
-			      sector_t from, sector_t size)
+static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
+		struct parsed_partitions *state, int p)
 {
-	unsigned int zone_sectors = bdev_zone_sectors(bdev);
+	sector_t size = state->parts[p].size;
+	sector_t from = state->parts[p].from;
+	struct hd_struct *part;
 
-	/*
-	 * If this function is called, then the disk is a zoned block device
-	 * (host-aware or host-managed). This can be detected even if the
-	 * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not
-	 * set). In this case, however, only host-aware devices will be seen
-	 * as a block device is not created for host-managed devices. Without
-	 * zoned block device support, host-aware drives can still be used as
-	 * regular block devices (no zone operation) and their zone size will
-	 * be reported as 0. Allow this case.
-	 */
-	if (!zone_sectors)
+	if (!size)
 		return true;
 
-	/*
-	 * Check partition start and size alignement. If the drive has a
-	 * smaller last runt zone, ignore it and allow the partition to
-	 * use it. Check the zone size too: it should be a power of 2 number
-	 * of sectors.
-	 */
-	if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
-		u32 rem;
-
-		div_u64_rem(from, zone_sectors, &rem);
-		if (rem)
+	if (from >= get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d start %llu is beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) from);
+		if (disk_unlock_native_capacity(disk))
 			return false;
-		if ((from + size) < get_capacity(disk)) {
-			div_u64_rem(size, zone_sectors, &rem);
-			if (rem)
-				return false;
-		}
+		return true;
+	}
 
-	} else {
+	if (from + size > get_capacity(disk)) {
+		printk(KERN_WARNING
+		       "%s: p%d size %llu extends beyond EOD, ",
+		       disk->disk_name, p, (unsigned long long) size);
 
-		if (from & (zone_sectors - 1))
-			return false;
-		if ((from + size) < get_capacity(disk) &&
-		    (size & (zone_sectors - 1)))
+		if (disk_unlock_native_capacity(disk))
 			return false;
 
+		/*
+		 * We can not ignore partitions of broken tables created by for
+		 * example camera firmware, but we limit them to the end of the
+		 * disk to avoid creating invalid block devices.
+		 */
+		size = get_capacity(disk) - from;
+	}
+
+	part = add_partition(disk, p, from, size, state->parts[p].flags,
+			     &state->parts[p].info);
+	if (IS_ERR(part)) {
+		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
+		       disk->disk_name, p, -PTR_ERR(part));
+		return true;
 	}
 
+#ifdef CONFIG_BLK_DEV_MD
+	if (state->parts[p].flags & ADDPART_FLAG_RAID)
+		md_autodetect_dev(part_to_dev(part)->devt);
+#endif
 	return true;
 }
 
-int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+int blk_add_partitions(struct gendisk *disk, struct block_device *bdev)
 {
-	struct parsed_partitions *state = NULL;
-	struct hd_struct *part;
-	int p, highest, res;
-rescan:
-	if (state && !IS_ERR(state)) {
-		free_partitions(state);
-		state = NULL;
-	}
+	struct parsed_partitions *state;
+	int ret = -EAGAIN, p, highest;
 
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
+	if (!disk_part_scan_enabled(disk))
+		return 0;
 
-	if (disk->fops->revalidate_disk)
-		disk->fops->revalidate_disk(disk);
-	check_disk_size_change(disk, bdev, true);
-	bdev->bd_invalidated = 0;
-	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
+	state = check_partition(disk, bdev);
+	if (!state)
 		return 0;
 	if (IS_ERR(state)) {
 		/*
-		 * I/O error reading the partition table.  If any
-		 * partition code tried to read beyond EOD, retry
-		 * after unlocking native capacity.
+		 * I/O error reading the partition table.  If we tried to read
+		 * beyond EOD, retry after unlocking the native capacity.
 		 */
 		if (PTR_ERR(state) == -ENOSPC) {
 			printk(KERN_WARNING "%s: partition table beyond EOD, ",
 			       disk->disk_name);
 			if (disk_unlock_native_capacity(disk))
-				goto rescan;
+				return -EAGAIN;
 		}
 		return -EIO;
 	}
+
 	/*
-	 * If any partition code tried to read beyond EOD, try
-	 * unlocking native capacity even if partition table is
-	 * successfully read as we could be missing some partitions.
+	 * Partitions are not supported on zoned block devices.
+	 */
+	if (bdev_is_zoned(bdev)) {
+		pr_warn("%s: ignoring partition table on zoned block device\n",
+			disk->disk_name);
+		ret = 0;
+		goto out_free_state;
+	}
+
+	/*
+	 * If we read beyond EOD, try unlocking native capacity even if the
+	 * partition table was successfully read as we could be missing some
+	 * partitions.
 	 */
 	if (state->access_beyond_eod) {
 		printk(KERN_WARNING
 		       "%s: partition table partially beyond EOD, ",
 		       disk->disk_name);
 		if (disk_unlock_native_capacity(disk))
-			goto rescan;
+			goto out_free_state;
 	}
 
 	/* tell userspace that the media / partition table may have changed */
 	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
 
-	/* Detect the highest partition number and preallocate
-	 * disk->part_tbl.  This is an optimization and not strictly
-	 * necessary.
+	/*
+	 * Detect the highest partition number and preallocate disk->part_tbl.
+	 * This is an optimization and not strictly necessary.
 	 */
 	for (p = 1, highest = 0; p < state->limit; p++)
 		if (state->parts[p].size)
 			highest = p;
-
 	disk_expand_part_tbl(disk, highest);
 
-	/* add partitions */
-	for (p = 1; p < state->limit; p++) {
-		sector_t size, from;
-
-		size = state->parts[p].size;
-		if (!size)
-			continue;
-
-		from = state->parts[p].from;
-		if (from >= get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu is beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) from);
-			if (disk_unlock_native_capacity(disk))
-				goto rescan;
-			continue;
-		}
-
-		if (from + size > get_capacity(disk)) {
-			printk(KERN_WARNING
-			       "%s: p%d size %llu extends beyond EOD, ",
-			       disk->disk_name, p, (unsigned long long) size);
-
-			if (disk_unlock_native_capacity(disk)) {
-				/* free state and restart */
-				goto rescan;
-			} else {
-				/*
-				 * we can not ignore partitions of broken tables
-				 * created by for example camera firmware, but
-				 * we limit them to the end of the disk to avoid
-				 * creating invalid block devices
-				 */
-				size = get_capacity(disk) - from;
-			}
-		}
-
-		/*
-		 * On a zoned block device, partitions should be aligned on the
-		 * device zone size (i.e. zone boundary crossing not allowed).
-		 * Otherwise, resetting the write pointer of the last zone of
-		 * one partition may impact the following partition.
-		 */
-		if (bdev_is_zoned(bdev) &&
-		    !part_zone_aligned(disk, bdev, from, size)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu+%llu is not zone aligned\n",
-			       disk->disk_name, p, (unsigned long long) from,
-			       (unsigned long long) size);
-			continue;
-		}
+	for (p = 1; p < state->limit; p++)
+		if (!blk_add_partition(disk, bdev, state, p))
+			goto out_free_state;
 
-		part = add_partition(disk, p, from, size,
-				     state->parts[p].flags,
-				     &state->parts[p].info);
-		if (IS_ERR(part)) {
-			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-			       disk->disk_name, p, -PTR_ERR(part));
-			continue;
-		}
-#ifdef CONFIG_BLK_DEV_MD
-		if (state->parts[p].flags & ADDPART_FLAG_RAID)
-			md_autodetect_dev(part_to_dev(part)->devt);
-#endif
-	}
+	ret = 0;
+out_free_state:
 	free_partitions(state);
-	return 0;
-}
-
-int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
-{
-	int res;
-
-	if (!bdev->bd_invalidated)
-		return 0;
-
-	res = drop_partitions(disk, bdev);
-	if (res)
-		return res;
-
-	set_capacity(disk, 0);
-	check_disk_size_change(disk, bdev, false);
-	bdev->bd_invalidated = 0;
-	/* tell userspace that the media / partition table may have changed */
-	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
-
-	return 0;
+	return ret;
 }
 
 unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
diff --git a/block/sed-opal.c b/block/sed-opal.c
index b4c761973ac1..880cc57a5f6b 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_DATASTORE] =
+		{ 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 },
 
 	/* C_PIN_TABLE object ID's */
 	[OPAL_C_PIN_MSID] =
@@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
  *
  * the result is provided in dev->resp->tok[4]
  */
-static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
+static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid,
 				  u64 column)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	const unsigned int half = OPAL_UID_LENGTH/2;
+	const unsigned int half = OPAL_UID_LENGTH_HALF;
 
 	/* sed-opal UIDs can be split in two halves:
 	 *  first:  actual table index
@@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
 	 * first part of the target table as relative index into that table
 	 */
 	memcpy(uid, opaluid[OPAL_TABLE_TABLE], half);
-	memcpy(uid+half, opaluid[table], half);
+	memcpy(uid + half, table_uid, half);
 
 	return generic_get_column(dev, uid, column);
 }
@@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	return get_active_key_cont(dev);
 }
 
+static int generic_table_write_data(struct opal_dev *dev, const u64 data,
+				    u64 offset, u64 size, const u8 *uid)
+{
+	const u8 __user *src = (u8 __user *)(uintptr_t)data;
+	u8 *dst;
+	u64 len;
+	size_t off = 0;
+	int err;
+
+	/* do we fit in the available space? */
+	err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	len = response_get_u64(&dev->parsed, 4);
+	if (size > len || offset > len - size) {
+		pr_debug("Does not fit in the table (%llu vs. %llu)\n",
+			  offset + size, len);
+		return -ENOSPC;
+	}
+
+	/* do the actual transmission(s) */
+	while (off < size) {
+		err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_WHERE);
+		add_token_u64(&err, dev, offset + off);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+
+		/*
+		 * The bytestring header is either 1 or 2 bytes, so assume 2.
+		 * There also needs to be enough space to accommodate the
+		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
+		 * cmd_finalize.
+		 */
+		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
+			  (size_t)(size - off));
+		pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size);
+
+		dst = add_bytestring_header(&err, dev, len);
+		if (!dst)
+			break;
+
+		if (copy_from_user(dst, src + off, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		dev->pos += len;
+
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		if (err)
+			break;
+
+		err = finalize_and_send(dev, parse_and_check_status);
+		if (err)
+			break;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int generic_lr_enable_disable(struct opal_dev *dev,
 				     u8 *uid, bool rle, bool wle,
 				     bool rl, bool wl)
@@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 static int write_shadow_mbr(struct opal_dev *dev, void *data)
 {
 	struct opal_shadow_mbr *shadow = data;
-	const u8 __user *src;
-	u8 *dst;
-	size_t off = 0;
-	u64 len;
-	int err = 0;
-
-	/* do we fit in the available shadow mbr space? */
-	err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS);
-	if (err) {
-		pr_debug("MBR: could not get shadow size\n");
-		return err;
-	}
-
-	len = response_get_u64(&dev->parsed, 4);
-	if (shadow->size > len || shadow->offset > len - shadow->size) {
-		pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n",
-			 shadow->offset + shadow->size, len);
-		return -ENOSPC;
-	}
-
-	/* do the actual transmission(s) */
-	src = (u8 __user *)(uintptr_t)shadow->data;
-	while (off < shadow->size) {
-		err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]);
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_WHERE);
-		add_token_u64(&err, dev, shadow->offset + off);
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_VALUES);
-
-		/*
-		 * The bytestring header is either 1 or 2 bytes, so assume 2.
-		 * There also needs to be enough space to accommodate the
-		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
-		 * cmd_finalize.
-		 */
-		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
-			  (size_t)(shadow->size - off));
-		pr_debug("MBR: write bytes %zu+%llu/%llu\n",
-			 off, len, shadow->size);
-
-		dst = add_bytestring_header(&err, dev, len);
-		if (!dst)
-			break;
-		if (copy_from_user(dst, src + off, len))
-			err = -EFAULT;
-		dev->pos += len;
-
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-		if (err)
-			break;
-
-		err = finalize_and_send(dev, parse_and_check_status);
-		if (err)
-			break;
-
-		off += len;
-	}
 
-	return err;
+	return generic_table_write_data(dev, shadow->data, shadow->offset,
+					shadow->size, opaluid[OPAL_MBR]);
 }
 
 static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
@@ -1874,7 +1886,6 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 {
 	struct opal_lr_act *opal_act = data;
 	u8 user_lr[OPAL_UID_LENGTH];
-	u8 uint_3 = 0x83;
 	int err, i;
 
 	err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID],
@@ -1887,10 +1898,7 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 			return err;
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, uint_3);
-		add_token_u8(&err, dev, 6);
-		add_token_u8(&err, dev, 0);
-		add_token_u8(&err, dev, 0);
+		add_token_u64(&err, dev, OPAL_SUM_SET_LIST);
 
 		add_token_u8(&err, dev, OPAL_STARTLIST);
 		add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
@@ -1957,6 +1965,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	return 0;
 }
 
+static int write_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *write_tbl = data;
+
+	return generic_table_write_data(dev, write_tbl->data, write_tbl->offset,
+					write_tbl->size, write_tbl->table_uid);
+}
+
+static int read_table_data_cont(struct opal_dev *dev)
+{
+	int err;
+	const char *data_read;
+
+	err = parse_and_check_status(dev);
+	if (err)
+		return err;
+
+	dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read);
+	dev->prev_data = (void *)data_read;
+	if (!dev->prev_data) {
+		pr_debug("%s: Couldn't read data from the table.\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	return 0;
+}
+
+/*
+ * IO_BUFFER_LENGTH = 2048
+ * sizeof(header) = 56
+ * No. of Token Bytes in the Response = 11
+ * MAX size of data that can be carried in response buffer
+ * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD.
+ */
+#define OPAL_MAX_READ_TABLE (0x7BD)
+
+static int read_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *read_tbl = data;
+	int err;
+	size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE;
+	u64 table_len, len;
+	u64 offset = read_tbl->offset, read_size = read_tbl->size - 1;
+	u8 __user *dst;
+
+	err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	table_len = response_get_u64(&dev->parsed, 4);
+
+	/* Check if the user is trying to read from the table limits */
+	if (read_size > table_len || offset > table_len - read_size) {
+		pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n",
+			  offset + read_size, table_len);
+		return -EINVAL;
+	}
+
+	while (off < read_size) {
+		err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_STARTROW);
+		add_token_u64(&err, dev, offset + off); /* start row value */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_ENDROW);
+
+		len = min(max_read_size, (size_t)(read_size - off));
+		add_token_u64(&err, dev, offset + off + len); /* end row value
+							       */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+		if (err) {
+			pr_debug("Error building read table data command.\n");
+			break;
+		}
+
+		err = finalize_and_send(dev, read_table_data_cont);
+		if (err)
+			break;
+
+		/* len+1: This includes the NULL terminator at the end*/
+		if (dev->prev_d_len > len + 1) {
+			err = -EOVERFLOW;
+			break;
+		}
+
+		dst = (u8 __user *)(uintptr_t)read_tbl->data;
+		if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) {
+			pr_debug("Error copying data to userspace\n");
+			err = -EFAULT;
+			break;
+		}
+		dev->prev_data = NULL;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int end_opal_session(struct opal_dev *dev, void *data)
 {
 	int err = 0;
@@ -2443,6 +2558,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 }
 EXPORT_SYMBOL(opal_unlock_from_suspend);
 
+static int opal_read_table(struct opal_dev *dev,
+			   struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step read_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ read_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, read_table_steps,
+			     ARRAY_SIZE(read_table_steps));
+}
+
+static int opal_write_table(struct opal_dev *dev,
+			    struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step write_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ write_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, write_table_steps,
+			     ARRAY_SIZE(write_table_steps));
+}
+
+static int opal_generic_read_write_table(struct opal_dev *dev,
+					 struct opal_read_write_table *rw_tbl)
+{
+	int ret, bit_set;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev);
+
+	bit_set = fls64(rw_tbl->flags) - 1;
+	switch (bit_set) {
+	case OPAL_READ_TABLE:
+		ret = opal_read_table(dev, rw_tbl);
+		break;
+	case OPAL_WRITE_TABLE:
+		ret = opal_write_table(dev, rw_tbl);
+		break;
+	default:
+		pr_debug("Invalid bit set in the flag (%016llx).\n",
+			 rw_tbl->flags);
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&dev->dev_lock);
+
+	return ret;
+}
+
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 {
 	void *p;
@@ -2505,6 +2682,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 	case IOC_OPAL_PSID_REVERT_TPR:
 		ret = opal_reverttper(dev, p, true);
 		break;
+	case IOC_OPAL_GENERIC_TABLE_RW:
+		ret = opal_generic_read_write_table(dev, p);
+		break;
 	default:
 		break;
 	}
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 9803c7e0376e..f4907d941f03 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_prepare(struct request *rq)
 {
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
 {
 }
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 76d2ce3a1b5b..d16d893bd195 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -13,7 +13,7 @@
 #include <crypto/sha.h>
 #include <asm/unaligned.h>
 #include <keys/asymmetric-subtype.h>
-#include <keys/trusted.h>
+#include <keys/trusted_tpm.h>
 #include <crypto/asym_tpm_subtype.h>
 #include <crypto/public_key.h>
 
@@ -21,10 +21,6 @@
 #define TPM_ORD_LOADKEY2	65
 #define TPM_ORD_UNBIND		30
 #define TPM_ORD_SIGN		60
-#define TPM_LOADKEY2_SIZE		59
-#define TPM_FLUSHSPECIFIC_SIZE		18
-#define TPM_UNBIND_SIZE			63
-#define TPM_SIGN_SIZE			63
 
 #define TPM_RT_KEY                      0x00000001
 
@@ -68,16 +64,13 @@ static int tpm_loadkey2(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_LOADKEY2_SIZE + keybloblen);
-	store32(tb, TPM_ORD_LOADKEY2);
-	store32(tb, keyhandle);
-	storebytes(tb, keyblob, keybloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_LOADKEY2);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, keyblob, keybloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -101,12 +94,9 @@ static int tpm_loadkey2(struct tpm_buf *tb,
  */
 static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle)
 {
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_COMMAND);
-	store32(tb, TPM_FLUSHSPECIFIC_SIZE);
-	store32(tb, TPM_ORD_FLUSHSPECIFIC);
-	store32(tb, handle);
-	store32(tb, TPM_RT_KEY);
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_FLUSHSPECIFIC);
+	tpm_buf_append_u32(tb, handle);
+	tpm_buf_append_u32(tb, TPM_RT_KEY);
 
 	return trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 }
@@ -155,17 +145,14 @@ static int tpm_unbind(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_UNBIND_SIZE + bloblen);
-	store32(tb, TPM_ORD_UNBIND);
-	store32(tb, keyhandle);
-	store32(tb, bloblen);
-	storebytes(tb, blob, bloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_UNBIND);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append_u32(tb, bloblen);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -241,17 +228,14 @@ static int tpm_sign(struct tpm_buf *tb,
 		return ret;
 
 	/* build the request buffer */
-	INIT_BUF(tb);
-	store16(tb, TPM_TAG_RQU_AUTH1_COMMAND);
-	store32(tb, TPM_SIGN_SIZE + bloblen);
-	store32(tb, TPM_ORD_SIGN);
-	store32(tb, keyhandle);
-	store32(tb, bloblen);
-	storebytes(tb, blob, bloblen);
-	store32(tb, authhandle);
-	storebytes(tb, nonceodd, TPM_NONCE_SIZE);
-	store8(tb, cont);
-	storebytes(tb, authdata, SHA1_DIGEST_SIZE);
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SIGN);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append_u32(tb, bloblen);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE);
 
 	ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
 	if (ret < 0) {
@@ -519,7 +503,7 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 			   struct kernel_pkey_params *params,
 			   const void *in, void *out)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	uint32_t keyhandle;
 	uint8_t srkauth[SHA1_DIGEST_SIZE];
 	uint8_t keyauth[SHA1_DIGEST_SIZE];
@@ -533,14 +517,14 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 	if (strcmp(params->encoding, "pkcs1"))
 		return -ENOPKG;
 
-	tb = kzalloc(sizeof(*tb), GFP_KERNEL);
-	if (!tb)
-		return -ENOMEM;
+	r = tpm_buf_init(&tb, 0, 0);
+	if (r)
+		return r;
 
 	/* TODO: Handle a non-all zero SRK authorization */
 	memset(srkauth, 0, sizeof(srkauth));
 
-	r = tpm_loadkey2(tb, SRKHANDLE, srkauth,
+	r = tpm_loadkey2(&tb, SRKHANDLE, srkauth,
 				tk->blob, tk->blob_len, &keyhandle);
 	if (r < 0) {
 		pr_devel("loadkey2 failed (%d)\n", r);
@@ -550,16 +534,16 @@ static int tpm_key_decrypt(struct tpm_key *tk,
 	/* TODO: Handle a non-all zero key authorization */
 	memset(keyauth, 0, sizeof(keyauth));
 
-	r = tpm_unbind(tb, keyhandle, keyauth,
+	r = tpm_unbind(&tb, keyhandle, keyauth,
 		       in, params->in_len, out, params->out_len);
 	if (r < 0)
 		pr_devel("tpm_unbind failed (%d)\n", r);
 
-	if (tpm_flushspecific(tb, keyhandle) < 0)
+	if (tpm_flushspecific(&tb, keyhandle) < 0)
 		pr_devel("flushspecific failed (%d)\n", r);
 
 error:
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 	pr_devel("<==%s() = %d\n", __func__, r);
 	return r;
 }
@@ -643,7 +627,7 @@ static int tpm_key_sign(struct tpm_key *tk,
 			struct kernel_pkey_params *params,
 			const void *in, void *out)
 {
-	struct tpm_buf *tb;
+	struct tpm_buf tb;
 	uint32_t keyhandle;
 	uint8_t srkauth[SHA1_DIGEST_SIZE];
 	uint8_t keyauth[SHA1_DIGEST_SIZE];
@@ -681,15 +665,14 @@ static int tpm_key_sign(struct tpm_key *tk,
 		goto error_free_asn1_wrapped;
 	}
 
-	r = -ENOMEM;
-	tb = kzalloc(sizeof(*tb), GFP_KERNEL);
-	if (!tb)
+	r = tpm_buf_init(&tb, 0, 0);
+	if (r)
 		goto error_free_asn1_wrapped;
 
 	/* TODO: Handle a non-all zero SRK authorization */
 	memset(srkauth, 0, sizeof(srkauth));
 
-	r = tpm_loadkey2(tb, SRKHANDLE, srkauth,
+	r = tpm_loadkey2(&tb, SRKHANDLE, srkauth,
 			 tk->blob, tk->blob_len, &keyhandle);
 	if (r < 0) {
 		pr_devel("loadkey2 failed (%d)\n", r);
@@ -699,15 +682,15 @@ static int tpm_key_sign(struct tpm_key *tk,
 	/* TODO: Handle a non-all zero key authorization */
 	memset(keyauth, 0, sizeof(keyauth));
 
-	r = tpm_sign(tb, keyhandle, keyauth, in, in_len, out, params->out_len);
+	r = tpm_sign(&tb, keyhandle, keyauth, in, in_len, out, params->out_len);
 	if (r < 0)
 		pr_devel("tpm_sign failed (%d)\n", r);
 
-	if (tpm_flushspecific(tb, keyhandle) < 0)
+	if (tpm_flushspecific(&tb, keyhandle) < 0)
 		pr_devel("flushspecific failed (%d)\n", r);
 
 error_free_tb:
-	kzfree(tb);
+	tpm_buf_destroy(&tb);
 error_free_asn1_wrapped:
 	kfree(asn1_wrapped);
 	pr_devel("<==%s() = %d\n", __func__, r);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3b2525908dd8..a1a858ad4d18 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -905,8 +905,8 @@ void acpi_cppc_processor_exit(struct acpi_processor *pr)
 			pcc_data[pcc_ss_id]->refcount--;
 			if (!pcc_data[pcc_ss_id]->refcount) {
 				pcc_mbox_free_channel(pcc_data[pcc_ss_id]->pcc_channel);
-				pcc_data[pcc_ss_id]->pcc_channel_acquired = 0;
 				kfree(pcc_data[pcc_ss_id]);
+				pcc_data[pcc_ss_id] = NULL;
 			}
 		}
 	}
diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/hmat/hmat.c
index 8f9a28a870b0..8b0de8a3c647 100644
--- a/drivers/acpi/hmat/hmat.c
+++ b/drivers/acpi/hmat/hmat.c
@@ -403,7 +403,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 		pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
-	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID) {
+	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
 		target = find_mem_target(p->memory_PD);
 		if (!target) {
 			pr_debug("HMAT: Memory Domain missing from SRAT\n");
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 1413324982f0..14e68f202f81 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1322,7 +1322,7 @@ static ssize_t scrub_show(struct device *dev,
 	nfit_device_lock(dev);
 	nd_desc = dev_get_drvdata(dev);
 	if (!nd_desc) {
-		device_unlock(dev);
+		nfit_device_unlock(dev);
 		return rc;
 	}
 	acpi_desc = to_acpi_desc(nd_desc);
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 08da9c29f1e9..62114a03a51a 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -290,14 +290,13 @@ static int acpi_processor_notifier(struct notifier_block *nb,
 				   unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
-	int cpu = policy->cpu;
 
 	if (event == CPUFREQ_CREATE_POLICY) {
-		acpi_thermal_cpufreq_init(cpu);
-		acpi_processor_ppc_init(cpu);
+		acpi_thermal_cpufreq_init(policy);
+		acpi_processor_ppc_init(policy);
 	} else if (event == CPUFREQ_REMOVE_POLICY) {
-		acpi_processor_ppc_exit(cpu);
-		acpi_thermal_cpufreq_exit(cpu);
+		acpi_processor_ppc_exit(policy);
+		acpi_thermal_cpufreq_exit(policy);
 	}
 
 	return 0;
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 2261713d1aec..5909e8fa4013 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -81,10 +81,10 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 	pr->performance_platform_limit = (int)ppc;
 
 	if (ppc >= pr->performance->state_count ||
-	    unlikely(!dev_pm_qos_request_active(&pr->perflib_req)))
+	    unlikely(!freq_qos_request_active(&pr->perflib_req)))
 		return 0;
 
-	ret = dev_pm_qos_update_request(&pr->perflib_req,
+	ret = freq_qos_update_request(&pr->perflib_req,
 			pr->performance->states[ppc].core_frequency * 1000);
 	if (ret < 0) {
 		pr_warn("Failed to update perflib freq constraint: CPU%d (%d)\n",
@@ -157,26 +157,36 @@ void acpi_processor_ignore_ppc_init(void)
 		ignore_ppc = 0;
 }
 
-void acpi_processor_ppc_init(int cpu)
+void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
-	int ret;
+	unsigned int cpu;
 
-	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-				     &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     INT_MAX);
-	if (ret < 0) {
-		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
-		       ret);
-		return;
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+		int ret;
+
+		if (!pr)
+			continue;
+
+		ret = freq_qos_add_request(&policy->constraints,
+					   &pr->perflib_req,
+					   FREQ_QOS_MAX, INT_MAX);
+		if (ret < 0)
+			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
 	}
 }
 
-void acpi_processor_ppc_exit(int cpu)
+void acpi_processor_ppc_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
+	unsigned int cpu;
 
-	dev_pm_qos_remove_request(&pr->perflib_req);
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+
+		if (pr)
+			freq_qos_remove_request(&pr->perflib_req);
+	}
 }
 
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index ec2638f1df4f..41feb88ee92d 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -105,7 +105,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 
 		pr = per_cpu(processors, i);
 
-		if (unlikely(!dev_pm_qos_request_active(&pr->thermal_req)))
+		if (unlikely(!freq_qos_request_active(&pr->thermal_req)))
 			continue;
 
 		policy = cpufreq_cpu_get(i);
@@ -116,7 +116,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 
 		cpufreq_cpu_put(policy);
 
-		ret = dev_pm_qos_update_request(&pr->thermal_req, max_freq);
+		ret = freq_qos_update_request(&pr->thermal_req, max_freq);
 		if (ret < 0) {
 			pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
 				pr->id, ret);
@@ -125,26 +125,36 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	return 0;
 }
 
-void acpi_thermal_cpufreq_init(int cpu)
+void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
-	int ret;
-
-	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-				     &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     INT_MAX);
-	if (ret < 0) {
-		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
-		       ret);
-		return;
+	unsigned int cpu;
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+		int ret;
+
+		if (!pr)
+			continue;
+
+		ret = freq_qos_add_request(&policy->constraints,
+					   &pr->thermal_req,
+					   FREQ_QOS_MAX, INT_MAX);
+		if (ret < 0)
+			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
 	}
 }
 
-void acpi_thermal_cpufreq_exit(int cpu)
+void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
+	unsigned int cpu;
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, policy->cpu);
 
-	dev_pm_qos_remove_request(&pr->thermal_req);
+		if (pr)
+			freq_qos_remove_request(&pr->thermal_req);
+	}
 }
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9fa77d72ef27..2af937a8b1c5 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -362,19 +362,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		},
 	},
 	/*
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=196907
-	 * Some Dell XPS13 9360 cannot do suspend-to-idle using the Low Power
-	 * S0 Idle firmware interface.
-	 */
-	{
-	.callback = init_default_s3,
-	.ident = "Dell XPS13 9360",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
-		},
-	},
-	/*
 	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
 	 * the Low Power S0 Idle firmware interface (see
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index f39f075abff9..fe1523664816 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -409,9 +409,11 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 		 */
 		rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node);
 		if (IS_ERR(rstc)) {
-			if (PTR_ERR(rstc) != -EPROBE_DEFER)
-				dev_err(&dev->dev, "Can't get amba reset!\n");
-			return PTR_ERR(rstc);
+			ret = PTR_ERR(rstc);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&dev->dev, "can't get reset: %d\n",
+					ret);
+			goto err_reset;
 		}
 		reset_control_deassert(rstc);
 		reset_control_put(rstc);
@@ -472,6 +474,12 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	release_resource(&dev->res);
  err_out:
 	return ret;
+
+ err_reset:
+	amba_put_disable_pclk(dev);
+	iounmap(tmp);
+	dev_pm_domain_detach(&dev->dev, true);
+	goto err_release;
 }
 
 /*
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 5b9ac2122e89..265d9dd46a5e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -97,10 +97,6 @@ DEFINE_SHOW_ATTRIBUTE(proc);
 #define SZ_1K                               0x400
 #endif
 
-#ifndef SZ_4M
-#define SZ_4M                               0x400000
-#endif
-
 #define FORBIDDEN_MMAP_FLAGS                (VM_WRITE)
 
 enum {
@@ -5177,9 +5173,6 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (proc->tsk != current->group_leader)
 		return -EINVAL;
 
-	if ((vma->vm_end - vma->vm_start) > SZ_4M)
-		vma->vm_end = vma->vm_start + SZ_4M;
-
 	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
 		     "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
 		     __func__, proc->pid, vma->vm_start, vma->vm_end,
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index d42a8b2f636a..eb76a823fbb2 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
+#include <linux/sizes.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
@@ -689,7 +690,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	alloc->buffer = (void __user *)vma->vm_start;
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->pages = kcalloc((vma->vm_end - vma->vm_start) / PAGE_SIZE,
+	alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start,
+				   SZ_4M);
+	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
 			       sizeof(alloc->pages[0]),
 			       GFP_KERNEL);
 	if (alloc->pages == NULL) {
@@ -697,7 +700,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		failure_string = "alloc page array";
 		goto err_alloc_pages_failed;
 	}
-	alloc->buffer_size = vma->vm_end - vma->vm_start;
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 753985c01517..46dc54d18f0b 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -56,7 +56,7 @@ struct acard_sg {
 	__le32			size;	 /* bit 31 (EOT) max==0x10000 (64k) */
 };
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc);
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int acard_ahci_port_start(struct ata_port *ap);
 static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
 	return si;
 }
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index dd92faf197d5..ec6c64fce74a 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -56,6 +56,7 @@ enum board_ids {
 	board_ahci_yes_fbs,
 
 	/* board IDs for specific chipsets in alphabetical order */
+	board_ahci_al,
 	board_ahci_avn,
 	board_ahci_mcp65,
 	board_ahci_mcp77,
@@ -167,6 +168,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.port_ops	= &ahci_ops,
 	},
 	/* by chipsets */
+	[board_ahci_al] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_MSI),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_avn] = {
 		.flags		= AHCI_FLAG_COMMON,
 		.pio_mask	= ATA_PIO4,
@@ -415,6 +423,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(ATI, 0x4394), board_ahci_sb700 }, /* ATI SB700/800 */
 	{ PCI_VDEVICE(ATI, 0x4395), board_ahci_sb700 }, /* ATI SB700/800 */
 
+	/* Amazon's Annapurna Labs support */
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031),
+		.class = PCI_CLASS_STORAGE_SATA_AHCI,
+		.class_mask = 0xffffff,
+		board_ahci_al },
 	/* AMD */
 	{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
 	{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
@@ -1600,7 +1613,9 @@ static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hp
 	 */
 	if (!id || id->vendor != PCI_VENDOR_ID_INTEL)
 		return;
-	if (((enum board_ids) id->driver_data) < board_ahci_pcs7)
+
+	/* Skip applying the quirk on Denverton and beyond */
+	if (((enum board_ids) id->driver_data) >= board_ahci_pcs7)
 		return;
 
 	/*
diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c
index e3163dae5e85..cb55ebc1725b 100644
--- a/drivers/ata/ahci_tegra.c
+++ b/drivers/ata/ahci_tegra.c
@@ -483,7 +483,6 @@ static int tegra_ahci_probe(struct platform_device *pdev)
 	struct tegra_ahci_priv *tegra;
 	struct resource *res;
 	int ret;
-	unsigned int i;
 
 	hpriv = ahci_platform_get_resources(pdev, 0);
 	if (IS_ERR(hpriv))
@@ -543,8 +542,9 @@ static int tegra_ahci_probe(struct platform_device *pdev)
 	if (!tegra->supplies)
 		return -ENOMEM;
 
-	for (i = 0; i < tegra->soc->num_supplies; i++)
-		tegra->supplies[i].supply = tegra->soc->supply_names[i];
+	regulator_bulk_set_supply_names(tegra->supplies,
+					tegra->soc->supply_names,
+					tegra->soc->num_supplies);
 
 	ret = devm_regulator_bulk_get(&pdev->dev,
 				      tegra->soc->num_supplies,
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index e4da725381d3..3ca7720e7d8f 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -841,6 +841,12 @@ static int piix_broken_suspend(void)
 			},
 		},
 		{
+			.ident = "TECRA M3",
+			.matches = {
+				DMI_MATCH(DMI_OEM_STRING, "Tecra M3,"),
+			},
+		},
+		{
 			.ident = "TECRA M4",
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
@@ -955,18 +961,10 @@ static int piix_broken_suspend(void)
 
 		{ }	/* terminate list */
 	};
-	static const char *oemstrs[] = {
-		"Tecra M3,",
-	};
-	int i;
 
 	if (dmi_check_system(sysids))
 		return 1;
 
-	for (i = 0; i < ARRAY_SIZE(oemstrs); i++)
-		if (dmi_find_device(DMI_DEV_TYPE_OEM_STRING, oemstrs[i], NULL))
-			return 1;
-
 	/* TECRA M4 sometimes forgets its identify and reports bogus
 	 * DMI information.  As the bogus information is a bit
 	 * generic, match as many entries as possible.  This manual
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index bff369d9a1a7..ea5bf5f4cbed 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int ahci_port_start(struct ata_port *ap);
 static void ahci_port_stop(struct ata_port *ap);
-static void ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc);
 static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc);
 static void ahci_freeze(struct ata_port *ap);
 static void ahci_thaw(struct ata_port *ap);
@@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc)
 		return sata_pmp_qc_defer_cmd_switch(qc);
 }
 
-static void ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static void ahci_fbs_dec_intr(struct ata_port *ap)
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index e742780950de..8befce036af8 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -153,17 +153,13 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
 {
 	int rc, i;
 
-	if (hpriv->ahci_regulator) {
-		rc = regulator_enable(hpriv->ahci_regulator);
-		if (rc)
-			return rc;
-	}
+	rc = regulator_enable(hpriv->ahci_regulator);
+	if (rc)
+		return rc;
 
-	if (hpriv->phy_regulator) {
-		rc = regulator_enable(hpriv->phy_regulator);
-		if (rc)
-			goto disable_ahci_pwrs;
-	}
+	rc = regulator_enable(hpriv->phy_regulator);
+	if (rc)
+		goto disable_ahci_pwrs;
 
 	for (i = 0; i < hpriv->nports; i++) {
 		if (!hpriv->target_pwrs[i])
@@ -181,11 +177,9 @@ disable_target_pwrs:
 		if (hpriv->target_pwrs[i])
 			regulator_disable(hpriv->target_pwrs[i]);
 
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->phy_regulator);
 disable_ahci_pwrs:
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->ahci_regulator);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators);
@@ -207,10 +201,8 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv)
 		regulator_disable(hpriv->target_pwrs[i]);
 	}
 
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->phy_regulator);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
 /**
@@ -359,7 +351,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port,
 	struct regulator *target_pwr;
 	int rc = 0;
 
-	target_pwr = regulator_get_optional(dev, "target");
+	target_pwr = regulator_get(dev, "target");
 
 	if (!IS_ERR(target_pwr))
 		hpriv->target_pwrs[port] = target_pwr;
@@ -436,16 +428,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->ahci_regulator = devm_regulator_get_optional(dev, "ahci");
+	hpriv->ahci_regulator = devm_regulator_get(dev, "ahci");
 	if (IS_ERR(hpriv->ahci_regulator)) {
 		rc = PTR_ERR(hpriv->ahci_regulator);
-		if (rc == -EPROBE_DEFER)
+		if (rc != 0)
 			goto err_out;
-		rc = 0;
-		hpriv->ahci_regulator = NULL;
 	}
 
-	hpriv->phy_regulator = devm_regulator_get_optional(dev, "phy");
+	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
 	if (IS_ERR(hpriv->phy_regulator)) {
 		rc = PTR_ERR(hpriv->phy_regulator);
 		if (rc == -EPROBE_DEFER)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 28c492be0a57..e9017c570bc5 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4980,7 +4980,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc)
 	return ATA_DEFER_LINK;
 }
 
-void ata_noop_qc_prep(struct ata_queued_cmd *qc) { }
+enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc)
+{
+	return AC_ERR_OK;
+}
 
 /**
  *	ata_sg_init - Associate command with scatter-gather table.
@@ -5443,7 +5446,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 		return;
 	}
 
-	ap->ops->qc_prep(qc);
+	qc->err_mask |= ap->ops->qc_prep(qc);
+	if (unlikely(qc->err_mask))
+		goto err;
 	trace_ata_qc_issue(qc);
 	qc->err_mask |= ap->ops->qc_issue(qc);
 	if (unlikely(qc->err_mask))
@@ -6708,6 +6713,9 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
+	/* Ensure ata_port probe has completed */
+	async_synchronize_full();
+
 	for (i = 0; i < host->n_ports; i++)
 		ata_port_detach(host->ports[i]);
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 4ed682da52ae..038db94216a9 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc)
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
 
@@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg_dumb(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep);
 
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 3aa006c5ed0c..6bd2228bb6ff 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -100,7 +100,7 @@ static void artop6210_load_piomode(struct ata_port *ap, struct ata_device *adev,
 {
 	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
 	int dn = adev->devno + 2 * ap->port_no;
-	const u16 timing[2][5] = {
+	static const u16 timing[2][5] = {
 		{ 0x0000, 0x000A, 0x0008, 0x0303, 0x0301 },
 		{ 0x0700, 0x070A, 0x0708, 0x0403, 0x0401 }
 
@@ -154,7 +154,7 @@ static void artop6260_load_piomode (struct ata_port *ap, struct ata_device *adev
 {
 	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
 	int dn = adev->devno + 2 * ap->port_no;
-	const u8 timing[2][5] = {
+	static const u8 timing[2][5] = {
 		{ 0x00, 0x0A, 0x08, 0x33, 0x31 },
 		{ 0x70, 0x7A, 0x78, 0x43, 0x41 }
 
diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c
index 41e0d6a6cd05..27b0952fde6b 100644
--- a/drivers/ata/pata_falcon.c
+++ b/drivers/ata/pata_falcon.c
@@ -33,7 +33,6 @@
 #define DRV_NAME "pata_falcon"
 #define DRV_VERSION "0.1.0"
 
-#define ATA_HD_BASE	0xfff00000
 #define ATA_HD_CONTROL	0x39
 
 static struct scsi_host_template pata_falcon_sht = {
@@ -120,24 +119,22 @@ static struct ata_port_operations pata_falcon_ops = {
 	.set_mode	= pata_falcon_set_mode,
 };
 
-static int pata_falcon_init_one(void)
+static int __init pata_falcon_init_one(struct platform_device *pdev)
 {
+	struct resource *res;
 	struct ata_host *host;
 	struct ata_port *ap;
-	struct platform_device *pdev;
 	void __iomem *base;
 
-	if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE))
-		return -ENODEV;
-
-	pr_info(DRV_NAME ": Atari Falcon PATA controller\n");
+	dev_info(&pdev->dev, "Atari Falcon PATA controller\n");
 
-	pdev = platform_device_register_simple(DRV_NAME, 0, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
 
-	if (!devm_request_mem_region(&pdev->dev, ATA_HD_BASE, 0x40, DRV_NAME)) {
-		pr_err(DRV_NAME ": resources busy\n");
+	if (!devm_request_mem_region(&pdev->dev, res->start,
+				     resource_size(res), DRV_NAME)) {
+		dev_err(&pdev->dev, "resources busy\n");
 		return -EBUSY;
 	}
 
@@ -152,7 +149,7 @@ static int pata_falcon_init_one(void)
 	ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY;
 	ap->flags |= ATA_FLAG_PIO_POLLING;
 
-	base = (void __iomem *)ATA_HD_BASE;
+	base = (void __iomem *)res->start;
 	ap->ioaddr.data_addr		= base;
 	ap->ioaddr.error_addr		= base + 1 + 1 * 4;
 	ap->ioaddr.feature_addr		= base + 1 + 1 * 4;
@@ -174,9 +171,26 @@ static int pata_falcon_init_one(void)
 	return ata_host_activate(host, 0, NULL, 0, &pata_falcon_sht);
 }
 
-module_init(pata_falcon_init_one);
+static int __exit pata_falcon_remove_one(struct platform_device *pdev)
+{
+	struct ata_host *host = platform_get_drvdata(pdev);
+
+	ata_host_detach(host);
+
+	return 0;
+}
+
+static struct platform_driver pata_falcon_driver = {
+	.remove = __exit_p(pata_falcon_remove_one),
+	.driver   = {
+		.name	= "atari-falcon-ide",
+	},
+};
+
+module_platform_driver_probe(pata_falcon_driver, pata_falcon_init_one);
 
 MODULE_AUTHOR("Bartlomiej Zolnierkiewicz");
 MODULE_DESCRIPTION("low-level driver for Atari Falcon PATA");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:atari-falcon-ide");
 MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 57f2ec71cfc3..1bfd0154dad5 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap)
 	return ATA_CBL_PATA40;
 }
 
-static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 {
 	unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE);
 	struct ata_port *ap = qc->ap;
@@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 		   __func__, qc, qc->flags, write, qc->dev->devno);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	table = (struct dbdma_cmd *) priv->dma_table_cpu;
 
@@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 	table->command = cpu_to_le16(DBDMA_STOP);
 
 	dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi);
+
+	return AC_ERR_OK;
 }
 
 
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 4afcb8e63e21..41430f79663c 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d)
 /*
  * Prepare taskfile for submission.
  */
-static void pxa_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pata_pxa_data *pd = qc->ap->private_data;
 	struct dma_async_tx_descriptor *tx;
 	enum dma_transfer_direction dir;
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM);
 	tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir,
 				     DMA_PREP_INTERRUPT);
 	if (!tx) {
 		ata_dev_err(qc->dev, "prep_slave_sg() failed\n");
-		return;
+		return AC_ERR_OK;
 	}
 	tx->callback = pxa_ata_dma_irq;
 	tx->callback_param = pd;
 	pd->dma_cookie = dmaengine_submit(tx);
+
+	return AC_ERR_OK;
 }
 
 /*
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index cb490531b62e..5db55e1e2a61 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev,
 				const struct pci_device_id *ent);
 static int adma_port_start(struct ata_port *ap);
 static void adma_port_stop(struct ata_port *ap);
-static void adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int adma_qc_issue(struct ata_queued_cmd *qc);
 static int adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static void adma_freeze(struct ata_port *ap);
@@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
 	return i;
 }
 
-static void adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct adma_port_priv *pp = qc->ap->private_data;
 	u8  *buf = pp->pkt;
@@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 
 	adma_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	buf[i++] = 0;	/* Response flags */
 	buf[i++] = 0;	/* reserved */
@@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 			printk("%s\n", obuf);
 	}
 #endif
+	return AC_ERR_OK;
 }
 
 static inline void adma_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 8e9cb198fcd1..9239615d8a04 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
 	return num_prde;
 }
 
-static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sata_fsl_port_priv *pp = ap->private_data;
@@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 
 	VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n",
 		desc_info, ttl_dwords, num_prde);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index 7f99e23bff88..a6b76cc12a66 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc)
 	prd[-1].flags |= PRD_END;
 }
 
-static void inic_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct inic_port_priv *pp = qc->ap->private_data;
 	struct inic_pkt *pkt = pp->pkt;
@@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc)
 		inic_fill_sg(prd, qc);
 
 	pp->cpb_tbl[0] = pp->pkt_dma;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int inic_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index ad385a113391..277f11909fc1 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val)
 static int mv_port_start(struct ata_port *ap);
 static void mv_port_stop(struct ata_port *ap);
 static int mv_qc_defer(struct ata_queued_cmd *qc);
-static void mv_qc_prep(struct ata_queued_cmd *qc);
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc);
 static unsigned int mv_qc_issue(struct ata_queued_cmd *qc);
 static int mv_hardreset(struct ata_link *link, unsigned int *class,
 			unsigned long deadline);
@@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	switch (tf->protocol) {
 	case ATA_PROT_DMA:
 		if (tf->command == ATA_CMD_DSM)
-			return;
+			return AC_ERR_OK;
 		/* fall-thru */
 	case ATA_PROT_NCQ:
 		break;	/* continue below */
 	case ATA_PROT_PIO:
 		mv_rw_multi_errata_sata24(qc);
-		return;
+		return AC_ERR_OK;
 	default:
-		return;
+		return AC_ERR_OK;
 	}
 
 	/* Fill in command request block
@@ -2098,12 +2098,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 		 * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none
 		 * of which are defined/used by Linux.  If we get here, this
 		 * driver needs work.
-		 *
-		 * FIXME: modify libata to give qc_prep a return value and
-		 * return error here.
 		 */
-		BUG_ON(tf->command);
-		break;
+		ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__,
+				tf->command);
+		return AC_ERR_INVALID;
 	}
 	mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0);
 	mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0);
@@ -2116,8 +2114,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1);	/* last */
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
@@ -2132,7 +2132,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2143,9 +2143,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 
 	if ((tf->protocol != ATA_PROT_DMA) &&
 	    (tf->protocol != ATA_PROT_NCQ))
-		return;
+		return AC_ERR_OK;
 	if (tf->command == ATA_CMD_DSM)
-		return;  /* use bmdma for this */
+		return AC_ERR_OK;  /* use bmdma for this */
 
 	/* Fill in Gen IIE command request block */
 	if (!(tf->flags & ATA_TFLAG_WRITE))
@@ -2186,8 +2186,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 		);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 56946012d113..65ec8dff1c51 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
 static int nv_adma_slave_config(struct scsi_device *sdev);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
 static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
 static void nv_adma_irq_clear(struct ata_port *ap);
@@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap);
 static void nv_swncq_error_handler(struct ata_port *ap);
 static int nv_swncq_slave_config(struct scsi_device *sdev);
 static int nv_swncq_port_start(struct ata_port *ap);
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc);
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
 static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc);
 static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis);
@@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc)
 	return 1;
 }
 
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct nv_adma_port_priv *pp = qc->ap->private_data;
 	struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag];
@@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 			(qc->flags & ATA_QCFLAG_DMAMAP));
 		nv_adma_register_mode(qc->ap);
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	cpb->resp_flags = NV_CPB_RESP_DONE;
@@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 	cpb->ctl_flags = ctl_flags;
 	wmb();
 	cpb->resp_flags = 0;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
@@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap)
 	return 0;
 }
 
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (qc->tf.protocol != ATA_PROT_NCQ) {
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	nv_swncq_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 5fd464765ddc..c451d7d1c817 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va
 static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int pdc_common_port_start(struct ata_port *ap);
 static int pdc_sata_port_start(struct ata_port *ap);
-static void pdc_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static int pdc_check_atapi_dma(struct ata_queued_cmd *qc);
@@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc)
 	prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void pdc_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pdc_port_priv *pp = qc->ap->private_data;
 	unsigned int i;
@@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static int pdc_is_sataii_tx4(unsigned long flags)
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index c53c5a47204d..ef00ab644afb 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int qs_port_start(struct ata_port *ap);
 static void qs_host_stop(struct ata_host *host);
-static void qs_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int qs_qc_issue(struct ata_queued_cmd *qc);
 static int qs_check_atapi_dma(struct ata_queued_cmd *qc);
 static void qs_freeze(struct ata_port *ap);
@@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc)
 	return si;
 }
 
-static void qs_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct qs_port_priv *pp = qc->ap->private_data;
 	u8 dflags = QS_DF_PORD, *buf = pp->pkt;
@@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	qs_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	nelem = qs_fill_sg(qc);
 
@@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	/* frame information structure (FIS) */
 	ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]);
+
+	return AC_ERR_OK;
 }
 
 static inline void qs_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 3495e1733a8e..980aacdbcf3b 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc)
 	prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND);
 }
 
-static void sata_rcar_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sata_rcar_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index e6fbae2f645a..75321f1ceba5 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev);
 static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed);
-static void sil_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc);
 static void sil_bmdma_setup(struct ata_queued_cmd *qc);
 static void sil_bmdma_start(struct ata_queued_cmd *qc);
 static void sil_bmdma_stop(struct ata_queued_cmd *qc);
@@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc)
 		last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void sil_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sil_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static unsigned char sil_get_device_cache_line(struct pci_dev *pdev)
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 7bef82de53ca..560070d4f1d0 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev);
 static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val);
 static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val);
 static int sil24_qc_defer(struct ata_queued_cmd *qc);
-static void sil24_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc);
 static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc);
 static void sil24_pmp_attach(struct ata_port *ap);
@@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc)
 	return ata_std_qc_defer(qc);
 }
 
-static void sil24_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sil24_port_priv *pp = ap->private_data;
@@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc)
 
 	if (qc->flags & ATA_QCFLAG_DMAMAP)
 		sil24_fill_sg(qc, sge);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 2277ba0c9c7f..2c7b30c5ea3d 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap);
 static void pdc_freeze(struct ata_port *ap);
 static void pdc_thaw(struct ata_port *ap);
 static int pdc_port_start(struct ata_port *ap);
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static unsigned int pdc20621_dimm_init(struct ata_host *host);
@@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
 	VPRINTK("ata pkt buf ofs %u, mmio copied\n", i);
 }
 
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc)
 {
 	switch (qc->tf.protocol) {
 	case ATA_PROT_DMA:
@@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static void __pdc20621_push_hdma(struct ata_queued_cmd *qc,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2db62d98e395..7bd9cd366d41 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/fwnode.h>
@@ -3179,6 +3180,8 @@ void device_shutdown(void)
 	wait_for_device_probe();
 	device_block_probing();
 
+	cpufreq_suspend();
+
 	spin_lock(&devices_kset->list_lock);
 	/*
 	 * Walk the devices list backward, shutting down each in turn.
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index cc37511de866..6265871a4af2 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -554,12 +554,27 @@ ssize_t __weak cpu_show_mds(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_tsx_async_abort(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
+ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
 static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
+static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
+static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -568,6 +583,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_spec_store_bypass.attr,
 	&dev_attr_l1tf.attr,
 	&dev_attr_mds.attr,
+	&dev_attr_tsx_async_abort.attr,
+	&dev_attr_itlb_multihit.attr,
 	NULL
 };
 
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 6bea4f3f8040..84c4e1f72cbd 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -540,6 +540,9 @@ static ssize_t soft_offline_page_store(struct device *dev,
 	pfn >>= PAGE_SHIFT;
 	if (!pfn_valid(pfn))
 		return -ENXIO;
+	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
+	if (!pfn_to_online_page(pfn))
+		return -EIO;
 	ret = soft_offline_page(pfn_to_page(pfn), 0);
 	return ret == 0 ? count : ret;
 }
@@ -869,3 +872,39 @@ int walk_memory_blocks(unsigned long start, unsigned long size,
 	}
 	return ret;
 }
+
+struct for_each_memory_block_cb_data {
+	walk_memory_blocks_func_t func;
+	void *arg;
+};
+
+static int for_each_memory_block_cb(struct device *dev, void *data)
+{
+	struct memory_block *mem = to_memory_block(dev);
+	struct for_each_memory_block_cb_data *cb_data = data;
+
+	return cb_data->func(mem, cb_data->arg);
+}
+
+/**
+ * for_each_memory_block - walk through all present memory blocks
+ *
+ * @arg: argument passed to func
+ * @func: callback for each memory block walked
+ *
+ * This function walks through all present memory blocks, calling func on
+ * each memory block.
+ *
+ * In case func() returns an error, walking is aborted and the error is
+ * returned.
+ */
+int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
+{
+	struct for_each_memory_block_cb_data cb_data = {
+		.func = func,
+		.arg = arg,
+	};
+
+	return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
+				for_each_memory_block_cb);
+}
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 6c90fd7e2ff8..350dcafd751f 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -115,20 +115,10 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	switch (type) {
-	case DEV_PM_QOS_RESUME_LATENCY:
+	if (type == DEV_PM_QOS_RESUME_LATENCY) {
 		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
 			: pm_qos_read_value(&qos->resume_latency);
-		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->min_frequency);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->max_frequency);
-		break;
-	default:
+	} else {
 		WARN_ON(1);
 		ret = 0;
 	}
@@ -169,14 +159,6 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 			req->dev->power.set_latency_tolerance(req->dev, value);
 		}
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = pm_qos_update_target(&qos->min_frequency,
-					   &req->data.pnode, action, value);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = pm_qos_update_target(&qos->max_frequency,
-					   &req->data.pnode, action, value);
-		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -227,24 +209,6 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 
-	c = &qos->min_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MAX;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
-	c = &qos->max_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MIN;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -305,18 +269,6 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		memset(req, 0, sizeof(*req));
 	}
 
-	c = &qos->min_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
-	c = &qos->max_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -428,8 +380,6 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
-	case DEV_PM_QOS_MIN_FREQUENCY:
-	case DEV_PM_QOS_MAX_FREQUENCY:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -557,14 +507,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier,
 		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
 						       notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->min_frequency.notifiers,
-						       notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->max_frequency.notifiers,
-						       notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
@@ -604,14 +546,6 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
 							 notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->min_frequency.notifiers,
-							 notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->max_frequency.notifiers,
-							 notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 5b248763a672..a18155cdce41 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -786,7 +786,6 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 
 	if (nc->tentative && connection->agreed_pro_version < 92) {
 		rcu_read_unlock();
-		mutex_unlock(&sock->mutex);
 		drbd_err(connection, "--dry-run is not supported by peer");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f6f77eaa7217..739b372a5112 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -417,18 +417,20 @@ out_free_page:
 	return ret;
 }
 
-static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
+static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
+			int mode)
 {
 	/*
-	 * We use punch hole to reclaim the free space used by the
-	 * image a.k.a. discard. However we do not support discard if
-	 * encryption is enabled, because it may give an attacker
-	 * useful information.
+	 * We use fallocate to manipulate the space mappings used by the image
+	 * a.k.a. discard/zerorange. However we do not support this if
+	 * encryption is enabled, because it may give an attacker useful
+	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
-	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	int ret;
 
+	mode |= FALLOC_FL_KEEP_SIZE;
+
 	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
 		ret = -EOPNOTSUPP;
 		goto out;
@@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
-	case REQ_OP_DISCARD:
 	case REQ_OP_WRITE_ZEROES:
-		return lo_discard(lo, rq, pos);
+		/*
+		 * If the caller doesn't want deallocation, call zeroout to
+		 * write zeroes the range.  Otherwise, punch them out.
+		 */
+		return lo_fallocate(lo, rq, pos,
+			(rq->cmd_flags & REQ_NOUNMAP) ?
+				FALLOC_FL_ZERO_RANGE :
+				FALLOC_FL_PUNCH_HOLE);
+	case REQ_OP_DISCARD:
+		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
 			return lo_write_transfer(lo, rq, pos);
@@ -630,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo,
 {
 	int rc;
 
-	rc = blkdev_reread_part(bdev);
+	mutex_lock(&bdev->bd_mutex);
+	rc = bdev_disk_changed(bdev, false);
+	mutex_unlock(&bdev->bd_mutex);
 	if (rc)
 		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
 			__func__, lo->lo_number, lo->lo_file_name, rc);
@@ -1154,10 +1166,11 @@ out_unlock:
 		 * must be at least one and it can only become zero when the
 		 * current holder is released.
 		 */
-		if (release)
-			err = __blkdev_reread_part(bdev);
-		else
-			err = blkdev_reread_part(bdev);
+		if (!release)
+			mutex_lock(&bdev->bd_mutex);
+		err = bdev_disk_changed(bdev, false);
+		if (!release)
+			mutex_unlock(&bdev->bd_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo_number, err);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 964f78cfffa0..f6bafa9a68b9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s {
 /*
  * This function check_for_surprise_removal is called
  * while card is removed from the system and it will
- * read the vendor id from the configration space
+ * read the vendor id from the configuration space
  *
  * @pdev Pointer to the pci_dev structure.
  *
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 478aa86fc1f2..57532465fb83 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -385,17 +385,16 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	struct nbd_device *nbd = cmd->nbd;
 	struct nbd_config *config;
 
+	if (!mutex_trylock(&cmd->lock))
+		return BLK_EH_RESET_TIMER;
+
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		cmd->status = BLK_STS_TIMEOUT;
+		mutex_unlock(&cmd->lock);
 		goto done;
 	}
 	config = nbd->config;
 
-	if (!mutex_trylock(&cmd->lock)) {
-		nbd_config_put(nbd);
-		return BLK_EH_RESET_TIMER;
-	}
-
 	if (config->num_connections > 1) {
 		dev_err_ratelimited(nbd_to_dev(nbd),
 				    "Connection timed out, retrying (%d/%d alive)\n",
@@ -711,6 +710,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		ret = -ENOENT;
 		goto out;
 	}
+	if (cmd->status != BLK_STS_OK) {
+		dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n",
+			req);
+		ret = -ENOENT;
+		goto out;
+	}
 	if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
 		dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
 			req);
@@ -792,7 +797,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
+	mutex_lock(&cmd->lock);
 	cmd->status = BLK_STS_IOERR;
+	mutex_unlock(&cmd->lock);
+
 	blk_mq_complete_request(req);
 	return true;
 }
@@ -972,6 +980,26 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
+static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd,
+				     int *err)
+{
+	struct socket *sock;
+
+	*err = 0;
+	sock = sockfd_lookup(fd, err);
+	if (!sock)
+		return NULL;
+
+	if (sock->ops->shutdown == sock_no_shutdown) {
+		dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n");
+		*err = -EINVAL;
+		sockfd_put(sock);
+		return NULL;
+	}
+
+	return sock;
+}
+
 static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 			  bool netlink)
 {
@@ -981,7 +1009,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	struct nbd_sock *nsock;
 	int err;
 
-	sock = sockfd_lookup(arg, &err);
+	sock = nbd_get_socket(nbd, arg, &err);
 	if (!sock)
 		return err;
 
@@ -1004,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
+
+	config->socks = socks;
+
 	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
 	if (!nsock) {
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
 
-	config->socks = socks;
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
@@ -1033,7 +1062,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 	int i;
 	int err;
 
-	sock = sockfd_lookup(arg, &err);
+	sock = nbd_get_socket(nbd, arg, &err);
 	if (!sock)
 		return err;
 
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index a235c45e22a7..bc837862b767 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -91,11 +91,13 @@ struct nullb {
 #ifdef CONFIG_BLK_DEV_ZONED
 int null_zone_init(struct nullb_device *dev);
 void null_zone_exit(struct nullb_device *dev);
-int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones);
+int null_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data);
 blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 				enum req_opf op, sector_t sector,
 				sector_t nr_sectors);
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len);
 #else
 static inline int null_zone_init(struct nullb_device *dev)
 {
@@ -103,17 +105,18 @@ static inline int null_zone_init(struct nullb_device *dev)
 	return -EINVAL;
 }
 static inline void null_zone_exit(struct nullb_device *dev) {}
-static inline int null_zone_report(struct gendisk *disk, sector_t sector,
-				   struct blk_zone *zones,
-				   unsigned int *nr_zones)
-{
-	return -EOPNOTSUPP;
-}
 static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
 					     enum req_opf op, sector_t sector,
 					     sector_t nr_sectors)
 {
 	return BLK_STS_NOTSUPP;
 }
+static inline size_t null_zone_valid_read_len(struct nullb *nullb,
+					      sector_t sector,
+					      unsigned int len)
+{
+	return len;
+}
+#define null_report_zones	NULL
 #endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 0e7da5015ccd..795fda576824 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val,
 	int result;
 
 	result = kstrtouint(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
 	unsigned long tmp;
 
 	result = kstrtoul(page, 0, &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -255,7 +255,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 	int result;
 
 	result = kstrtobool(page,  &tmp);
-	if (result)
+	if (result < 0)
 		return result;
 
 	*val = tmp;
@@ -263,7 +263,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 }
 
 /* The following macro should only be used with TYPE = {uint, ulong, bool}. */
-#define NULLB_DEVICE_ATTR(NAME, TYPE)						\
+#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY)					\
 static ssize_t									\
 nullb_device_##NAME##_show(struct config_item *item, char *page)		\
 {										\
@@ -274,31 +274,57 @@ static ssize_t									\
 nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
 			    size_t count)					\
 {										\
-	if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags))	\
-		return -EBUSY;							\
-	return nullb_device_##TYPE##_attr_store(				\
-			&to_nullb_device(item)->NAME, page, count);		\
+	int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;	\
+	struct nullb_device *dev = to_nullb_device(item);			\
+	TYPE new_value;								\
+	int ret;								\
+										\
+	ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);	\
+	if (ret < 0)								\
+		return ret;							\
+	if (apply_fn)								\
+		ret = apply_fn(dev, new_value);					\
+	else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) 		\
+		ret = -EBUSY;							\
+	if (ret < 0)								\
+		return ret;							\
+	dev->NAME = new_value;							\
+	return count;								\
 }										\
 CONFIGFS_ATTR(nullb_device_, NAME);
 
-NULLB_DEVICE_ATTR(size, ulong);
-NULLB_DEVICE_ATTR(completion_nsec, ulong);
-NULLB_DEVICE_ATTR(submit_queues, uint);
-NULLB_DEVICE_ATTR(home_node, uint);
-NULLB_DEVICE_ATTR(queue_mode, uint);
-NULLB_DEVICE_ATTR(blocksize, uint);
-NULLB_DEVICE_ATTR(irqmode, uint);
-NULLB_DEVICE_ATTR(hw_queue_depth, uint);
-NULLB_DEVICE_ATTR(index, uint);
-NULLB_DEVICE_ATTR(blocking, bool);
-NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
-NULLB_DEVICE_ATTR(memory_backed, bool);
-NULLB_DEVICE_ATTR(discard, bool);
-NULLB_DEVICE_ATTR(mbps, uint);
-NULLB_DEVICE_ATTR(cache_size, ulong);
-NULLB_DEVICE_ATTR(zoned, bool);
-NULLB_DEVICE_ATTR(zone_size, ulong);
-NULLB_DEVICE_ATTR(zone_nr_conv, uint);
+static int nullb_apply_submit_queues(struct nullb_device *dev,
+				     unsigned int submit_queues)
+{
+	struct nullb *nullb = dev->nullb;
+	struct blk_mq_tag_set *set;
+
+	if (!nullb)
+		return 0;
+
+	set = nullb->tag_set;
+	blk_mq_update_nr_hw_queues(set, submit_queues);
+	return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
+}
+
+NULLB_DEVICE_ATTR(size, ulong, NULL);
+NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
+NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
+NULLB_DEVICE_ATTR(home_node, uint, NULL);
+NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
+NULLB_DEVICE_ATTR(blocksize, uint, NULL);
+NULLB_DEVICE_ATTR(irqmode, uint, NULL);
+NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
+NULLB_DEVICE_ATTR(index, uint, NULL);
+NULLB_DEVICE_ATTR(blocking, bool, NULL);
+NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL);
+NULLB_DEVICE_ATTR(memory_backed, bool, NULL);
+NULLB_DEVICE_ATTR(discard, bool, NULL);
+NULLB_DEVICE_ATTR(mbps, uint, NULL);
+NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zoned, bool, NULL);
+NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -467,7 +493,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -996,6 +1022,16 @@ next:
 	return 0;
 }
 
+static void nullb_fill_pattern(struct nullb *nullb, struct page *page,
+			       unsigned int len, unsigned int off)
+{
+	void *dst;
+
+	dst = kmap_atomic(page);
+	memset(dst + off, 0xFF, len);
+	kunmap_atomic(dst);
+}
+
 static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
 {
 	size_t temp;
@@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	unsigned int len, unsigned int off, bool is_write, sector_t sector,
 	bool is_fua)
 {
+	struct nullb_device *dev = nullb->dev;
+	unsigned int valid_len = len;
 	int err = 0;
 
 	if (!is_write) {
-		err = copy_from_nullb(nullb, page, off, sector, len);
+		if (dev->zoned)
+			valid_len = null_zone_valid_read_len(nullb,
+				sector, len);
+
+		if (valid_len) {
+			err = copy_from_nullb(nullb, page, off,
+				sector, valid_len);
+			off += valid_len;
+			len -= valid_len;
+		}
+
+		if (len)
+			nullb_fill_pattern(nullb, page, len, off);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);
@@ -1418,20 +1468,9 @@ static void null_config_discard(struct nullb *nullb)
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
 }
 
-static int null_open(struct block_device *bdev, fmode_t mode)
-{
-	return 0;
-}
-
-static void null_release(struct gendisk *disk, fmode_t mode)
-{
-}
-
-static const struct block_device_operations null_fops = {
-	.owner =	THIS_MODULE,
-	.open =		null_open,
-	.release =	null_release,
-	.report_zones =	null_zone_report,
+static const struct block_device_operations null_ops = {
+	.owner		= THIS_MODULE,
+	.report_zones	= null_report_zones,
 };
 
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
@@ -1532,7 +1571,7 @@ static int null_gendisk_register(struct nullb *nullb)
 	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
-	disk->fops		= &null_fops;
+	disk->fops		= &null_ops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 3d7fdea872f8..d4d88b581822 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -66,22 +66,53 @@ void null_zone_exit(struct nullb_device *dev)
 	kvfree(dev->zones);
 }
 
-int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones)
+int null_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nullb *nullb = disk->private_data;
 	struct nullb_device *dev = nullb->dev;
-	unsigned int zno, nrz = 0;
-
-	zno = null_zone_no(dev, sector);
-	if (zno < dev->nr_zones) {
-		nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno);
-		memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone));
+	unsigned int first_zone, i;
+	struct blk_zone zone;
+	int error;
+
+	first_zone = null_zone_no(dev, sector);
+	if (first_zone >= dev->nr_zones)
+		return 0;
+
+	nr_zones = min(nr_zones, dev->nr_zones - first_zone);
+	for (i = 0; i < nr_zones; i++) {
+		/*
+		 * Stacked DM target drivers will remap the zone information by
+		 * modifying the zone information passed to the report callback.
+		 * So use a local copy to avoid corruption of the device zone
+		 * array.
+		 */
+		memcpy(&zone, &dev->zones[first_zone + i],
+		       sizeof(struct blk_zone));
+		error = cb(&zone, i, data);
+		if (error)
+			return error;
 	}
 
-	*nr_zones = nrz;
+	return nr_zones;
+}
 
-	return 0;
+size_t null_zone_valid_read_len(struct nullb *nullb,
+				sector_t sector, unsigned int len)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+	unsigned int nr_sectors = len >> SECTOR_SHIFT;
+
+	/* Read must be below the write pointer position */
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL ||
+	    sector + nr_sectors <= zone->wp)
+		return len;
+
+	if (sector > zone->wp)
+		return 0;
+
+	return (zone->wp - sector) << SECTOR_SHIFT;
 }
 
 static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
@@ -118,14 +149,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
+static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
+				   sector_t sector)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	unsigned int zno = null_zone_no(dev, sector);
-	struct blk_zone *zone = &dev->zones[zno];
+	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
 	size_t i;
 
-	switch (req_op(cmd->rq)) {
+	switch (op) {
 	case REQ_OP_ZONE_RESET_ALL:
 		for (i = 0; i < dev->nr_zones; i++) {
 			if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
@@ -141,6 +172,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
 		zone->cond = BLK_ZONE_COND_EMPTY;
 		zone->wp = zone->start;
 		break;
+	case REQ_OP_ZONE_OPEN:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_EXP_OPEN;
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_CLOSED;
+		break;
+	case REQ_OP_ZONE_FINISH:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
+
+		zone->cond = BLK_ZONE_COND_FULL;
+		zone->wp = zone->start + zone->len;
+		break;
 	default:
 		return BLK_STS_NOTSUPP;
 	}
@@ -155,7 +209,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
 		return null_zone_write(cmd, sector, nr_sectors);
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
-		return null_zone_reset(cmd, sector);
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return null_zone_mgmt(cmd, op, sector);
 	default:
 		return BLK_STS_OK;
 	}
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 7c4350c0fb77..13527a0b4e44 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2087,7 +2087,7 @@ static int rbd_object_map_update_finish(struct rbd_obj_request *obj_req,
 	struct rbd_device *rbd_dev = obj_req->img_request->rbd_dev;
 	struct ceph_osd_data *osd_data;
 	u64 objno;
-	u8 state, new_state, current_state;
+	u8 state, new_state, uninitialized_var(current_state);
 	bool has_current_state;
 	void *p;
 
@@ -6639,10 +6639,13 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 	queue_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork, 0);
 	ret = wait_for_completion_killable_timeout(&rbd_dev->acquire_wait,
 			    ceph_timeout_jiffies(rbd_dev->opts->lock_timeout));
-	if (ret > 0)
+	if (ret > 0) {
 		ret = rbd_dev->acquire_err;
-	else if (!ret)
-		ret = -ETIMEDOUT;
+	} else {
+		cancel_delayed_work_sync(&rbd_dev->lock_dwork);
+		if (!ret)
+			ret = -ETIMEDOUT;
+	}
 
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret);
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 76b73ddf8fd7..10f6368117d8 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -1000,8 +1000,10 @@ static void rsxx_pci_remove(struct pci_dev *dev)
 
 	cancel_work_sync(&card->event_work);
 
+	destroy_workqueue(card->event_wq);
 	rsxx_destroy_dev(card);
 	rsxx_dma_destroy(card);
+	destroy_workqueue(card->creg_ctrl.creg_wq);
 
 	spin_lock_irqsave(&card->irq_lock, flags);
 	rsxx_disable_ier_and_isr(card, CR_INTR_ALL);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d58a359a6622..4285e75e52c3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -413,13 +413,14 @@ static void reset_bdev(struct zram *zram)
 static ssize_t backing_dev_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	struct file *file;
 	struct zram *zram = dev_to_zram(dev);
-	struct file *file = zram->backing_dev;
 	char *p;
 	ssize_t ret;
 
 	down_read(&zram->init_lock);
-	if (!zram->backing_dev) {
+	file = zram->backing_dev;
+	if (!file) {
 		memcpy(buf, "none\n", 5);
 		up_read(&zram->init_lock);
 		return 5;
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index ad50efb470aa..2b6670daf7fc 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -74,6 +74,7 @@ static const char * const clock_names[SYSC_MAX_CLOCKS] = {
  * @clk_disable_quirk: module specific clock disable quirk
  * @reset_done_quirk: module specific reset done quirk
  * @module_enable_quirk: module specific enable quirk
+ * @module_disable_quirk: module specific disable quirk
  */
 struct sysc {
 	struct device *dev;
@@ -100,6 +101,7 @@ struct sysc {
 	void (*clk_disable_quirk)(struct sysc *sysc);
 	void (*reset_done_quirk)(struct sysc *sysc);
 	void (*module_enable_quirk)(struct sysc *sysc);
+	void (*module_disable_quirk)(struct sysc *sysc);
 };
 
 static void sysc_parse_dts_quirks(struct sysc *ddata, struct device_node *np,
@@ -959,6 +961,9 @@ static int sysc_disable_module(struct device *dev)
 	if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV)
 		return 0;
 
+	if (ddata->module_disable_quirk)
+		ddata->module_disable_quirk(ddata);
+
 	regbits = ddata->cap->regbits;
 	reg = sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
 
@@ -1248,6 +1253,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 		   SYSC_MODULE_QUIRK_SGX),
 	SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
 		   SYSC_MODULE_QUIRK_WDT),
+	/* Watchdog on am3 and am4 */
+	SYSC_QUIRK("wdt", 0x44e35000, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
+		   SYSC_MODULE_QUIRK_WDT | SYSC_QUIRK_SWSUP_SIDLE),
 
 #ifdef DEBUG
 	SYSC_QUIRK("adc", 0, 0, 0x10, -1, 0x47300001, 0xffffffff, 0),
@@ -1440,14 +1448,14 @@ static void sysc_reset_done_quirk_wdt(struct sysc *ddata)
 				   !(val & 0x10), 100,
 				   MAX_MODULE_SOFTRESET_WAIT);
 	if (error)
-		dev_warn(ddata->dev, "wdt disable spr failed\n");
+		dev_warn(ddata->dev, "wdt disable step1 failed\n");
 
-	sysc_write(ddata, wps, 0x5555);
+	sysc_write(ddata, spr, 0x5555);
 	error = readl_poll_timeout(ddata->module_va + wps, val,
 				   !(val & 0x10), 100,
 				   MAX_MODULE_SOFTRESET_WAIT);
 	if (error)
-		dev_warn(ddata->dev, "wdt disable wps failed\n");
+		dev_warn(ddata->dev, "wdt disable step2 failed\n");
 }
 
 static void sysc_init_module_quirks(struct sysc *ddata)
@@ -1471,8 +1479,10 @@ static void sysc_init_module_quirks(struct sysc *ddata)
 	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX)
 		ddata->module_enable_quirk = sysc_module_enable_quirk_sgx;
 
-	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT)
+	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT) {
 		ddata->reset_done_quirk = sysc_reset_done_quirk_wdt;
+		ddata->module_disable_quirk = sysc_reset_done_quirk_wdt;
+	}
 }
 
 static int sysc_clockdomain_init(struct sysc *ddata)
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 80b850ef1bf6..8d53b8ef545c 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -13,7 +13,6 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
-#include <linux/freezer.h>
 #include <linux/fs.h>
 #include <linux/hw_random.h>
 #include <linux/kernel.h>
@@ -422,9 +421,7 @@ static int hwrng_fillfn(void *unused)
 {
 	long rc;
 
-	set_freezable();
-
-	while (!kthread_freezable_should_stop(NULL)) {
+	while (!kthread_should_stop()) {
 		struct hwrng *rng;
 
 		rng = get_current_rng();
diff --git a/drivers/char/random.c b/drivers/char/random.c
index de434feb873a..01b8868b9bed 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -327,7 +327,6 @@
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
-#include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/workqueue.h>
 #include <linux/irq.h>
@@ -2500,8 +2499,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 	 * We'll be woken up again once below random_write_wakeup_thresh,
 	 * or when the calling thread is about to terminate.
 	 */
-	wait_event_freezable(random_write_wait,
-			kthread_should_stop() ||
+	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index 9c37047f4b56..aacdeed93320 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -67,6 +67,13 @@ config TCG_TIS_SPI
 	  within Linux. To compile this driver as a module, choose  M here;
 	  the module will be called tpm_tis_spi.
 
+config TCG_TIS_SPI_CR50
+	bool "Cr50 SPI Interface"
+	depends on TCG_TIS_SPI
+	help
+	  If you have a H1 secure module running Cr50 firmware on SPI bus,
+	  say Yes and it will be accessible from within Linux.
+
 config TCG_TIS_I2C_ATMEL
 	tristate "TPM Interface Specification 1.2 Interface (I2C - Atmel)"
 	depends on I2C
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index c354cdff9c62..5a0d99d4fec0 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -21,7 +21,9 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o
 tpm-$(CONFIG_OF) += eventlog/of.o
 obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
 obj-$(CONFIG_TCG_TIS) += tpm_tis.o
-obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
+obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o
+tpm_tis_spi_mod-y := tpm_tis_spi.o
+tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
 obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
 obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
 obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index d7a3888ad80f..a438b1206fcb 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
+#include <linux/suspend.h>
 #include <linux/freezer.h>
 #include <linux/tpm_eventlog.h>
 
@@ -394,7 +395,11 @@ int tpm_pm_suspend(struct device *dev)
 		return -ENODEV;
 
 	if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED)
-		return 0;
+		goto suspended;
+
+	if ((chip->flags & TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED) &&
+	    !pm_suspend_via_firmware())
+		goto suspended;
 
 	if (!tpm_chip_start(chip)) {
 		if (chip->flags & TPM_CHIP_FLAG_TPM2)
@@ -405,6 +410,7 @@ int tpm_pm_suspend(struct device *dev)
 		tpm_chip_stop(chip);
 	}
 
+suspended:
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_pm_suspend);
@@ -453,62 +459,6 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 }
 EXPORT_SYMBOL_GPL(tpm_get_random);
 
-/**
- * tpm_seal_trusted() - seal a trusted key payload
- * @chip:	a &struct tpm_chip instance, %NULL for the default chip
- * @options:	authentication values and other options
- * @payload:	the key data in clear and encrypted form
- *
- * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
- * the keyring subsystem.
- *
- * Return: same as with tpm_transmit_cmd()
- */
-int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload,
-		     struct trusted_key_options *options)
-{
-	int rc;
-
-	chip = tpm_find_get_ops(chip);
-	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
-		return -ENODEV;
-
-	rc = tpm2_seal_trusted(chip, payload, options);
-
-	tpm_put_ops(chip);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_seal_trusted);
-
-/**
- * tpm_unseal_trusted() - unseal a trusted key
- * @chip:	a &struct tpm_chip instance, %NULL for the default chip
- * @options:	authentication values and other options
- * @payload:	the key data in clear and encrypted form
- *
- * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in
- * the keyring subsystem.
- *
- * Return: same as with tpm_transmit_cmd()
- */
-int tpm_unseal_trusted(struct tpm_chip *chip,
-		       struct trusted_key_payload *payload,
-		       struct trusted_key_options *options)
-{
-	int rc;
-
-	chip = tpm_find_get_ops(chip);
-	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
-		return -ENODEV;
-
-	rc = tpm2_unseal_trusted(chip, payload, options);
-
-	tpm_put_ops(chip);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_unseal_trusted);
-
 static int __init tpm_init(void)
 {
 	int rc;
diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c
index edfa89160010..3b53b3e5ec3e 100644
--- a/drivers/char/tpm/tpm-sysfs.c
+++ b/drivers/char/tpm/tpm-sysfs.c
@@ -217,6 +217,7 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct tpm_chip *chip = to_tpm_chip(dev);
+	struct tpm1_version *version;
 	ssize_t rc = 0;
 	char *str = buf;
 	cap_t cap;
@@ -232,31 +233,31 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr,
 	str += sprintf(str, "Manufacturer: 0x%x\n",
 		       be32_to_cpu(cap.manufacturer_id));
 
-	/* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */
-	rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
+	/* TPM 1.2 */
+	if (!tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
 			 "attempting to determine the 1.2 version",
-			 sizeof(cap.tpm_version_1_2));
-	if (!rc) {
-		str += sprintf(str,
-			       "TCG version: %d.%d\nFirmware version: %d.%d\n",
-			       cap.tpm_version_1_2.Major,
-			       cap.tpm_version_1_2.Minor,
-			       cap.tpm_version_1_2.revMajor,
-			       cap.tpm_version_1_2.revMinor);
-	} else {
-		/* Otherwise just use TPM_STRUCT_VER */
-		if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
-				"attempting to determine the 1.1 version",
-				sizeof(cap.tpm_version)))
-			goto out_ops;
-		str += sprintf(str,
-			       "TCG version: %d.%d\nFirmware version: %d.%d\n",
-			       cap.tpm_version.Major,
-			       cap.tpm_version.Minor,
-			       cap.tpm_version.revMajor,
-			       cap.tpm_version.revMinor);
+			 sizeof(cap.version2))) {
+		version = &cap.version2.version;
+		goto out_print;
 	}
+
+	/* TPM 1.1 */
+	if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
+			"attempting to determine the 1.1 version",
+			sizeof(cap.version1))) {
+		goto out_ops;
+	}
+
+	version = &cap.version1;
+
+out_print:
+	str += sprintf(str,
+		       "TCG version: %d.%d\nFirmware version: %d.%d\n",
+		       version->major, version->minor,
+		       version->rev_major, version->rev_minor);
+
 	rc = str - buf;
+
 out_ops:
 	tpm_put_ops(chip);
 	return rc;
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index a7fea3e0ca86..b9e1547be6b5 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -25,7 +25,6 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/tpm.h>
-#include <linux/highmem.h>
 #include <linux/tpm_eventlog.h>
 
 #ifdef CONFIG_X86
@@ -58,123 +57,6 @@ enum tpm_addr {
 #define TPM_ERR_DISABLED        0x7
 #define TPM_ERR_INVALID_POSTINIT 38
 
-#define TPM_HEADER_SIZE		10
-
-enum tpm2_const {
-	TPM2_PLATFORM_PCR       =     24,
-	TPM2_PCR_SELECT_MIN     = ((TPM2_PLATFORM_PCR + 7) / 8),
-};
-
-enum tpm2_timeouts {
-	TPM2_TIMEOUT_A          =    750,
-	TPM2_TIMEOUT_B          =   2000,
-	TPM2_TIMEOUT_C          =    200,
-	TPM2_TIMEOUT_D          =     30,
-	TPM2_DURATION_SHORT     =     20,
-	TPM2_DURATION_MEDIUM    =    750,
-	TPM2_DURATION_LONG      =   2000,
-	TPM2_DURATION_LONG_LONG = 300000,
-	TPM2_DURATION_DEFAULT   = 120000,
-};
-
-enum tpm2_structures {
-	TPM2_ST_NO_SESSIONS	= 0x8001,
-	TPM2_ST_SESSIONS	= 0x8002,
-};
-
-/* Indicates from what layer of the software stack the error comes from */
-#define TSS2_RC_LAYER_SHIFT	 16
-#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT)
-
-enum tpm2_return_codes {
-	TPM2_RC_SUCCESS		= 0x0000,
-	TPM2_RC_HASH		= 0x0083, /* RC_FMT1 */
-	TPM2_RC_HANDLE		= 0x008B,
-	TPM2_RC_INITIALIZE	= 0x0100, /* RC_VER1 */
-	TPM2_RC_FAILURE		= 0x0101,
-	TPM2_RC_DISABLED	= 0x0120,
-	TPM2_RC_COMMAND_CODE    = 0x0143,
-	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
-	TPM2_RC_REFERENCE_H0	= 0x0910,
-	TPM2_RC_RETRY		= 0x0922,
-};
-
-enum tpm2_command_codes {
-	TPM2_CC_FIRST		        = 0x011F,
-	TPM2_CC_HIERARCHY_CONTROL       = 0x0121,
-	TPM2_CC_HIERARCHY_CHANGE_AUTH   = 0x0129,
-	TPM2_CC_CREATE_PRIMARY          = 0x0131,
-	TPM2_CC_SEQUENCE_COMPLETE       = 0x013E,
-	TPM2_CC_SELF_TEST	        = 0x0143,
-	TPM2_CC_STARTUP		        = 0x0144,
-	TPM2_CC_SHUTDOWN	        = 0x0145,
-	TPM2_CC_NV_READ                 = 0x014E,
-	TPM2_CC_CREATE		        = 0x0153,
-	TPM2_CC_LOAD		        = 0x0157,
-	TPM2_CC_SEQUENCE_UPDATE         = 0x015C,
-	TPM2_CC_UNSEAL		        = 0x015E,
-	TPM2_CC_CONTEXT_LOAD	        = 0x0161,
-	TPM2_CC_CONTEXT_SAVE	        = 0x0162,
-	TPM2_CC_FLUSH_CONTEXT	        = 0x0165,
-	TPM2_CC_VERIFY_SIGNATURE        = 0x0177,
-	TPM2_CC_GET_CAPABILITY	        = 0x017A,
-	TPM2_CC_GET_RANDOM	        = 0x017B,
-	TPM2_CC_PCR_READ	        = 0x017E,
-	TPM2_CC_PCR_EXTEND	        = 0x0182,
-	TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185,
-	TPM2_CC_HASH_SEQUENCE_START     = 0x0186,
-	TPM2_CC_CREATE_LOADED           = 0x0191,
-	TPM2_CC_LAST		        = 0x0193, /* Spec 1.36 */
-};
-
-enum tpm2_permanent_handles {
-	TPM2_RS_PW		= 0x40000009,
-};
-
-enum tpm2_capabilities {
-	TPM2_CAP_HANDLES	= 1,
-	TPM2_CAP_COMMANDS	= 2,
-	TPM2_CAP_PCRS		= 5,
-	TPM2_CAP_TPM_PROPERTIES = 6,
-};
-
-enum tpm2_properties {
-	TPM_PT_TOTAL_COMMANDS	= 0x0129,
-};
-
-enum tpm2_startup_types {
-	TPM2_SU_CLEAR	= 0x0000,
-	TPM2_SU_STATE	= 0x0001,
-};
-
-enum tpm2_cc_attrs {
-	TPM2_CC_ATTR_CHANDLES	= 25,
-	TPM2_CC_ATTR_RHANDLE	= 28,
-};
-
-#define TPM_VID_INTEL    0x8086
-#define TPM_VID_WINBOND  0x1050
-#define TPM_VID_STM      0x104A
-
-enum tpm_chip_flags {
-	TPM_CHIP_FLAG_TPM2		= BIT(1),
-	TPM_CHIP_FLAG_IRQ		= BIT(2),
-	TPM_CHIP_FLAG_VIRTUAL		= BIT(3),
-	TPM_CHIP_FLAG_HAVE_TIMEOUTS	= BIT(4),
-	TPM_CHIP_FLAG_ALWAYS_POWERED	= BIT(5),
-};
-
-#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)
-
-struct tpm_header {
-	__be16 tag;
-	__be32 length;
-	union {
-		__be32 ordinal;
-		__be32 return_code;
-	};
-} __packed;
-
 #define TPM_TAG_RQU_COMMAND 193
 
 struct	stclear_flags_t {
@@ -186,19 +68,16 @@ struct	stclear_flags_t {
 	u8	bGlobalLock;
 } __packed;
 
-struct	tpm_version_t {
-	u8	Major;
-	u8	Minor;
-	u8	revMajor;
-	u8	revMinor;
+struct tpm1_version {
+	u8 major;
+	u8 minor;
+	u8 rev_major;
+	u8 rev_minor;
 } __packed;
 
-struct	tpm_version_1_2_t {
-	__be16	tag;
-	u8	Major;
-	u8	Minor;
-	u8	revMajor;
-	u8	revMinor;
+struct tpm1_version2 {
+	__be16 tag;
+	struct tpm1_version version;
 } __packed;
 
 struct	timeout_t {
@@ -243,8 +122,8 @@ typedef union {
 	struct	stclear_flags_t	stclear_flags;
 	__u8	owned;
 	__be32	num_pcrs;
-	struct	tpm_version_t	tpm_version;
-	struct	tpm_version_1_2_t tpm_version_1_2;
+	struct tpm1_version version1;
+	struct tpm1_version2 version2;
 	__be32	manufacturer_id;
 	struct timeout_t  timeout;
 	struct duration_t duration;
@@ -274,102 +153,6 @@ enum tpm_sub_capabilities {
  * compiler warnings about stack frame size. */
 #define TPM_MAX_RNG_DATA	128
 
-/* A string buffer type for constructing TPM commands. This is based on the
- * ideas of string buffer code in security/keys/trusted.h but is heap based
- * in order to keep the stack usage minimal.
- */
-
-enum tpm_buf_flags {
-	TPM_BUF_OVERFLOW	= BIT(0),
-};
-
-struct tpm_buf {
-	struct page *data_page;
-	unsigned int flags;
-	u8 *data;
-};
-
-static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	head->tag = cpu_to_be16(tag);
-	head->length = cpu_to_be32(sizeof(*head));
-	head->ordinal = cpu_to_be32(ordinal);
-}
-
-static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
-{
-	buf->data_page = alloc_page(GFP_HIGHUSER);
-	if (!buf->data_page)
-		return -ENOMEM;
-
-	buf->flags = 0;
-	buf->data = kmap(buf->data_page);
-	tpm_buf_reset(buf, tag, ordinal);
-	return 0;
-}
-
-static inline void tpm_buf_destroy(struct tpm_buf *buf)
-{
-	kunmap(buf->data_page);
-	__free_page(buf->data_page);
-}
-
-static inline u32 tpm_buf_length(struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	return be32_to_cpu(head->length);
-}
-
-static inline u16 tpm_buf_tag(struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-
-	return be16_to_cpu(head->tag);
-}
-
-static inline void tpm_buf_append(struct tpm_buf *buf,
-				  const unsigned char *new_data,
-				  unsigned int new_len)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-	u32 len = tpm_buf_length(buf);
-
-	/* Return silently if overflow has already happened. */
-	if (buf->flags & TPM_BUF_OVERFLOW)
-		return;
-
-	if ((len + new_len) > PAGE_SIZE) {
-		WARN(1, "tpm_buf: overflow\n");
-		buf->flags |= TPM_BUF_OVERFLOW;
-		return;
-	}
-
-	memcpy(&buf->data[len], new_data, new_len);
-	head->length = cpu_to_be32(len + new_len);
-}
-
-static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value)
-{
-	tpm_buf_append(buf, &value, 1);
-}
-
-static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value)
-{
-	__be16 value2 = cpu_to_be16(value);
-
-	tpm_buf_append(buf, (u8 *) &value2, 2);
-}
-
-static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value)
-{
-	__be32 value2 = cpu_to_be32(value);
-
-	tpm_buf_append(buf, (u8 *) &value2, 4);
-}
-
 extern struct class *tpm_class;
 extern struct class *tpmrm_class;
 extern dev_t tpm_devt;
@@ -429,11 +212,6 @@ static inline void tpm_add_ppi(struct tpm_chip *chip)
 }
 #endif
 
-static inline u32 tpm2_rc_value(u32 rc)
-{
-	return (rc & BIT(7)) ? rc & 0xff : rc;
-}
-
 int tpm2_get_timeouts(struct tpm_chip *chip);
 int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx,
 		  struct tpm_digest *digest, u16 *digest_size_ptr);
@@ -441,12 +219,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx,
 		    struct tpm_digest *digests);
 int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max);
 void tpm2_flush_context(struct tpm_chip *chip, u32 handle);
-int tpm2_seal_trusted(struct tpm_chip *chip,
-		      struct trusted_key_payload *payload,
-		      struct trusted_key_options *options);
-int tpm2_unseal_trusted(struct tpm_chip *chip,
-			struct trusted_key_payload *payload,
-			struct trusted_key_options *options);
 ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,
 			u32 *value, const char *desc);
 
diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c
index 149e953ca369..ca7158fa6e6c 100644
--- a/drivers/char/tpm/tpm1-cmd.c
+++ b/drivers/char/tpm/tpm1-cmd.c
@@ -343,6 +343,7 @@ int tpm1_get_timeouts(struct tpm_chip *chip)
 {
 	cap_t cap;
 	unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4];
+	unsigned long durations[3];
 	ssize_t rc;
 
 	rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL,
@@ -427,6 +428,20 @@ int tpm1_get_timeouts(struct tpm_chip *chip)
 		usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long));
 	chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */
 
+	/*
+	 * Provide the ability for vendor overrides of duration values in case
+	 * of misreporting.
+	 */
+	if (chip->ops->update_durations)
+		chip->ops->update_durations(chip, durations);
+
+	if (chip->duration_adjusted) {
+		dev_info(&chip->dev, HW_ERR "Adjusting reported durations.");
+		chip->duration[TPM_SHORT] = durations[0];
+		chip->duration[TPM_MEDIUM] = durations[1];
+		chip->duration[TPM_LONG] = durations[2];
+	}
+
 	/* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above
 	 * value wrong and apparently reports msecs rather than usecs. So we
 	 * fix up the resulting too-small TPM_SHORT value to make things work.
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index ba9acae83bff..fdb457704aa7 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -13,20 +13,6 @@
 
 #include "tpm.h"
 #include <crypto/hash_info.h>
-#include <keys/trusted-type.h>
-
-enum tpm2_object_attributes {
-	TPM2_OA_USER_WITH_AUTH		= BIT(6),
-};
-
-enum tpm2_session_attributes {
-	TPM2_SA_CONTINUE_SESSION	= BIT(0),
-};
-
-struct tpm2_hash {
-	unsigned int crypto_id;
-	unsigned int tpm_id;
-};
 
 static struct tpm2_hash tpm2_hash_map[] = {
 	{HASH_ALGO_SHA1, TPM_ALG_SHA1},
@@ -377,299 +363,6 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle)
 	tpm_buf_destroy(&buf);
 }
 
-/**
- * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer.
- *
- * @buf: an allocated tpm_buf instance
- * @session_handle: session handle
- * @nonce: the session nonce, may be NULL if not used
- * @nonce_len: the session nonce length, may be 0 if not used
- * @attributes: the session attributes
- * @hmac: the session HMAC or password, may be NULL if not used
- * @hmac_len: the session HMAC or password length, maybe 0 if not used
- */
-static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle,
-				 const u8 *nonce, u16 nonce_len,
-				 u8 attributes,
-				 const u8 *hmac, u16 hmac_len)
-{
-	tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len);
-	tpm_buf_append_u32(buf, session_handle);
-	tpm_buf_append_u16(buf, nonce_len);
-
-	if (nonce && nonce_len)
-		tpm_buf_append(buf, nonce, nonce_len);
-
-	tpm_buf_append_u8(buf, attributes);
-	tpm_buf_append_u16(buf, hmac_len);
-
-	if (hmac && hmac_len)
-		tpm_buf_append(buf, hmac, hmac_len);
-}
-
-/**
- * tpm2_seal_trusted() - seal the payload of a trusted key
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- *
- * Return: < 0 on error and 0 on success.
- */
-int tpm2_seal_trusted(struct tpm_chip *chip,
-		      struct trusted_key_payload *payload,
-		      struct trusted_key_options *options)
-{
-	unsigned int blob_len;
-	struct tpm_buf buf;
-	u32 hash;
-	int i;
-	int rc;
-
-	for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) {
-		if (options->hash == tpm2_hash_map[i].crypto_id) {
-			hash = tpm2_hash_map[i].tpm_id;
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(tpm2_hash_map))
-		return -EINVAL;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, options->keyhandle);
-	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     0 /* session_attributes */,
-			     options->keyauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	/* sensitive */
-	tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1);
-
-	tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE);
-	tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE);
-	tpm_buf_append_u16(&buf, payload->key_len + 1);
-	tpm_buf_append(&buf, payload->key, payload->key_len);
-	tpm_buf_append_u8(&buf, payload->migratable);
-
-	/* public */
-	tpm_buf_append_u16(&buf, 14 + options->policydigest_len);
-	tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH);
-	tpm_buf_append_u16(&buf, hash);
-
-	/* policy */
-	if (options->policydigest_len) {
-		tpm_buf_append_u32(&buf, 0);
-		tpm_buf_append_u16(&buf, options->policydigest_len);
-		tpm_buf_append(&buf, options->policydigest,
-			       options->policydigest_len);
-	} else {
-		tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH);
-		tpm_buf_append_u16(&buf, 0);
-	}
-
-	/* public parameters */
-	tpm_buf_append_u16(&buf, TPM_ALG_NULL);
-	tpm_buf_append_u16(&buf, 0);
-
-	/* outside info */
-	tpm_buf_append_u16(&buf, 0);
-
-	/* creation PCR */
-	tpm_buf_append_u32(&buf, 0);
-
-	if (buf.flags & TPM_BUF_OVERFLOW) {
-		rc = -E2BIG;
-		goto out;
-	}
-
-	rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data");
-	if (rc)
-		goto out;
-
-	blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]);
-	if (blob_len > MAX_BLOB_SIZE) {
-		rc = -E2BIG;
-		goto out;
-	}
-	if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) {
-		rc = -EFAULT;
-		goto out;
-	}
-
-	memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len);
-	payload->blob_len = blob_len;
-
-out:
-	tpm_buf_destroy(&buf);
-
-	if (rc > 0) {
-		if (tpm2_rc_value(rc) == TPM2_RC_HASH)
-			rc = -EINVAL;
-		else
-			rc = -EPERM;
-	}
-
-	return rc;
-}
-
-/**
- * tpm2_load_cmd() - execute a TPM2_Load command
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- * @blob_handle: returned blob handle
- *
- * Return: 0 on success.
- *        -E2BIG on wrong payload size.
- *        -EPERM on tpm error status.
- *        < 0 error from tpm_transmit_cmd.
- */
-static int tpm2_load_cmd(struct tpm_chip *chip,
-			 struct trusted_key_payload *payload,
-			 struct trusted_key_options *options,
-			 u32 *blob_handle)
-{
-	struct tpm_buf buf;
-	unsigned int private_len;
-	unsigned int public_len;
-	unsigned int blob_len;
-	int rc;
-
-	private_len = be16_to_cpup((__be16 *) &payload->blob[0]);
-	if (private_len > (payload->blob_len - 2))
-		return -E2BIG;
-
-	public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]);
-	blob_len = private_len + public_len + 4;
-	if (blob_len > payload->blob_len)
-		return -E2BIG;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, options->keyhandle);
-	tpm2_buf_append_auth(&buf, TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     0 /* session_attributes */,
-			     options->keyauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	tpm_buf_append(&buf, payload->blob, blob_len);
-
-	if (buf.flags & TPM_BUF_OVERFLOW) {
-		rc = -E2BIG;
-		goto out;
-	}
-
-	rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob");
-	if (!rc)
-		*blob_handle = be32_to_cpup(
-			(__be32 *) &buf.data[TPM_HEADER_SIZE]);
-
-out:
-	tpm_buf_destroy(&buf);
-
-	if (rc > 0)
-		rc = -EPERM;
-
-	return rc;
-}
-
-/**
- * tpm2_unseal_cmd() - execute a TPM2_Unload command
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- * @blob_handle: blob handle
- *
- * Return: 0 on success
- *         -EPERM on tpm error status
- *         < 0 error from tpm_transmit_cmd
- */
-static int tpm2_unseal_cmd(struct tpm_chip *chip,
-			   struct trusted_key_payload *payload,
-			   struct trusted_key_options *options,
-			   u32 blob_handle)
-{
-	struct tpm_buf buf;
-	u16 data_len;
-	u8 *data;
-	int rc;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, blob_handle);
-	tpm2_buf_append_auth(&buf,
-			     options->policyhandle ?
-			     options->policyhandle : TPM2_RS_PW,
-			     NULL /* nonce */, 0,
-			     TPM2_SA_CONTINUE_SESSION,
-			     options->blobauth /* hmac */,
-			     TPM_DIGEST_SIZE);
-
-	rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing");
-	if (rc > 0)
-		rc = -EPERM;
-
-	if (!rc) {
-		data_len = be16_to_cpup(
-			(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
-		if (data_len < MIN_KEY_SIZE ||  data_len > MAX_KEY_SIZE + 1) {
-			rc = -EFAULT;
-			goto out;
-		}
-
-		if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) {
-			rc = -EFAULT;
-			goto out;
-		}
-		data = &buf.data[TPM_HEADER_SIZE + 6];
-
-		memcpy(payload->key, data, data_len - 1);
-		payload->key_len = data_len - 1;
-		payload->migratable = data[data_len - 1];
-	}
-
-out:
-	tpm_buf_destroy(&buf);
-	return rc;
-}
-
-/**
- * tpm2_unseal_trusted() - unseal the payload of a trusted key
- *
- * @chip: TPM chip to use
- * @payload: the key data in clear and encrypted form
- * @options: authentication values and other options
- *
- * Return: Same as with tpm_transmit_cmd.
- */
-int tpm2_unseal_trusted(struct tpm_chip *chip,
-			struct trusted_key_payload *payload,
-			struct trusted_key_options *options)
-{
-	u32 blob_handle;
-	int rc;
-
-	rc = tpm2_load_cmd(chip, payload, options, &blob_handle);
-	if (rc)
-		return rc;
-
-	rc = tpm2_unseal_cmd(chip, payload, options, blob_handle);
-	tpm2_flush_context(chip, blob_handle);
-	return rc;
-}
-
 struct tpm2_get_cap_out {
 	u8 more_data;
 	__be32 subcap_id;
@@ -939,6 +632,10 @@ static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip)
 
 	chip->cc_attrs_tbl = devm_kcalloc(&chip->dev, 4, nr_commands,
 					  GFP_KERNEL);
+	if (!chip->cc_attrs_tbl) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
 	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
 	if (rc)
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index e59f1f91d7f3..a9dcf31eadd2 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -22,6 +22,7 @@
 #include "tpm.h"
 
 #define ACPI_SIG_TPM2 "TPM2"
+#define TPM_CRB_MAX_RESOURCES 3
 
 static const guid_t crb_acpi_start_guid =
 	GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714,
@@ -91,7 +92,6 @@ enum crb_status {
 struct crb_priv {
 	u32 sm;
 	const char *hid;
-	void __iomem *iobase;
 	struct crb_regs_head __iomem *regs_h;
 	struct crb_regs_tail __iomem *regs_t;
 	u8 __iomem *cmd;
@@ -434,21 +434,27 @@ static const struct tpm_class_ops tpm_crb = {
 
 static int crb_check_resource(struct acpi_resource *ares, void *data)
 {
-	struct resource *io_res = data;
+	struct resource *iores_array = data;
 	struct resource_win win;
 	struct resource *res = &(win.res);
+	int i;
 
 	if (acpi_dev_resource_memory(ares, res) ||
 	    acpi_dev_resource_address_space(ares, &win)) {
-		*io_res = *res;
-		io_res->name = NULL;
+		for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) {
+			if (resource_type(iores_array + i) != IORESOURCE_MEM) {
+				iores_array[i] = *res;
+				iores_array[i].name = NULL;
+				break;
+			}
+		}
 	}
 
 	return 1;
 }
 
-static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv,
-				 struct resource *io_res, u64 start, u32 size)
+static void __iomem *crb_map_res(struct device *dev, struct resource *iores,
+				 void __iomem **iobase_ptr, u64 start, u32 size)
 {
 	struct resource new_res = {
 		.start	= start,
@@ -460,10 +466,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv,
 	if (start != new_res.start)
 		return (void __iomem *) ERR_PTR(-EINVAL);
 
-	if (!resource_contains(io_res, &new_res))
+	if (!iores)
 		return devm_ioremap_resource(dev, &new_res);
 
-	return priv->iobase + (new_res.start - io_res->start);
+	if (!*iobase_ptr) {
+		*iobase_ptr = devm_ioremap_resource(dev, iores);
+		if (IS_ERR(*iobase_ptr))
+			return *iobase_ptr;
+	}
+
+	return *iobase_ptr + (new_res.start - iores->start);
 }
 
 /*
@@ -490,9 +502,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res,
 static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 		      struct acpi_table_tpm2 *buf)
 {
-	struct list_head resources;
-	struct resource io_res;
+	struct list_head acpi_resource_list;
+	struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} };
+	void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL};
 	struct device *dev = &device->dev;
+	struct resource *iores;
+	void __iomem **iobase_ptr;
+	int i;
 	u32 pa_high, pa_low;
 	u64 cmd_pa;
 	u32 cmd_size;
@@ -501,21 +517,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	u32 rsp_size;
 	int ret;
 
-	INIT_LIST_HEAD(&resources);
-	ret = acpi_dev_get_resources(device, &resources, crb_check_resource,
-				     &io_res);
+	INIT_LIST_HEAD(&acpi_resource_list);
+	ret = acpi_dev_get_resources(device, &acpi_resource_list,
+				     crb_check_resource, iores_array);
 	if (ret < 0)
 		return ret;
-	acpi_dev_free_resource_list(&resources);
+	acpi_dev_free_resource_list(&acpi_resource_list);
 
-	if (resource_type(&io_res) != IORESOURCE_MEM) {
+	if (resource_type(iores_array) != IORESOURCE_MEM) {
 		dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n");
 		return -EINVAL;
+	} else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) ==
+		IORESOURCE_MEM) {
+		dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n");
+		memset(iores_array + TPM_CRB_MAX_RESOURCES,
+		       0, sizeof(*iores_array));
+		iores_array[TPM_CRB_MAX_RESOURCES].flags = 0;
 	}
 
-	priv->iobase = devm_ioremap_resource(dev, &io_res);
-	if (IS_ERR(priv->iobase))
-		return PTR_ERR(priv->iobase);
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) {
+		if (buf->control_address >= iores_array[i].start &&
+		    buf->control_address + sizeof(struct crb_regs_tail) - 1 <=
+		    iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address,
+				   sizeof(struct crb_regs_tail));
+
+	if (IS_ERR(priv->regs_t))
+		return PTR_ERR(priv->regs_t);
 
 	/* The ACPI IO region starts at the head area and continues to include
 	 * the control area, as one nice sane region except for some older
@@ -523,9 +559,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	 */
 	if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) ||
 	    (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) {
-		if (buf->control_address == io_res.start +
+		if (iores &&
+		    buf->control_address == iores->start +
 		    sizeof(*priv->regs_h))
-			priv->regs_h = priv->iobase;
+			priv->regs_h = *iobase_ptr;
 		else
 			dev_warn(dev, FW_BUG "Bad ACPI memory layout");
 	}
@@ -534,13 +571,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	if (ret)
 		return ret;
 
-	priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address,
-				   sizeof(struct crb_regs_tail));
-	if (IS_ERR(priv->regs_t)) {
-		ret = PTR_ERR(priv->regs_t);
-		goto out_relinquish_locality;
-	}
-
 	/*
 	 * PTT HW bug w/a: wake up the device to access
 	 * possibly not retained registers.
@@ -552,13 +582,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high);
 	pa_low  = ioread32(&priv->regs_t->ctrl_cmd_pa_low);
 	cmd_pa = ((u64)pa_high << 32) | pa_low;
-	cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa,
-				      ioread32(&priv->regs_t->ctrl_cmd_size));
+	cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size);
+
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; iores_array[i].end; ++i) {
+		if (cmd_pa >= iores_array[i].start &&
+		    cmd_pa <= iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	if (iores)
+		cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size);
 
 	dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n",
 		pa_high, pa_low, cmd_size);
 
-	priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size);
+	priv->cmd = crb_map_res(dev, iores, iobase_ptr,	cmd_pa, cmd_size);
 	if (IS_ERR(priv->cmd)) {
 		ret = PTR_ERR(priv->cmd);
 		goto out;
@@ -566,11 +609,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 
 	memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8);
 	rsp_pa = le64_to_cpu(__rsp_pa);
-	rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa,
-				      ioread32(&priv->regs_t->ctrl_rsp_size));
+	rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size);
+
+	iores = NULL;
+	iobase_ptr = NULL;
+	for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) {
+		if (rsp_pa >= iores_array[i].start &&
+		    rsp_pa <= iores_array[i].end) {
+			iores = iores_array + i;
+			iobase_ptr = iobase_array + i;
+			break;
+		}
+	}
+
+	if (iores)
+		rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size);
 
 	if (cmd_pa != rsp_pa) {
-		priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size);
+		priv->rsp = crb_map_res(dev, iores, iobase_ptr,
+					rsp_pa, rsp_size);
 		ret = PTR_ERR_OR_ZERO(priv->rsp);
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e4fdde93ed4c..e7df342a317d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev)
 	}
 	tpm_info.res = *res;
 
-	tpm_info.irq = platform_get_irq(pdev, 0);
+	tpm_info.irq = platform_get_irq_optional(pdev, 0);
 	if (tpm_info.irq <= 0) {
 		if (pdev != force_pdev)
 			tpm_info.irq = -1;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 270f43acbb77..8af2cee1a762 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -506,6 +506,84 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
 	return rc;
 }
 
+struct tis_vendor_durations_override {
+	u32 did_vid;
+	struct tpm1_version version;
+	unsigned long durations[3];
+};
+
+static const struct  tis_vendor_durations_override vendor_dur_overrides[] = {
+	/* STMicroelectronics 0x104a */
+	{ 0x0000104a,
+	  { 1, 2, 8, 28 },
+	  { (2 * 60 * HZ), (2 * 60 * HZ), (2 * 60 * HZ) } },
+};
+
+static void tpm_tis_update_durations(struct tpm_chip *chip,
+				     unsigned long *duration_cap)
+{
+	struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
+	struct tpm1_version *version;
+	u32 did_vid;
+	int i, rc;
+	cap_t cap;
+
+	chip->duration_adjusted = false;
+
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, true);
+
+	rc = tpm_tis_read32(priv, TPM_DID_VID(0), &did_vid);
+	if (rc < 0) {
+		dev_warn(&chip->dev, "%s: failed to read did_vid. %d\n",
+			 __func__, rc);
+		goto out;
+	}
+
+	/* Try to get a TPM version 1.2 or 1.1 TPM_CAP_VERSION_INFO */
+	rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap,
+			 "attempting to determine the 1.2 version",
+			 sizeof(cap.version2));
+	if (!rc) {
+		version = &cap.version2.version;
+	} else {
+		rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap,
+				 "attempting to determine the 1.1 version",
+				 sizeof(cap.version1));
+
+		if (rc)
+			goto out;
+
+		version = &cap.version1;
+	}
+
+	for (i = 0; i != ARRAY_SIZE(vendor_dur_overrides); i++) {
+		if (vendor_dur_overrides[i].did_vid != did_vid)
+			continue;
+
+		if ((version->major ==
+		     vendor_dur_overrides[i].version.major) &&
+		    (version->minor ==
+		     vendor_dur_overrides[i].version.minor) &&
+		    (version->rev_major ==
+		     vendor_dur_overrides[i].version.rev_major) &&
+		    (version->rev_minor ==
+		     vendor_dur_overrides[i].version.rev_minor)) {
+
+			memcpy(duration_cap,
+			       vendor_dur_overrides[i].durations,
+			       sizeof(vendor_dur_overrides[i].durations));
+
+			chip->duration_adjusted = true;
+			goto out;
+		}
+	}
+
+out:
+	if (chip->ops->clk_enable != NULL)
+		chip->ops->clk_enable(chip, false);
+}
+
 struct tis_vendor_timeout_override {
 	u32 did_vid;
 	unsigned long timeout_us[4];
@@ -842,6 +920,7 @@ static const struct tpm_class_ops tpm_tis = {
 	.send = tpm_tis_send,
 	.cancel = tpm_tis_ready,
 	.update_timeouts = tpm_tis_update_timeouts,
+	.update_durations = tpm_tis_update_durations,
 	.req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_canceled = tpm_tis_req_canceled,
diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c
index 19513e622053..d1754fd6c573 100644
--- a/drivers/char/tpm/tpm_tis_spi.c
+++ b/drivers/char/tpm/tpm_tis_spi.c
@@ -20,42 +20,64 @@
  * Dorn and Kyleen Hall and Jarko Sakkinnen.
  */
 
+#include <linux/acpi.h>
+#include <linux/completion.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/wait.h>
-#include <linux/acpi.h>
-#include <linux/freezer.h>
 
+#include <linux/of_device.h>
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_irq.h>
-#include <linux/of_gpio.h>
 #include <linux/tpm.h>
+
 #include "tpm.h"
 #include "tpm_tis_core.h"
+#include "tpm_tis_spi.h"
 
 #define MAX_SPI_FRAMESIZE 64
 
-struct tpm_tis_spi_phy {
-	struct tpm_tis_data priv;
-	struct spi_device *spi_device;
-	u8 *iobuf;
-};
-
-static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data)
+/*
+ * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short,
+ * keep trying to read from the device until MISO goes high indicating the
+ * wait state has ended.
+ *
+ * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
+ */
+static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy,
+				    struct spi_transfer *spi_xfer)
 {
-	return container_of(data, struct tpm_tis_spi_phy, priv);
+	struct spi_message m;
+	int ret, i;
+
+	if ((phy->iobuf[3] & 0x01) == 0) {
+		// handle SPI wait states
+		phy->iobuf[0] = 0;
+
+		for (i = 0; i < TPM_RETRY; i++) {
+			spi_xfer->len = 1;
+			spi_message_init(&m);
+			spi_message_add_tail(spi_xfer, &m);
+			ret = spi_sync_locked(phy->spi_device, &m);
+			if (ret < 0)
+				return ret;
+			if (phy->iobuf[0] & 0x01)
+				break;
+		}
+
+		if (i == TPM_RETRY)
+			return -ETIMEDOUT;
+	}
+
+	return 0;
 }
 
-static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
-				u8 *in, const u8 *out)
+int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+			 u8 *in, const u8 *out)
 {
 	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
 	int ret = 0;
-	int i;
 	struct spi_message m;
 	struct spi_transfer spi_xfer;
 	u8 transfer_len;
@@ -82,26 +104,9 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
 		if (ret < 0)
 			goto exit;
 
-		if ((phy->iobuf[3] & 0x01) == 0) {
-			// handle SPI wait states
-			phy->iobuf[0] = 0;
-
-			for (i = 0; i < TPM_RETRY; i++) {
-				spi_xfer.len = 1;
-				spi_message_init(&m);
-				spi_message_add_tail(&spi_xfer, &m);
-				ret = spi_sync_locked(phy->spi_device, &m);
-				if (ret < 0)
-					goto exit;
-				if (phy->iobuf[0] & 0x01)
-					break;
-			}
-
-			if (i == TPM_RETRY) {
-				ret = -ETIMEDOUT;
-				goto exit;
-			}
-		}
+		ret = phy->flow_control(phy, &spi_xfer);
+		if (ret < 0)
+			goto exit;
 
 		spi_xfer.cs_change = 0;
 		spi_xfer.len = transfer_len;
@@ -117,6 +122,7 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
 
 		spi_message_init(&m);
 		spi_message_add_tail(&spi_xfer, &m);
+		reinit_completion(&phy->ready);
 		ret = spi_sync_locked(phy->spi_device, &m);
 		if (ret < 0)
 			goto exit;
@@ -146,7 +152,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
 	return tpm_tis_spi_transfer(data, addr, len, NULL, value);
 }
 
-static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
+int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
 {
 	__le16 result_le;
 	int rc;
@@ -159,7 +165,7 @@ static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
 	return rc;
 }
 
-static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
+int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
 {
 	__le32 result_le;
 	int rc;
@@ -172,7 +178,7 @@ static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result)
 	return rc;
 }
 
-static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
+int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 {
 	__le32 value_le;
 	int rc;
@@ -184,6 +190,18 @@ static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 	return rc;
 }
 
+int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
+		     int irq, const struct tpm_tis_phy_ops *phy_ops)
+{
+	phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
+	if (!phy->iobuf)
+		return -ENOMEM;
+
+	phy->spi_device = spi;
+
+	return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL);
+}
+
 static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
 	.read_bytes = tpm_tis_spi_read_bytes,
 	.write_bytes = tpm_tis_spi_write_bytes,
@@ -202,11 +220,7 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	if (!phy)
 		return -ENOMEM;
 
-	phy->spi_device = dev;
-
-	phy->iobuf = devm_kmalloc(&dev->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
-	if (!phy->iobuf)
-		return -ENOMEM;
+	phy->flow_control = tpm_tis_spi_flow_control;
 
 	/* If the SPI device has an IRQ then use that */
 	if (dev->irq > 0)
@@ -214,11 +228,27 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	else
 		irq = -1;
 
-	return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops,
-				 NULL);
+	init_completion(&phy->ready);
+	return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops);
+}
+
+typedef int (*tpm_tis_spi_probe_func)(struct spi_device *);
+
+static int tpm_tis_spi_driver_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *spi_dev_id = spi_get_device_id(spi);
+	tpm_tis_spi_probe_func probe_func;
+
+	probe_func = of_device_get_match_data(&spi->dev);
+	if (!probe_func && spi_dev_id)
+		probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data;
+	if (!probe_func)
+		return -ENODEV;
+
+	return probe_func(spi);
 }
 
-static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
+static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume);
 
 static int tpm_tis_spi_remove(struct spi_device *dev)
 {
@@ -230,15 +260,17 @@ static int tpm_tis_spi_remove(struct spi_device *dev)
 }
 
 static const struct spi_device_id tpm_tis_spi_id[] = {
-	{"tpm_tis_spi", 0},
+	{ "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+	{ "cr50", (unsigned long)cr50_spi_probe },
 	{}
 };
 MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id);
 
 static const struct of_device_id of_tis_spi_match[] = {
-	{ .compatible = "st,st33htpm-spi", },
-	{ .compatible = "infineon,slb9670", },
-	{ .compatible = "tcg,tpm_tis-spi", },
+	{ .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe },
+	{ .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe },
+	{ .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe },
+	{ .compatible = "google,cr50", .data = cr50_spi_probe },
 	{}
 };
 MODULE_DEVICE_TABLE(of, of_tis_spi_match);
@@ -251,13 +283,12 @@ MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match);
 
 static struct spi_driver tpm_tis_spi_driver = {
 	.driver = {
-		.owner = THIS_MODULE,
 		.name = "tpm_tis_spi",
 		.pm = &tpm_tis_pm,
 		.of_match_table = of_match_ptr(of_tis_spi_match),
 		.acpi_match_table = ACPI_PTR(acpi_tis_spi_match),
 	},
-	.probe = tpm_tis_spi_probe,
+	.probe = tpm_tis_spi_driver_probe,
 	.remove = tpm_tis_spi_remove,
 	.id_table = tpm_tis_spi_id,
 };
diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h
new file mode 100644
index 000000000000..bba73979c368
--- /dev/null
+++ b/drivers/char/tpm/tpm_tis_spi.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 Infineon Technologies AG
+ * Copyright (C) 2016 STMicroelectronics SAS
+ */
+
+#ifndef TPM_TIS_SPI_H
+#define TPM_TIS_SPI_H
+
+#include "tpm_tis_core.h"
+
+struct tpm_tis_spi_phy {
+	struct tpm_tis_data priv;
+	struct spi_device *spi_device;
+	int (*flow_control)(struct tpm_tis_spi_phy *phy,
+			     struct spi_transfer *xfer);
+	struct completion ready;
+	unsigned long wake_after;
+
+	u8 *iobuf;
+};
+
+static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data)
+{
+	return container_of(data, struct tpm_tis_spi_phy, priv);
+}
+
+extern int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy,
+			    int irq, const struct tpm_tis_phy_ops *phy_ops);
+
+extern int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+				u8 *in, const u8 *out);
+
+extern int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result);
+extern int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result);
+extern int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value);
+
+#ifdef CONFIG_TCG_TIS_SPI_CR50
+extern int cr50_spi_probe(struct spi_device *spi);
+#else
+static inline int cr50_spi_probe(struct spi_device *spi)
+{
+	return -ENODEV;
+}
+#endif
+
+#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_TCG_TIS_SPI_CR50)
+extern int tpm_tis_spi_resume(struct device *dev);
+#else
+#define tpm_tis_spi_resume	NULL
+#endif
+
+#endif
diff --git a/drivers/char/tpm/tpm_tis_spi_cr50.c b/drivers/char/tpm/tpm_tis_spi_cr50.c
new file mode 100644
index 000000000000..37d72e818335
--- /dev/null
+++ b/drivers/char/tpm/tpm_tis_spi_cr50.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This device driver implements a TCG PTP FIFO interface over SPI for chips
+ * with Cr50 firmware.
+ * It is based on tpm_tis_spi driver by Peter Huewe and Christophe Ricard.
+ */
+
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/spi/spi.h>
+#include <linux/wait.h>
+
+#include "tpm_tis_core.h"
+#include "tpm_tis_spi.h"
+
+/*
+ * Cr50 timing constants:
+ * - can go to sleep not earlier than after CR50_SLEEP_DELAY_MSEC.
+ * - needs up to CR50_WAKE_START_DELAY_USEC to wake after sleep.
+ * - requires waiting for "ready" IRQ, if supported; or waiting for at least
+ *   CR50_NOIRQ_ACCESS_DELAY_MSEC between transactions, if IRQ is not supported.
+ * - waits for up to CR50_FLOW_CONTROL for flow control 'ready' indication.
+ */
+#define CR50_SLEEP_DELAY_MSEC			1000
+#define CR50_WAKE_START_DELAY_USEC		1000
+#define CR50_NOIRQ_ACCESS_DELAY			msecs_to_jiffies(2)
+#define CR50_READY_IRQ_TIMEOUT			msecs_to_jiffies(TPM2_TIMEOUT_A)
+#define CR50_FLOW_CONTROL			msecs_to_jiffies(TPM2_TIMEOUT_A)
+#define MAX_IRQ_CONFIRMATION_ATTEMPTS		3
+
+#define TPM_CR50_FW_VER(l)			(0x0f90 | ((l) << 12))
+#define TPM_CR50_MAX_FW_VER_LEN			64
+
+struct cr50_spi_phy {
+	struct tpm_tis_spi_phy spi_phy;
+
+	struct mutex time_track_mutex;
+	unsigned long last_access;
+
+	unsigned long access_delay;
+
+	unsigned int irq_confirmation_attempt;
+	bool irq_needs_confirmation;
+	bool irq_confirmed;
+};
+
+static inline struct cr50_spi_phy *to_cr50_spi_phy(struct tpm_tis_spi_phy *phy)
+{
+	return container_of(phy, struct cr50_spi_phy, spi_phy);
+}
+
+/*
+ * The cr50 interrupt handler just signals waiting threads that the
+ * interrupt was asserted.  It does not do any processing triggered
+ * by interrupts but is instead used to avoid fixed delays.
+ */
+static irqreturn_t cr50_spi_irq_handler(int dummy, void *dev_id)
+{
+	struct cr50_spi_phy *cr50_phy = dev_id;
+
+	cr50_phy->irq_confirmed = true;
+	complete(&cr50_phy->spi_phy.ready);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Cr50 needs to have at least some delay between consecutive
+ * transactions. Make sure we wait.
+ */
+static void cr50_ensure_access_delay(struct cr50_spi_phy *phy)
+{
+	unsigned long allowed_access = phy->last_access + phy->access_delay;
+	unsigned long time_now = jiffies;
+	struct device *dev = &phy->spi_phy.spi_device->dev;
+
+	/*
+	 * Note: There is a small chance, if Cr50 is not accessed in a few days,
+	 * that time_in_range will not provide the correct result after the wrap
+	 * around for jiffies. In this case, we'll have an unneeded short delay,
+	 * which is fine.
+	 */
+	if (time_in_range_open(time_now, phy->last_access, allowed_access)) {
+		unsigned long remaining, timeout = allowed_access - time_now;
+
+		remaining = wait_for_completion_timeout(&phy->spi_phy.ready,
+							timeout);
+		if (!remaining && phy->irq_confirmed)
+			dev_warn(dev, "Timeout waiting for TPM ready IRQ\n");
+	}
+
+	if (phy->irq_needs_confirmation) {
+		unsigned int attempt = ++phy->irq_confirmation_attempt;
+
+		if (phy->irq_confirmed) {
+			phy->irq_needs_confirmation = false;
+			phy->access_delay = CR50_READY_IRQ_TIMEOUT;
+			dev_info(dev, "TPM ready IRQ confirmed on attempt %u\n",
+				 attempt);
+		} else if (attempt > MAX_IRQ_CONFIRMATION_ATTEMPTS) {
+			phy->irq_needs_confirmation = false;
+			dev_warn(dev, "IRQ not confirmed - will use delays\n");
+		}
+	}
+}
+
+/*
+ * Cr50 might go to sleep if there is no SPI activity for some time and
+ * miss the first few bits/bytes on the bus. In such case, wake it up
+ * by asserting CS and give it time to start up.
+ */
+static bool cr50_needs_waking(struct cr50_spi_phy *phy)
+{
+	/*
+	 * Note: There is a small chance, if Cr50 is not accessed in a few days,
+	 * that time_in_range will not provide the correct result after the wrap
+	 * around for jiffies. In this case, we'll probably timeout or read
+	 * incorrect value from TPM_STS and just retry the operation.
+	 */
+	return !time_in_range_open(jiffies, phy->last_access,
+				   phy->spi_phy.wake_after);
+}
+
+static void cr50_wake_if_needed(struct cr50_spi_phy *cr50_phy)
+{
+	struct tpm_tis_spi_phy *phy = &cr50_phy->spi_phy;
+
+	if (cr50_needs_waking(cr50_phy)) {
+		/* Assert CS, wait 1 msec, deassert CS */
+		struct spi_transfer spi_cs_wake = { .delay_usecs = 1000 };
+
+		spi_sync_transfer(phy->spi_device, &spi_cs_wake, 1);
+		/* Wait for it to fully wake */
+		usleep_range(CR50_WAKE_START_DELAY_USEC,
+			     CR50_WAKE_START_DELAY_USEC * 2);
+	}
+
+	/* Reset the time when we need to wake Cr50 again */
+	phy->wake_after = jiffies + msecs_to_jiffies(CR50_SLEEP_DELAY_MSEC);
+}
+
+/*
+ * Flow control: clock the bus and wait for cr50 to set LSB before
+ * sending/receiving data. TCG PTP spec allows it to happen during
+ * the last byte of header, but cr50 never does that in practice,
+ * and earlier versions had a bug when it was set too early, so don't
+ * check for it during header transfer.
+ */
+static int cr50_spi_flow_control(struct tpm_tis_spi_phy *phy,
+				 struct spi_transfer *spi_xfer)
+{
+	struct device *dev = &phy->spi_device->dev;
+	unsigned long timeout = jiffies + CR50_FLOW_CONTROL;
+	struct spi_message m;
+	int ret;
+
+	spi_xfer->len = 1;
+
+	do {
+		spi_message_init(&m);
+		spi_message_add_tail(spi_xfer, &m);
+		ret = spi_sync_locked(phy->spi_device, &m);
+		if (ret < 0)
+			return ret;
+
+		if (time_after(jiffies, timeout)) {
+			dev_warn(dev, "Timeout during flow control\n");
+			return -EBUSY;
+		}
+	} while (!(phy->iobuf[0] & 0x01));
+
+	return 0;
+}
+
+static int tpm_tis_spi_cr50_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
+				     u8 *in, const u8 *out)
+{
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	struct cr50_spi_phy *cr50_phy = to_cr50_spi_phy(phy);
+	int ret;
+
+	mutex_lock(&cr50_phy->time_track_mutex);
+	/*
+	 * Do this outside of spi_bus_lock in case cr50 is not the
+	 * only device on that spi bus.
+	 */
+	cr50_ensure_access_delay(cr50_phy);
+	cr50_wake_if_needed(cr50_phy);
+
+	ret = tpm_tis_spi_transfer(data, addr, len, in, out);
+
+	cr50_phy->last_access = jiffies;
+	mutex_unlock(&cr50_phy->time_track_mutex);
+
+	return ret;
+}
+
+static int tpm_tis_spi_cr50_read_bytes(struct tpm_tis_data *data, u32 addr,
+				       u16 len, u8 *result)
+{
+	return tpm_tis_spi_cr50_transfer(data, addr, len, result, NULL);
+}
+
+static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr,
+					u16 len, const u8 *value)
+{
+	return tpm_tis_spi_cr50_transfer(data, addr, len, NULL, value);
+}
+
+static const struct tpm_tis_phy_ops tpm_spi_cr50_phy_ops = {
+	.read_bytes = tpm_tis_spi_cr50_read_bytes,
+	.write_bytes = tpm_tis_spi_cr50_write_bytes,
+	.read16 = tpm_tis_spi_read16,
+	.read32 = tpm_tis_spi_read32,
+	.write32 = tpm_tis_spi_write32,
+};
+
+static void cr50_print_fw_version(struct tpm_tis_data *data)
+{
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	int i, len = 0;
+	char fw_ver[TPM_CR50_MAX_FW_VER_LEN + 1];
+	char fw_ver_block[4];
+
+	/*
+	 * Write anything to TPM_CR50_FW_VER to start from the beginning
+	 * of the version string
+	 */
+	tpm_tis_write8(data, TPM_CR50_FW_VER(data->locality), 0);
+
+	/* Read the string, 4 bytes at a time, until we get '\0' */
+	do {
+		tpm_tis_read_bytes(data, TPM_CR50_FW_VER(data->locality), 4,
+				   fw_ver_block);
+		for (i = 0; i < 4 && fw_ver_block[i]; ++len, ++i)
+			fw_ver[len] = fw_ver_block[i];
+	} while (i == 4 && len < TPM_CR50_MAX_FW_VER_LEN);
+	fw_ver[len] = '\0';
+
+	dev_info(&phy->spi_device->dev, "Cr50 firmware version: %s\n", fw_ver);
+}
+
+int cr50_spi_probe(struct spi_device *spi)
+{
+	struct tpm_tis_spi_phy *phy;
+	struct cr50_spi_phy *cr50_phy;
+	int ret;
+	struct tpm_chip *chip;
+
+	cr50_phy = devm_kzalloc(&spi->dev, sizeof(*cr50_phy), GFP_KERNEL);
+	if (!cr50_phy)
+		return -ENOMEM;
+
+	phy = &cr50_phy->spi_phy;
+	phy->flow_control = cr50_spi_flow_control;
+	phy->wake_after = jiffies;
+	init_completion(&phy->ready);
+
+	cr50_phy->access_delay = CR50_NOIRQ_ACCESS_DELAY;
+	cr50_phy->last_access = jiffies;
+	mutex_init(&cr50_phy->time_track_mutex);
+
+	if (spi->irq > 0) {
+		ret = devm_request_irq(&spi->dev, spi->irq,
+				       cr50_spi_irq_handler,
+				       IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				       "cr50_spi", cr50_phy);
+		if (ret < 0) {
+			if (ret == -EPROBE_DEFER)
+				return ret;
+			dev_warn(&spi->dev, "Requesting IRQ %d failed: %d\n",
+				 spi->irq, ret);
+			/*
+			 * This is not fatal, the driver will fall back to
+			 * delays automatically, since ready will never
+			 * be completed without a registered irq handler.
+			 * So, just fall through.
+			 */
+		} else {
+			/*
+			 * IRQ requested, let's verify that it is actually
+			 * triggered, before relying on it.
+			 */
+			cr50_phy->irq_needs_confirmation = true;
+		}
+	} else {
+		dev_warn(&spi->dev,
+			 "No IRQ - will use delays between transactions.\n");
+	}
+
+	ret = tpm_tis_spi_init(spi, phy, -1, &tpm_spi_cr50_phy_ops);
+	if (ret)
+		return ret;
+
+	cr50_print_fw_version(&phy->priv);
+
+	chip = dev_get_drvdata(&spi->dev);
+	chip->flags |= TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+int tpm_tis_spi_resume(struct device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_tis_data *data = dev_get_drvdata(&chip->dev);
+	struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
+	/*
+	 * Jiffies not increased during suspend, so we need to reset
+	 * the time to wake Cr50 after resume.
+	 */
+	phy->wake_after = jiffies;
+
+	return tpm_tis_resume(dev);
+}
+#endif
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 7270e7b69262..3259426f01dc 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1325,24 +1325,24 @@ static void set_console_size(struct port *port, u16 rows, u16 cols)
 	port->cons.ws.ws_col = cols;
 }
 
-static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
+static int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 {
 	struct port_buffer *buf;
-	unsigned int nr_added_bufs;
+	int nr_added_bufs;
 	int ret;
 
 	nr_added_bufs = 0;
 	do {
 		buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
 		if (!buf)
-			break;
+			return -ENOMEM;
 
 		spin_lock_irq(lock);
 		ret = add_inbuf(vq, buf);
 		if (ret < 0) {
 			spin_unlock_irq(lock);
 			free_buf(buf, true);
-			break;
+			return ret;
 		}
 		nr_added_bufs++;
 		spin_unlock_irq(lock);
@@ -1362,7 +1362,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 	char debugfs_name[16];
 	struct port *port;
 	dev_t devt;
-	unsigned int nr_added_bufs;
 	int err;
 
 	port = kmalloc(sizeof(*port), GFP_KERNEL);
@@ -1421,11 +1420,13 @@ static int add_port(struct ports_device *portdev, u32 id)
 	spin_lock_init(&port->outvq_lock);
 	init_waitqueue_head(&port->waitqueue);
 
-	/* Fill the in_vq with buffers so the host can send us data. */
-	nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock);
-	if (!nr_added_bufs) {
+	/* We can safely ignore ENOSPC because it means
+	 * the queue already has buffers. Buffers are removed
+	 * only by virtcons_remove(), not by unplug_port()
+	 */
+	err = fill_queue(port->in_vq, &port->inbuf_lock);
+	if (err < 0 && err != -ENOSPC) {
 		dev_err(port->dev, "Error allocating inbufs\n");
-		err = -ENOMEM;
 		goto free_device;
 	}
 
@@ -2059,14 +2060,11 @@ static int virtcons_probe(struct virtio_device *vdev)
 	INIT_WORK(&portdev->control_work, &control_work_handler);
 
 	if (multiport) {
-		unsigned int nr_added_bufs;
-
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
 
-		nr_added_bufs = fill_queue(portdev->c_ivq,
-					   &portdev->c_ivq_lock);
-		if (!nr_added_bufs) {
+		err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock);
+		if (err < 0) {
 			dev_err(&vdev->dev,
 				"Error allocating buffers for control queue\n");
 			/*
@@ -2077,7 +2075,7 @@ static int virtcons_probe(struct virtio_device *vdev)
 					   VIRTIO_CONSOLE_DEVICE_READY, 0);
 			/* Device was functional: we need full cleanup. */
 			virtcons_remove(vdev);
-			return -ENOMEM;
+			return err;
 		}
 	} else {
 		/*
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index 87083b3a2769..37c22667e831 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -297,7 +297,10 @@ static int clk_main_probe_frequency(struct regmap *regmap)
 		regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
 		if (mcfr & AT91_PMC_MAINRDY)
 			return 0;
-		usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
+		if (system_state < SYSTEM_RUNNING)
+			udelay(MAINF_LOOP_MIN_WAIT);
+		else
+			usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
 	} while (time_before(prep_time, timeout));
 
 	return -ETIMEDOUT;
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 9790ddfa5b3c..86238d5ecb4d 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -43,6 +43,7 @@ static const struct clk_pll_characteristics upll_characteristics = {
 };
 
 static const struct clk_programmable_layout sam9x60_programmable_layout = {
+	.pres_mask = 0xff,
 	.pres_shift = 8,
 	.css_mask = 0x1f,
 	.have_slck_mck = 0,
diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c
index 9bfe9a28294a..fac0ca56d42d 100644
--- a/drivers/clk/at91/sckc.c
+++ b/drivers/clk/at91/sckc.c
@@ -76,7 +76,10 @@ static int clk_slow_osc_prepare(struct clk_hw *hw)
 
 	writel(tmp | osc->bits->cr_osc32en, sckcr);
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 
 	return 0;
 }
@@ -187,7 +190,10 @@ static int clk_slow_rc_osc_prepare(struct clk_hw *hw)
 
 	writel(readl(sckcr) | osc->bits->cr_rcen, sckcr);
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 
 	return 0;
 }
@@ -288,7 +294,10 @@ static int clk_sam9x5_slow_set_parent(struct clk_hw *hw, u8 index)
 
 	writel(tmp, sckcr);
 
-	usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(SLOWCK_SW_TIME_USEC);
+	else
+		usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1);
 
 	return 0;
 }
@@ -533,7 +542,10 @@ static int clk_sama5d4_slow_osc_prepare(struct clk_hw *hw)
 		return 0;
 	}
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 	osc->prepared = true;
 
 	return 0;
diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c
index 1c1bb39bb04e..b1318e6b655b 100644
--- a/drivers/clk/clk-ast2600.c
+++ b/drivers/clk/clk-ast2600.c
@@ -266,10 +266,11 @@ static int aspeed_g6_clk_enable(struct clk_hw *hw)
 
 	/* Enable clock */
 	if (gate->flags & CLK_GATE_SET_TO_DISABLE) {
-		regmap_write(gate->map, get_clock_reg(gate), clk);
-	} else {
-		/* Use set to clear register */
+		/* Clock is clear to enable, so use set to clear register */
 		regmap_write(gate->map, get_clock_reg(gate) + 0x04, clk);
+	} else {
+		/* Clock is set to enable, so use write to set register */
+		regmap_write(gate->map, get_clock_reg(gate), clk);
 	}
 
 	if (gate->reset_idx >= 0) {
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index 067ab876911d..172589e94f60 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -638,7 +638,7 @@ static int imx8mm_clocks_probe(struct platform_device *pdev)
 					   clks[IMX8MM_CLK_A53_DIV],
 					   clks[IMX8MM_CLK_A53_SRC],
 					   clks[IMX8MM_ARM_PLL_OUT],
-					   clks[IMX8MM_CLK_24M]);
+					   clks[IMX8MM_SYS_PLL1_800M]);
 
 	imx_check_clocks(clks, ARRAY_SIZE(clks));
 
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index 47a4b44ba3cb..58b5acee3830 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -610,7 +610,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev)
 					   clks[IMX8MN_CLK_A53_DIV],
 					   clks[IMX8MN_CLK_A53_SRC],
 					   clks[IMX8MN_ARM_PLL_OUT],
-					   clks[IMX8MN_CLK_24M]);
+					   clks[IMX8MN_SYS_PLL1_800M]);
 
 	imx_check_clocks(clks, ARRAY_SIZE(clks));
 
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index ea4c791f106d..b3af61cc6fb9 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -343,6 +343,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x3,
 		.shift = 0,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn0_sel",
@@ -353,8 +354,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = {
 			{ .hw = &g12a_fclk_div3.hw },
 		},
 		.num_parents = 3,
-		/* This sub-tree is used a parking clock */
-		.flags = CLK_SET_RATE_NO_REPARENT,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -410,6 +410,7 @@ static struct clk_regmap g12a_cpu_clk_postmux0 = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 2,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn0",
@@ -466,6 +467,7 @@ static struct clk_regmap g12a_cpu_clk_dyn = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 10,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn",
@@ -485,6 +487,7 @@ static struct clk_regmap g12a_cpu_clk = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
@@ -504,6 +507,7 @@ static struct clk_regmap g12b_cpu_clk = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
@@ -523,6 +527,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x3,
 		.shift = 0,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn0_sel",
@@ -533,6 +538,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = {
 			{ .hw = &g12a_fclk_div3.hw },
 		},
 		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -567,6 +573,7 @@ static struct clk_regmap g12b_cpub_clk_postmux0 = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 2,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn0",
@@ -644,6 +651,7 @@ static struct clk_regmap g12b_cpub_clk_dyn = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 10,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn",
@@ -663,6 +671,7 @@ static struct clk_regmap g12b_cpub_clk = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk",
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 7cfb998eeb3e..1f9c056e684c 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -935,6 +935,7 @@ static struct clk_regmap gxbb_sar_adc_clk_div = {
 			&gxbb_sar_adc_clk_sel.hw
 		},
 		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 7670cc596c74..31466cd1842f 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -165,12 +165,18 @@ static const unsigned long exynos5x_clk_regs[] __initconst = {
 	GATE_BUS_CPU,
 	GATE_SCLK_CPU,
 	CLKOUT_CMU_CPU,
+	CPLL_CON0,
+	DPLL_CON0,
 	EPLL_CON0,
 	EPLL_CON1,
 	EPLL_CON2,
 	RPLL_CON0,
 	RPLL_CON1,
 	RPLL_CON2,
+	IPLL_CON0,
+	SPLL_CON0,
+	VPLL_CON0,
+	MPLL_CON0,
 	SRC_TOP0,
 	SRC_TOP1,
 	SRC_TOP2,
@@ -1172,8 +1178,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {
 	GATE(CLK_SCLK_ISP_SENSOR2, "sclk_isp_sensor2", "dout_isp_sensor2",
 			GATE_TOP_SCLK_ISP, 12, CLK_SET_RATE_PARENT, 0),
 
-	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
-
 	/* CDREX */
 	GATE(CLK_CLKM_PHY0, "clkm_phy0", "dout_sclk_cdrex",
 			GATE_BUS_CDREX0, 0, 0, 0),
@@ -1248,6 +1252,15 @@ static struct exynos5_subcmu_reg_dump exynos5x_gsc_suspend_regs[] = {
 	{ DIV2_RATIO0, 0, 0x30 },	/* DIV dout_gscl_blk_300 */
 };
 
+static const struct samsung_gate_clock exynos5x_g3d_gate_clks[] __initconst = {
+	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
+};
+
+static struct exynos5_subcmu_reg_dump exynos5x_g3d_suspend_regs[] = {
+	{ GATE_IP_G3D, 0x3ff, 0x3ff },	/* G3D gates */
+	{ SRC_TOP5, 0, BIT(16) },	/* MUX mout_user_aclk_g3d */
+};
+
 static const struct samsung_div_clock exynos5x_mfc_div_clks[] __initconst = {
 	DIV(0, "dout_mfc_blk", "mout_user_aclk333", DIV4_RATIO, 0, 2),
 };
@@ -1320,6 +1333,14 @@ static const struct exynos5_subcmu_info exynos5x_gsc_subcmu = {
 	.pd_name	= "GSC",
 };
 
+static const struct exynos5_subcmu_info exynos5x_g3d_subcmu = {
+	.gate_clks	= exynos5x_g3d_gate_clks,
+	.nr_gate_clks	= ARRAY_SIZE(exynos5x_g3d_gate_clks),
+	.suspend_regs	= exynos5x_g3d_suspend_regs,
+	.nr_suspend_regs = ARRAY_SIZE(exynos5x_g3d_suspend_regs),
+	.pd_name	= "G3D",
+};
+
 static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = {
 	.div_clks	= exynos5x_mfc_div_clks,
 	.nr_div_clks	= ARRAY_SIZE(exynos5x_mfc_div_clks),
@@ -1351,6 +1372,7 @@ static const struct exynos5_subcmu_info exynos5800_mau_subcmu = {
 static const struct exynos5_subcmu_info *exynos5x_subcmus[] = {
 	&exynos5x_disp_subcmu,
 	&exynos5x_gsc_subcmu,
+	&exynos5x_g3d_subcmu,
 	&exynos5x_mfc_subcmu,
 	&exynos5x_mscl_subcmu,
 };
@@ -1358,6 +1380,7 @@ static const struct exynos5_subcmu_info *exynos5x_subcmus[] = {
 static const struct exynos5_subcmu_info *exynos5800_subcmus[] = {
 	&exynos5x_disp_subcmu,
 	&exynos5x_gsc_subcmu,
+	&exynos5x_g3d_subcmu,
 	&exynos5x_mfc_subcmu,
 	&exynos5x_mscl_subcmu,
 	&exynos5800_mau_subcmu,
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 7824c2ba3d8e..4b1aa9382ad2 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -13,6 +13,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/slab.h>
 
 #include <dt-bindings/clock/exynos5433.h>
 
@@ -5584,6 +5585,8 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev)
 
 	data->clk_save = samsung_clk_alloc_reg_dump(info->clk_regs,
 						    info->nr_clk_regs);
+	if (!data->clk_save)
+		return -ENOMEM;
 	data->nr_clk_save = info->nr_clk_regs;
 	data->clk_suspend = info->suspend_regs;
 	data->nr_clk_suspend = info->nr_suspend_regs;
@@ -5592,12 +5595,19 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev)
 	if (data->nr_pclks > 0) {
 		data->pclks = devm_kcalloc(dev, sizeof(struct clk *),
 					   data->nr_pclks, GFP_KERNEL);
-
+		if (!data->pclks) {
+			kfree(data->clk_save);
+			return -ENOMEM;
+		}
 		for (i = 0; i < data->nr_pclks; i++) {
 			struct clk *clk = of_clk_get(dev->of_node, i);
 
-			if (IS_ERR(clk))
+			if (IS_ERR(clk)) {
+				kfree(data->clk_save);
+				while (--i >= 0)
+					clk_put(data->pclks[i]);
 				return PTR_ERR(clk);
+			}
 			data->pclks[i] = clk;
 		}
 	}
diff --git a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
index dcac1391767f..ef29582676f6 100644
--- a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
+++ b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
@@ -1224,7 +1224,7 @@ static int sun9i_a80_ccu_probe(struct platform_device *pdev)
 
 	/* Enforce d1 = 0, d2 = 0 for Audio PLL */
 	val = readl(reg + SUN9I_A80_PLL_AUDIO_REG);
-	val &= (BIT(16) & BIT(18));
+	val &= ~(BIT(16) | BIT(18));
 	writel(val, reg + SUN9I_A80_PLL_AUDIO_REG);
 
 	/* Enforce P = 1 for both CPU cluster PLLs */
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index d3a43381a792..27201fd26e44 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -1080,8 +1080,8 @@ static struct clk ** __init sunxi_divs_clk_setup(struct device_node *node,
 						 rate_hw, rate_ops,
 						 gate_hw, &clk_gate_ops,
 						 clkflags |
-						 data->div[i].critical ?
-							CLK_IS_CRITICAL : 0);
+						 (data->div[i].critical ?
+							CLK_IS_CRITICAL : 0));
 
 		WARN_ON(IS_ERR(clk_data->clks[i]));
 	}
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index a01ca9395179..f65e16c4f3c4 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -174,7 +174,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node)
 	struct clk_init_data init = { NULL };
 	const char **parent_names = NULL;
 	struct clk *clk;
-	int ret;
 
 	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
 	if (!clk_hw) {
@@ -207,11 +206,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node)
 	clk = ti_clk_register(NULL, &clk_hw->hw, node->name);
 
 	if (!IS_ERR(clk)) {
-		ret = ti_clk_add_alias(NULL, clk, node->name);
-		if (ret) {
-			clk_unregister(clk);
-			goto cleanup;
-		}
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		kfree(parent_names);
 		return;
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 975995eea15c..b0c0690a5a12 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -100,11 +100,12 @@ static bool _omap4_is_timeout(union omap4_timeout *time, u32 timeout)
 	 * can be from a timer that requires pm_runtime access, which
 	 * will eventually bring us here with timekeeping_suspended,
 	 * during both suspend entry and resume paths. This happens
-	 * at least on am43xx platform.
+	 * at least on am43xx platform. Account for flakeyness
+	 * with udelay() by multiplying the timeout value by 2.
 	 */
 	if (unlikely(_early_timeout || timekeeping_suspended)) {
 		if (time->cycles++ < timeout) {
-			udelay(1);
+			udelay(1 * 2);
 			return false;
 		}
 	} else {
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index 354b27d14a19..62812f80b5cc 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name)
 	return 0;
 }
 
+static const unsigned int sh_mtu2_channel_offsets[] = {
+	0x300, 0x380, 0x000,
+};
+
 static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 				 struct sh_mtu2_device *mtu)
 {
-	static const unsigned int channel_offsets[] = {
-		0x300, 0x380, 0x000,
-	};
 	char name[6];
 	int irq;
 	int ret;
@@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 		return ret;
 	}
 
-	ch->base = mtu->mapbase + channel_offsets[index];
+	ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index];
 	ch->index = index;
 
 	return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev));
@@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu,
 	}
 
 	/* Allocate and setup the channels. */
-	mtu->num_channels = 3;
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_unmap;
+
+	mtu->num_channels = min_t(unsigned int, ret,
+				  ARRAY_SIZE(sh_mtu2_channel_offsets));
 
 	mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels),
 				GFP_KERNEL);
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index a562f491b0f8..9318edcd8963 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -268,15 +268,12 @@ static int __init mtk_syst_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
 					TIMER_SYNC_TICKS, 0xffffffff);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 
 static int __init mtk_gpt_init(struct device_node *node)
@@ -293,7 +290,7 @@ static int __init mtk_gpt_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	/* Configure clock source */
 	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
@@ -311,9 +308,6 @@ static int __init mtk_gpt_init(struct device_node *node)
 	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
 TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c52d6fa32aac..48a224a6b178 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -720,7 +720,7 @@ static ssize_t store_##file_name					\
 	if (ret != 1)							\
 		return -EINVAL;						\
 									\
-	ret = dev_pm_qos_update_request(policy->object##_freq_req, val);\
+	ret = freq_qos_update_request(policy->object##_freq_req, val);\
 	return ret >= 0 ? count : ret;					\
 }
 
@@ -1202,19 +1202,21 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 		goto err_free_real_cpus;
 	}
 
+	freq_constraints_init(&policy->constraints);
+
 	policy->nb_min.notifier_call = cpufreq_notifier_min;
 	policy->nb_max.notifier_call = cpufreq_notifier_max;
 
-	ret = dev_pm_qos_add_notifier(dev, &policy->nb_min,
-				      DEV_PM_QOS_MIN_FREQUENCY);
+	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MIN,
+				    &policy->nb_min);
 	if (ret) {
 		dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n",
 			ret, cpumask_pr_args(policy->cpus));
 		goto err_kobj_remove;
 	}
 
-	ret = dev_pm_qos_add_notifier(dev, &policy->nb_max,
-				      DEV_PM_QOS_MAX_FREQUENCY);
+	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MAX,
+				    &policy->nb_max);
 	if (ret) {
 		dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n",
 			ret, cpumask_pr_args(policy->cpus));
@@ -1232,8 +1234,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	return policy;
 
 err_min_qos_notifier:
-	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
-				   DEV_PM_QOS_MIN_FREQUENCY);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN,
+				 &policy->nb_min);
 err_kobj_remove:
 	cpufreq_policy_put_kobj(policy);
 err_free_real_cpus:
@@ -1250,7 +1252,6 @@ err_free_policy:
 
 static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
-	struct device *dev = get_cpu_device(policy->cpu);
 	unsigned long flags;
 	int cpu;
 
@@ -1262,10 +1263,13 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	dev_pm_qos_remove_notifier(dev, &policy->nb_max,
-				   DEV_PM_QOS_MAX_FREQUENCY);
-	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
-				   DEV_PM_QOS_MIN_FREQUENCY);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MAX,
+				 &policy->nb_max);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN,
+				 &policy->nb_min);
+
+	/* Cancel any pending policy->update work before freeing the policy. */
+	cancel_work_sync(&policy->update);
 
 	if (policy->max_freq_req) {
 		/*
@@ -1274,10 +1278,10 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		 */
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 					     CPUFREQ_REMOVE_POLICY, policy);
-		dev_pm_qos_remove_request(policy->max_freq_req);
+		freq_qos_remove_request(policy->max_freq_req);
 	}
 
-	dev_pm_qos_remove_request(policy->min_freq_req);
+	freq_qos_remove_request(policy->min_freq_req);
 	kfree(policy->min_freq_req);
 
 	cpufreq_policy_put_kobj(policy);
@@ -1357,8 +1361,6 @@ static int cpufreq_online(unsigned int cpu)
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
 	if (new_policy) {
-		struct device *dev = get_cpu_device(cpu);
-
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
 			add_cpu_dev_symlink(policy, j);
@@ -1369,36 +1371,31 @@ static int cpufreq_online(unsigned int cpu)
 		if (!policy->min_freq_req)
 			goto out_destroy_policy;
 
-		ret = dev_pm_qos_add_request(dev, policy->min_freq_req,
-					     DEV_PM_QOS_MIN_FREQUENCY,
-					     policy->min);
+		ret = freq_qos_add_request(&policy->constraints,
+					   policy->min_freq_req, FREQ_QOS_MIN,
+					   policy->min);
 		if (ret < 0) {
 			/*
-			 * So we don't call dev_pm_qos_remove_request() for an
+			 * So we don't call freq_qos_remove_request() for an
 			 * uninitialized request.
 			 */
 			kfree(policy->min_freq_req);
 			policy->min_freq_req = NULL;
-
-			dev_err(dev, "Failed to add min-freq constraint (%d)\n",
-				ret);
 			goto out_destroy_policy;
 		}
 
 		/*
 		 * This must be initialized right here to avoid calling
-		 * dev_pm_qos_remove_request() on uninitialized request in case
+		 * freq_qos_remove_request() on uninitialized request in case
 		 * of errors.
 		 */
 		policy->max_freq_req = policy->min_freq_req + 1;
 
-		ret = dev_pm_qos_add_request(dev, policy->max_freq_req,
-					     DEV_PM_QOS_MAX_FREQUENCY,
-					     policy->max);
+		ret = freq_qos_add_request(&policy->constraints,
+					   policy->max_freq_req, FREQ_QOS_MAX,
+					   policy->max);
 		if (ret < 0) {
 			policy->max_freq_req = NULL;
-			dev_err(dev, "Failed to add max-freq constraint (%d)\n",
-				ret);
 			goto out_destroy_policy;
 		}
 
@@ -2374,7 +2371,6 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
-	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	int ret;
 
 	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
@@ -2386,8 +2382,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	 * PM QoS framework collects all the requests from users and provide us
 	 * the final aggregated value here.
 	 */
-	new_policy->min = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MIN_FREQUENCY);
-	new_policy->max = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MAX_FREQUENCY);
+	new_policy->min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN);
+	new_policy->max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX);
 
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(new_policy);
@@ -2518,7 +2514,7 @@ static int cpufreq_boost_set_sw(int state)
 			break;
 		}
 
-		ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max);
+		ret = freq_qos_update_request(policy->max_freq_req, policy->max);
 		if (ret < 0)
 			break;
 	}
@@ -2737,14 +2733,6 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 }
 EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
 
-/*
- * Stop cpufreq at shutdown to make sure it isn't holding any locks
- * or mutexes when secondary CPUs are halted.
- */
-static struct syscore_ops cpufreq_syscore_ops = {
-	.shutdown = cpufreq_suspend,
-};
-
 struct kobject *cpufreq_global_kobject;
 EXPORT_SYMBOL(cpufreq_global_kobject);
 
@@ -2756,8 +2744,6 @@ static int __init cpufreq_core_init(void)
 	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
 	BUG_ON(!cpufreq_global_kobject);
 
-	register_syscore_ops(&cpufreq_syscore_ops);
-
 	return 0;
 }
 module_param(off, int, 0444);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9f02de9a1b47..8ab31702cf6a 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -847,11 +847,9 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	value |= HWP_MAX_PERF(min_perf);
 	value |= HWP_MIN_PERF(min_perf);
 
-	/* Set EPP/EPB to min */
+	/* Set EPP to min */
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
-	else
-		intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE);
 
 	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
@@ -1088,10 +1086,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 
 static struct cpufreq_driver intel_pstate;
 
-static void update_qos_request(enum dev_pm_qos_req_type type)
+static void update_qos_request(enum freq_qos_req_type type)
 {
 	int max_state, turbo_max, freq, i, perf_pct;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	struct cpufreq_policy *policy;
 
 	for_each_possible_cpu(i) {
@@ -1112,7 +1110,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type)
 		else
 			turbo_max = cpu->pstate.turbo_pstate;
 
-		if (type == DEV_PM_QOS_MIN_FREQUENCY) {
+		if (type == FREQ_QOS_MIN) {
 			perf_pct = global.min_perf_pct;
 		} else {
 			req++;
@@ -1122,7 +1120,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type)
 		freq = DIV_ROUND_UP(turbo_max * perf_pct, 100);
 		freq *= cpu->pstate.scaling;
 
-		if (dev_pm_qos_update_request(req, freq) < 0)
+		if (freq_qos_update_request(req, freq) < 0)
 			pr_warn("Failed to update freq constraint: CPU%d\n", i);
 	}
 }
@@ -1153,7 +1151,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 	if (intel_pstate_driver == &intel_pstate)
 		intel_pstate_update_policies();
 	else
-		update_qos_request(DEV_PM_QOS_MAX_FREQUENCY);
+		update_qos_request(FREQ_QOS_MAX);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -1187,7 +1185,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 	if (intel_pstate_driver == &intel_pstate)
 		intel_pstate_update_policies();
 	else
-		update_qos_request(DEV_PM_QOS_MIN_FREQUENCY);
+		update_qos_request(FREQ_QOS_MIN);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -2381,7 +2379,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	int max_state, turbo_max, min_freq, max_freq, ret;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	struct cpudata *cpu;
 	struct device *dev;
 
@@ -2416,15 +2414,15 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
 	max_freq *= cpu->pstate.scaling;
 
-	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_MIN_FREQUENCY,
-				     min_freq);
+	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN,
+				   min_freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
 		goto free_req;
 	}
 
-	ret = dev_pm_qos_add_request(dev, req + 1, DEV_PM_QOS_MAX_FREQUENCY,
-				     max_freq);
+	ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX,
+				   max_freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
 		goto remove_min_req;
@@ -2435,7 +2433,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return 0;
 
 remove_min_req:
-	dev_pm_qos_remove_request(req);
+	freq_qos_remove_request(req);
 free_req:
 	kfree(req);
 pstate_exit:
@@ -2446,12 +2444,12 @@ pstate_exit:
 
 static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 
 	req = policy->driver_data;
 
-	dev_pm_qos_remove_request(req + 1);
-	dev_pm_qos_remove_request(req);
+	freq_qos_remove_request(req + 1);
+	freq_qos_remove_request(req);
 	kfree(req);
 
 	return intel_pstate_cpu_exit(policy);
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index bc9dd30395c4..037fe23bc6ed 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi);
 static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
 {
 	struct cpufreq_policy *policy;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	u8 node, slow_mode;
 	int cpu, ret;
 
@@ -86,7 +86,7 @@ static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
 
 	req = policy->driver_data;
 
-	ret = dev_pm_qos_update_request(req,
+	ret = freq_qos_update_request(req,
 			policy->freq_table[slow_mode].frequency);
 	if (ret < 0)
 		pr_warn("Failed to update freq constraint: %d\n", ret);
@@ -103,7 +103,7 @@ static struct pmi_handler cbe_pmi_handler = {
 
 void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	int ret;
 
 	if (!cbe_cpufreq_has_pmi)
@@ -113,9 +113,8 @@ void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy)
 	if (!req)
 		return;
 
-	ret = dev_pm_qos_add_request(get_cpu_device(policy->cpu), req,
-				     DEV_PM_QOS_MAX_FREQUENCY,
-				     policy->freq_table[0].frequency);
+	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MAX,
+				   policy->freq_table[0].frequency);
 	if (ret < 0) {
 		pr_err("Failed to add freq constraint (%d)\n", ret);
 		kfree(req);
@@ -128,10 +127,10 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_policy_init);
 
 void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req = policy->driver_data;
+	struct freq_qos_request *req = policy->driver_data;
 
 	if (cbe_cpufreq_has_pmi) {
-		dev_pm_qos_remove_request(req);
+		freq_qos_remove_request(req);
 		kfree(req);
 	}
 }
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index 932390b028f1..b0ce9bc78113 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -95,6 +95,10 @@ static int __init haltpoll_init(void)
 	int ret;
 	struct cpuidle_driver *drv = &haltpoll_driver;
 
+	/* Do not load haltpoll if idle= is passed */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return -ENODEV;
+
 	cpuidle_poll_state_init(drv);
 
 	if (!kvm_para_available() ||
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 774d991d7cca..aca75237bbcf 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1297,7 +1297,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt)
 	tp->write_seq = snd_isn;
 	tp->snd_nxt = snd_isn;
 	tp->snd_una = snd_isn;
-	inet_sk(sk)->inet_id = tp->write_seq ^ jiffies;
+	inet_sk(sk)->inet_id = prandom_u32();
 	assign_rxopt(sk, opt);
 
 	if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10))
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 0891ab829b1b..98bc5a4cd5e7 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1702,7 +1702,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return peekmsg(sk, msg, len, nonblock, flags);
 
 	if (sk_can_busy_loop(sk) &&
-	    skb_queue_empty(&sk->sk_receive_queue) &&
+	    skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    sk->sk_state == TCP_ESTABLISHED)
 		sk_busy_loop(sk, nonblock);
 
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 42a8f3f11681..709002515550 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -471,7 +471,7 @@ unlock:
 	if (pfence_excl)
 		*pfence_excl = fence_excl;
 	else if (fence_excl)
-		shared[++shared_count] = fence_excl;
+		shared[shared_count++] = fence_excl;
 
 	if (!shared_count) {
 		kfree(shared);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 9ba74ab7e912..c27e206a764c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1707,6 +1707,14 @@ static void sdma_add_scripts(struct sdma_engine *sdma,
 	if (!sdma->script_number)
 		sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1;
 
+	if (sdma->script_number > sizeof(struct sdma_script_start_addrs)
+				  / sizeof(s32)) {
+		dev_err(sdma->dev,
+			"SDMA script number %d not match with firmware.\n",
+			sdma->script_number);
+		return;
+	}
+
 	for (i = 0; i < sdma->script_number; i++)
 		if (addr_arr[i] > 0)
 			saddr_arr[i] = addr_arr[i];
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 8e90a405939d..ef73f65224b1 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -694,6 +694,25 @@ static int bam_dma_terminate_all(struct dma_chan *chan)
 
 	/* remove all transactions, including active transaction */
 	spin_lock_irqsave(&bchan->vc.lock, flag);
+	/*
+	 * If we have transactions queued, then some might be committed to the
+	 * hardware in the desc fifo.  The only way to reset the desc fifo is
+	 * to do a hardware reset (either by pipe or the entire block).
+	 * bam_chan_init_hw() will trigger a pipe reset, and also reinit the
+	 * pipe.  If the pipe is left disabled (default state after pipe reset)
+	 * and is accessed by a connected hardware engine, a fatal error in
+	 * the BAM will occur.  There is a small window where this could happen
+	 * with bam_chan_init_hw(), but it is assumed that the caller has
+	 * stopped activity on any attached hardware engine.  Make sure to do
+	 * this first so that the BAM hardware doesn't cause memory corruption
+	 * by accessing freed resources.
+	 */
+	if (!list_empty(&bchan->desc_list)) {
+		async_desc = list_first_entry(&bchan->desc_list,
+					      struct bam_async_desc, desc_node);
+		bam_chan_init_hw(bchan, async_desc->dir);
+	}
+
 	list_for_each_entry_safe(async_desc, tmp,
 				 &bchan->desc_list, desc_node) {
 		list_add(&async_desc->vd.node, &bchan->vc.desc_issued);
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 525dc7338fe3..8546ad034720 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -134,6 +134,10 @@
 #define SPRD_DMA_SRC_TRSF_STEP_OFFSET	0
 #define SPRD_DMA_TRSF_STEP_MASK		GENMASK(15, 0)
 
+/* SPRD DMA_SRC_BLK_STEP register definition */
+#define SPRD_DMA_LLIST_HIGH_MASK	GENMASK(31, 28)
+#define SPRD_DMA_LLIST_HIGH_SHIFT	28
+
 /* define DMA channel mode & trigger mode mask */
 #define SPRD_DMA_CHN_MODE_MASK		GENMASK(7, 0)
 #define SPRD_DMA_TRG_MODE_MASK		GENMASK(7, 0)
@@ -208,6 +212,7 @@ struct sprd_dma_dev {
 	struct sprd_dma_chn	channels[0];
 };
 
+static void sprd_dma_free_desc(struct virt_dma_desc *vd);
 static bool sprd_dma_filter_fn(struct dma_chan *chan, void *param);
 static struct of_dma_filter_info sprd_dma_info = {
 	.filter_fn = sprd_dma_filter_fn,
@@ -609,12 +614,19 @@ static int sprd_dma_alloc_chan_resources(struct dma_chan *chan)
 static void sprd_dma_free_chan_resources(struct dma_chan *chan)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	struct virt_dma_desc *cur_vd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&schan->vc.lock, flags);
+	if (schan->cur_desc)
+		cur_vd = &schan->cur_desc->vd;
+
 	sprd_dma_stop(schan);
 	spin_unlock_irqrestore(&schan->vc.lock, flags);
 
+	if (cur_vd)
+		sprd_dma_free_desc(cur_vd);
+
 	vchan_free_chan_resources(&schan->vc);
 	pm_runtime_put(chan->device->dev);
 }
@@ -717,6 +729,7 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 	u32 int_mode = flags & SPRD_DMA_INT_MASK;
 	int src_datawidth, dst_datawidth, src_step, dst_step;
 	u32 temp, fix_mode = 0, fix_en = 0;
+	phys_addr_t llist_ptr;
 
 	if (dir == DMA_MEM_TO_DEV) {
 		src_step = sprd_dma_get_step(slave_cfg->src_addr_width);
@@ -814,13 +827,16 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 		 * Set the link-list pointer point to next link-list
 		 * configuration's physical address.
 		 */
-		hw->llist_ptr = schan->linklist.phy_addr + temp;
+		llist_ptr = schan->linklist.phy_addr + temp;
+		hw->llist_ptr = lower_32_bits(llist_ptr);
+		hw->src_blk_step = (upper_32_bits(llist_ptr) << SPRD_DMA_LLIST_HIGH_SHIFT) &
+			SPRD_DMA_LLIST_HIGH_MASK;
 	} else {
 		hw->llist_ptr = 0;
+		hw->src_blk_step = 0;
 	}
 
 	hw->frg_step = 0;
-	hw->src_blk_step = 0;
 	hw->des_blk_step = 0;
 	return 0;
 }
@@ -1023,15 +1039,22 @@ static int sprd_dma_resume(struct dma_chan *chan)
 static int sprd_dma_terminate_all(struct dma_chan *chan)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	struct virt_dma_desc *cur_vd = NULL;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&schan->vc.lock, flags);
+	if (schan->cur_desc)
+		cur_vd = &schan->cur_desc->vd;
+
 	sprd_dma_stop(schan);
 
 	vchan_get_all_descriptors(&schan->vc, &head);
 	spin_unlock_irqrestore(&schan->vc.lock, flags);
 
+	if (cur_vd)
+		sprd_dma_free_desc(cur_vd);
+
 	vchan_dma_desc_free_list(&schan->vc, &head);
 	return 0;
 }
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 5f8adf5c1f20..6e1268552f74 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -40,6 +40,7 @@
 #define ADMA_CH_CONFIG_MAX_BURST_SIZE                   16
 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val)		((val) & 0xf)
 #define ADMA_CH_CONFIG_MAX_BUFS				8
+#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
 
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0xf) << 8)
@@ -77,6 +78,7 @@ struct tegra_adma;
  * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
  * @ch_req_rx_shift: Register offset for AHUB receive channel select.
  * @ch_base_offset: Register offset of DMA channel registers.
+ * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  * @ch_fifo_ctrl: Default value for channel FIFO CTRL register.
  * @ch_req_mask: Mask for Tx or Rx channel select.
  * @ch_req_max: Maximum number of Tx or Rx channels available.
@@ -95,6 +97,7 @@ struct tegra_adma_chip_data {
 	unsigned int ch_req_max;
 	unsigned int ch_reg_size;
 	unsigned int nr_channels;
+	bool has_outstanding_reqs;
 };
 
 /*
@@ -594,6 +597,8 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 			 ADMA_CH_CTRL_FLOWCTRL_EN;
 	ch_regs->config |= cdata->adma_get_burst_config(burst_size);
 	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
+	if (cdata->has_outstanding_reqs)
+		ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8);
 	ch_regs->fifo_ctrl = cdata->ch_fifo_ctrl;
 	ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK;
 
@@ -778,6 +783,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.ch_req_tx_shift	= 28,
 	.ch_req_rx_shift	= 24,
 	.ch_base_offset		= 0,
+	.has_outstanding_reqs	= false,
 	.ch_fifo_ctrl		= TEGRA210_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0xf,
 	.ch_req_max		= 10,
@@ -792,6 +798,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.ch_req_tx_shift	= 27,
 	.ch_req_rx_shift	= 22,
 	.ch_base_offset		= 0x10000,
+	.has_outstanding_reqs	= true,
 	.ch_fifo_ctrl		= TEGRA186_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0x1f,
 	.ch_req_max		= 20,
diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c
index 2f946f55076c..8c2f7ebe998c 100644
--- a/drivers/dma/ti/cppi41.c
+++ b/drivers/dma/ti/cppi41.c
@@ -586,9 +586,22 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
 	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
 {
 	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct dma_async_tx_descriptor *txd = NULL;
+	struct cppi41_dd *cdd = c->cdd;
 	struct cppi41_desc *d;
 	struct scatterlist *sg;
 	unsigned int i;
+	int error;
+
+	error = pm_runtime_get(cdd->ddev.dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
+		return NULL;
+	}
+
+	if (cdd->is_suspended)
+		goto err_out_not_ready;
 
 	d = c->desc;
 	for_each_sg(sgl, sg, sg_len, i) {
@@ -611,7 +624,13 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
 		d++;
 	}
 
-	return &c->txd;
+	txd = &c->txd;
+
+err_out_not_ready:
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+
+	return txd;
 }
 
 static void cppi41_compute_td_desc(struct cppi41_desc *d)
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index e7dc3c4dc8e0..5d56f1e4d332 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -68,6 +68,9 @@
 #define XILINX_DMA_DMACR_CIRC_EN		BIT(1)
 #define XILINX_DMA_DMACR_RUNSTOP		BIT(0)
 #define XILINX_DMA_DMACR_FSYNCSRC_MASK		GENMASK(6, 5)
+#define XILINX_DMA_DMACR_DELAY_MASK		GENMASK(31, 24)
+#define XILINX_DMA_DMACR_FRAME_COUNT_MASK	GENMASK(23, 16)
+#define XILINX_DMA_DMACR_MASTER_MASK		GENMASK(11, 8)
 
 #define XILINX_DMA_REG_DMASR			0x0004
 #define XILINX_DMA_DMASR_EOL_LATE_ERR		BIT(15)
@@ -1354,7 +1357,8 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 					   node);
 		hw = &segment->hw;
 
-		xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR, hw->buf_addr);
+		xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR,
+			     xilinx_prep_dma_addr_t(hw->buf_addr));
 
 		/* Start the transfer */
 		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
@@ -2117,8 +2121,10 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 	chan->config.gen_lock = cfg->gen_lock;
 	chan->config.master = cfg->master;
 
+	dmacr &= ~XILINX_DMA_DMACR_GENLOCK_EN;
 	if (cfg->gen_lock && chan->genlock) {
 		dmacr |= XILINX_DMA_DMACR_GENLOCK_EN;
+		dmacr &= ~XILINX_DMA_DMACR_MASTER_MASK;
 		dmacr |= cfg->master << XILINX_DMA_DMACR_MASTER_SHIFT;
 	}
 
@@ -2134,11 +2140,13 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 	chan->config.delay = cfg->delay;
 
 	if (cfg->coalesc <= XILINX_DMA_DMACR_FRAME_COUNT_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_FRAME_COUNT_MASK;
 		dmacr |= cfg->coalesc << XILINX_DMA_DMACR_FRAME_COUNT_SHIFT;
 		chan->config.coalesc = cfg->coalesc;
 	}
 
 	if (cfg->delay <= XILINX_DMA_DMACR_DELAY_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_DELAY_MASK;
 		dmacr |= cfg->delay << XILINX_DMA_DMACR_DELAY_SHIFT;
 		chan->config.delay = cfg->delay;
 	}
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index d413a0bdc9ad..0bb62857ffb2 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -553,7 +553,11 @@ void ghes_edac_unregister(struct ghes *ghes)
 	if (!ghes_pvt)
 		return;
 
+	if (atomic_dec_return(&ghes_init))
+		return;
+
 	mci = ghes_pvt->mci;
+	ghes_pvt = NULL;
 	edac_mc_del_mc(mci->pdev);
 	edac_mc_free(mci);
 }
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 9cd70d1a5622..a479023fa036 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev)
 	if (np) {
 		if (of_property_read_string(np, "method", &method)) {
 			pr_warn("missing \"method\" property\n");
-			return CONDUIT_INVALID;
+			return SMCCC_CONDUIT_NONE;
 		}
 
 		if (!strcmp("hvc", method)) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else if (!strcmp("smc", method)) {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 
 		pr_warn("invalid \"method\" property: %s\n", method);
 	} else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) {
 		if (acpi_psci_use_hvc()) {
 			sdei_firmware_call = &sdei_smccc_hvc;
-			return CONDUIT_HVC;
+			return SMCCC_CONDUIT_HVC;
 		} else {
 			sdei_firmware_call = &sdei_smccc_smc;
-			return CONDUIT_SMC;
+			return SMCCC_CONDUIT_SMC;
 		}
 	}
 
-	return CONDUIT_INVALID;
+	return SMCCC_CONDUIT_NONE;
 }
 
 static int sdei_probe(struct platform_device *pdev)
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 35ed56b9c34f..1e21fc3e9851 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -408,7 +408,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v)
 		bytes = ~0ull;
 	else if (size & 0x8000)
 		bytes = (u64)(size & 0x7fff) << 10;
-	else if (size != 0x7fff)
+	else if (size != 0x7fff || dm->length < 0x20)
 		bytes = (u64)size << 20;
 	else
 		bytes = (u64)get_unaligned((u32 *)&d[0x1C]) << 20;
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 178ee8106828..b248870a9806 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -182,6 +182,7 @@ config RESET_ATTACK_MITIGATION
 
 config EFI_RCI2_TABLE
 	bool "EFI Runtime Configuration Interface Table Version 2 Support"
+	depends on X86 || COMPILE_TEST
 	help
 	  Displays the content of the Runtime Configuration Interface
 	  Table version 2 on Dell EMC PowerEdge systems as a binary
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 69f00f7453a3..e98bbf8e56d9 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -554,7 +554,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 					      sizeof(*seed) + size);
 			if (seed != NULL) {
 				pr_notice("seeding entropy pool\n");
-				add_device_randomness(seed->bits, seed->size);
+				add_bootloader_randomness(seed->bits, seed->size);
 				early_memunmap(seed, sizeof(*seed) + size);
 			} else {
 				pr_err("Could not map UEFI random seed!\n");
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 0460c7581220..ee0661ddb25b 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -52,6 +52,7 @@ lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o random.o \
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= arm64-stub.o
+CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 #
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index e8f7aefb6813..41213bf5fcf5 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -195,6 +195,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long dram_base,
 				 efi_loaded_image_t *image)
 {
+	unsigned long kernel_base;
 	efi_status_t status;
 
 	/*
@@ -204,9 +205,18 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	 * loaded. These assumptions are made by the decompressor,
 	 * before any memory map is available.
 	 */
-	dram_base = round_up(dram_base, SZ_128M);
+	kernel_base = round_up(dram_base, SZ_128M);
 
-	status = reserve_kernel_base(sys_table, dram_base, reserve_addr,
+	/*
+	 * Note that some platforms (notably, the Raspberry Pi 2) put
+	 * spin-tables and other pieces of firmware at the base of RAM,
+	 * abusing the fact that the window of TEXT_OFFSET bytes at the
+	 * base of the kernel image is only partially used at the moment.
+	 * (Up to 5 pages are used for the swapper page tables)
+	 */
+	kernel_base += TEXT_OFFSET - 5 * PAGE_SIZE;
+
+	status = reserve_kernel_base(sys_table, kernel_base, reserve_addr,
 				     reserve_size);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n");
@@ -220,7 +230,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	*image_size = image->image_size;
 	status = efi_relocate_kernel(sys_table, image_addr, *image_size,
 				     *image_size,
-				     dram_base + MAX_UNCOMP_KERNEL_SIZE, 0);
+				     kernel_base + MAX_UNCOMP_KERNEL_SIZE, 0, 0);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table, "Failed to relocate kernel.\n");
 		efi_free(sys_table, *reserve_size, *reserve_addr);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 3caae7f2cf56..35dbc2791c97 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -260,11 +260,11 @@ fail:
 }
 
 /*
- * Allocate at the lowest possible address.
+ * Allocate at the lowest possible address that is not below 'min'.
  */
-efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
-			   unsigned long size, unsigned long align,
-			   unsigned long *addr)
+efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg,
+				 unsigned long size, unsigned long align,
+				 unsigned long *addr, unsigned long min)
 {
 	unsigned long map_size, desc_size, buff_size;
 	efi_memory_desc_t *map;
@@ -311,13 +311,8 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 		start = desc->phys_addr;
 		end = start + desc->num_pages * EFI_PAGE_SIZE;
 
-		/*
-		 * Don't allocate at 0x0. It will confuse code that
-		 * checks pointers against NULL. Skip the first 8
-		 * bytes so we start at a nice even number.
-		 */
-		if (start == 0x0)
-			start += 8;
+		if (start < min)
+			start = min;
 
 		start = round_up(start, align);
 		if ((start + size) > end)
@@ -698,7 +693,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 				 unsigned long image_size,
 				 unsigned long alloc_size,
 				 unsigned long preferred_addr,
-				 unsigned long alignment)
+				 unsigned long alignment,
+				 unsigned long min_addr)
 {
 	unsigned long cur_image_addr;
 	unsigned long new_addr = 0;
@@ -731,8 +727,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 	 * possible.
 	 */
 	if (status != EFI_SUCCESS) {
-		status = efi_low_alloc(sys_table_arg, alloc_size, alignment,
-				       &new_addr);
+		status = efi_low_alloc_above(sys_table_arg, alloc_size,
+					     alignment, &new_addr, min_addr);
 	}
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n");
diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c
index 877745c3aaf2..7baf48c01e72 100644
--- a/drivers/firmware/efi/test/efi_test.c
+++ b/drivers/firmware/efi/test/efi_test.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/efi.h>
+#include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
@@ -717,6 +718,13 @@ static long efi_test_ioctl(struct file *file, unsigned int cmd,
 
 static int efi_test_open(struct inode *inode, struct file *file)
 {
+	int ret = security_locked_down(LOCKDOWN_EFI_TEST);
+
+	if (ret)
+		return ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
 	/*
 	 * nothing special to do here
 	 * We do accept multiple open files at the same time as we
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index ebd7977653a8..31f9f0e369b9 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -88,6 +88,7 @@ int __init efi_tpm_eventlog_init(void)
 
 	if (tbl_size < 0) {
 		pr_err(FW_BUG "Failed to parse event in TPM Final Events Log\n");
+		ret = -EINVAL;
 		goto out_calc;
 	}
 
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 84f4ff351c62..b3b6c15e7b36 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -53,10 +53,18 @@ bool psci_tos_resident_on(int cpu)
 }
 
 struct psci_operations psci_ops = {
-	.conduit = PSCI_CONDUIT_NONE,
+	.conduit = SMCCC_CONDUIT_NONE,
 	.smccc_version = SMCCC_VERSION_1_0,
 };
 
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
+{
+	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+		return SMCCC_CONDUIT_NONE;
+
+	return psci_ops.conduit;
+}
+
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
@@ -212,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void)
 			      0, 0, 0);
 }
 
-static void set_conduit(enum psci_conduit conduit)
+static void set_conduit(enum arm_smccc_conduit conduit)
 {
 	switch (conduit) {
-	case PSCI_CONDUIT_HVC:
+	case SMCCC_CONDUIT_HVC:
 		invoke_psci_fn = __invoke_psci_fn_hvc;
 		break;
-	case PSCI_CONDUIT_SMC:
+	case SMCCC_CONDUIT_SMC:
 		invoke_psci_fn = __invoke_psci_fn_smc;
 		break;
 	default:
@@ -240,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np)
 	}
 
 	if (!strcmp("hvc", method)) {
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	} else if (!strcmp("smc", method)) {
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 	} else {
 		pr_warn("invalid \"method\" property: %s\n", method);
 		return -EINVAL;
@@ -583,9 +591,9 @@ int __init psci_acpi_init(void)
 	pr_info("probing for conduit method from ACPI.\n");
 
 	if (acpi_psci_use_hvc())
-		set_conduit(PSCI_CONDUIT_HVC);
+		set_conduit(SMCCC_CONDUIT_HVC);
 	else
-		set_conduit(PSCI_CONDUIT_SMC);
+		set_conduit(SMCCC_CONDUIT_SMC);
 
 	return psci_probe();
 }
diff --git a/drivers/gpio/gpio-bd70528.c b/drivers/gpio/gpio-bd70528.c
index 0c1ead12d883..4ba4d4a67881 100644
--- a/drivers/gpio/gpio-bd70528.c
+++ b/drivers/gpio/gpio-bd70528.c
@@ -25,13 +25,13 @@ static int bd70528_set_debounce(struct bd70528_gpio *bdgpio,
 	case 0:
 		val = BD70528_DEBOUNCE_DISABLE;
 		break;
-	case 1 ... 15:
+	case 1 ... 15000:
 		val = BD70528_DEBOUNCE_15MS;
 		break;
-	case 16 ... 30:
+	case 15001 ... 30000:
 		val = BD70528_DEBOUNCE_30MS;
 		break;
-	case 31 ... 50:
+	case 30001 ... 50000:
 		val = BD70528_DEBOUNCE_50MS;
 		break;
 	default:
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index 4d835f9089df..86a10c808ef6 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -293,8 +293,9 @@ static void intel_mid_irq_handler(struct irq_desc *desc)
 	chip->irq_eoi(data);
 }
 
-static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv)
+static int intel_mid_irq_init_hw(struct gpio_chip *chip)
 {
+	struct intel_mid_gpio *priv = gpiochip_get_data(chip);
 	void __iomem *reg;
 	unsigned base;
 
@@ -309,6 +310,8 @@ static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv)
 		reg = gpio_reg(&priv->chip, base, GEDR);
 		writel(~0, reg);
 	}
+
+	return 0;
 }
 
 static int __maybe_unused intel_gpio_runtime_idle(struct device *dev)
@@ -372,6 +375,7 @@ static int intel_gpio_probe(struct pci_dev *pdev,
 
 	girq = &priv->chip.irq;
 	girq->chip = &intel_mid_irqchip;
+	girq->init_hw = intel_mid_irq_init_hw;
 	girq->parent_handler = intel_mid_irq_handler;
 	girq->num_parents = 1;
 	girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
@@ -384,9 +388,8 @@ static int intel_gpio_probe(struct pci_dev *pdev,
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_simple_irq;
 
-	intel_mid_irq_init_hw(priv);
-
 	pci_set_drvdata(pdev, priv);
+
 	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
 		dev_err(&pdev->dev, "gpiochip_add error %d\n", retval);
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 6bb9741ad036..e9e47c0d5be7 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -294,8 +294,9 @@ static struct irq_chip lp_irqchip = {
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static void lp_gpio_irq_init_hw(struct lp_gpio *lg)
+static int lp_gpio_irq_init_hw(struct gpio_chip *chip)
 {
+	struct lp_gpio *lg = gpiochip_get_data(chip);
 	unsigned long reg;
 	unsigned base;
 
@@ -307,6 +308,8 @@ static void lp_gpio_irq_init_hw(struct lp_gpio *lg)
 		reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
 		outl(0xffffffff, reg);
 	}
+
+	return 0;
 }
 
 static int lp_gpio_probe(struct platform_device *pdev)
@@ -364,6 +367,7 @@ static int lp_gpio_probe(struct platform_device *pdev)
 
 		girq = &gc->irq;
 		girq->chip = &lp_irqchip;
+		girq->init_hw = lp_gpio_irq_init_hw;
 		girq->parent_handler = lp_gpio_irq_handler;
 		girq->num_parents = 1;
 		girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
@@ -373,9 +377,7 @@ static int lp_gpio_probe(struct platform_device *pdev)
 			return -ENOMEM;
 		girq->parents[0] = (unsigned)irq_rc->start;
 		girq->default_type = IRQ_TYPE_NONE;
-		girq->handler = handle_simple_irq;
-
-		lp_gpio_irq_init_hw(lg);
+		girq->handler = handle_bad_irq;
 	}
 
 	ret = devm_gpiochip_add_data(dev, gc, lg);
diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c
index faf86ea9c51a..642c6321c22a 100644
--- a/drivers/gpio/gpio-max77620.c
+++ b/drivers/gpio/gpio-max77620.c
@@ -192,13 +192,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio,
 	case 0:
 		val = MAX77620_CNFG_GPIO_DBNC_None;
 		break;
-	case 1000 ... 8000:
+	case 1 ... 8000:
 		val = MAX77620_CNFG_GPIO_DBNC_8ms;
 		break;
-	case 9000 ... 16000:
+	case 8001 ... 16000:
 		val = MAX77620_CNFG_GPIO_DBNC_16ms;
 		break;
-	case 17000 ... 32000:
+	case 16001 ... 32000:
 		val = MAX77620_CNFG_GPIO_DBNC_32ms;
 		break;
 	default:
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 4f27ddfe1e2f..3302125e5265 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -397,7 +397,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 {
 	const struct mrfld_gpio_pinrange *range;
 	const char *pinctrl_dev_name;
-	struct gpio_irq_chip *girq;
 	struct mrfld_gpio *priv;
 	u32 gpio_base, irq_base;
 	void __iomem *base;
@@ -445,21 +444,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 	raw_spin_lock_init(&priv->lock);
 
-	girq = &priv->chip.irq;
-	girq->chip = &mrfld_irqchip;
-	girq->parent_handler = mrfld_irq_handler;
-	girq->num_parents = 1;
-	girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
-				     sizeof(*girq->parents),
-				     GFP_KERNEL);
-	if (!girq->parents)
-		return -ENOMEM;
-	girq->parents[0] = pdev->irq;
-	girq->default_type = IRQ_TYPE_NONE;
-	girq->handler = handle_bad_irq;
-
-	mrfld_irq_init_hw(priv);
-
 	pci_set_drvdata(pdev, priv);
 	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
@@ -481,6 +465,18 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		}
 	}
 
+	retval = gpiochip_irqchip_add(&priv->chip, &mrfld_irqchip, irq_base,
+				      handle_bad_irq, IRQ_TYPE_NONE);
+	if (retval) {
+		dev_err(&pdev->dev, "could not connect irqchip to gpiochip\n");
+		return retval;
+	}
+
+	mrfld_irq_init_hw(priv);
+
+	gpiochip_set_chained_irqchip(&priv->chip, &mrfld_irqchip, pdev->irq,
+				     mrfld_irq_handler);
+
 	return 0;
 }
 
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 609ed16ae933..59ccfd24627d 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1304,11 +1304,28 @@ late_initcall_sync(acpi_gpio_handle_deferred_request_irqs);
 
 static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = {
 	{
+		/*
+		 * The Minix Neo Z83-4 has a micro-USB-B id-pin handler for
+		 * a non existing micro-USB-B connector which puts the HDMI
+		 * DDC pins in GPIO mode, breaking HDMI support.
+		 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "MINIX"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"),
 		}
 	},
+	{
+		/*
+		 * The Terra Pad 1061 has a micro-USB-B id-pin handler, which
+		 * instead of controlling the actual micro-USB-B turns the 5V
+		 * boost for its USB-A connector off. The actual micro-USB-B
+		 * connector is wired for charging only.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"),
+		}
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5833e4f380d6..104ed299d5ea 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -86,6 +86,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 				struct lock_class_key *lock_key,
 				struct lock_class_key *request_key);
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+static int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip);
 static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip);
 static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip);
 
@@ -1406,6 +1407,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	machine_gpiochip_add(chip);
 
+	ret = gpiochip_irqchip_init_hw(chip);
+	if (ret)
+		goto err_remove_acpi_chip;
+
 	ret = gpiochip_irqchip_init_valid_mask(chip);
 	if (ret)
 		goto err_remove_acpi_chip;
@@ -1622,6 +1627,16 @@ static struct gpio_chip *find_chip_by_name(const char *name)
  * The following is irqchip helper code for gpiochips.
  */
 
+static int gpiochip_irqchip_init_hw(struct gpio_chip *gc)
+{
+	struct gpio_irq_chip *girq = &gc->irq;
+
+	if (!girq->init_hw)
+		return 0;
+
+	return girq->init_hw(gc);
+}
+
 static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc)
 {
 	struct gpio_irq_chip *girq = &gc->irq;
@@ -2446,8 +2461,13 @@ static inline int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 {
 	return 0;
 }
-
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) {}
+
+static inline int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip)
+{
+	return 0;
+}
+
 static inline int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip)
 {
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 61e38e43ad1d..85b0515c0fdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -140,7 +140,12 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 	return 0;
 
 error_free:
-	while (i--) {
+	for (i = 0; i < last_entry; ++i) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
+
+		amdgpu_bo_unref(&bo);
+	}
+	for (i = first_userptr; i < num_entries; ++i) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
 
 		amdgpu_bo_unref(&bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2e53feed40e2..82823d9a8ba8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -536,7 +536,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 	list_for_each_entry(lobj, validated, tv.head) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo);
-		bool binding_userptr = false;
 		struct mm_struct *usermm;
 
 		usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm);
@@ -553,7 +552,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     lobj->user_pages);
-			binding_userptr = true;
 		}
 
 		if (p->evictable == lobj)
@@ -563,10 +561,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		if (r)
 			return r;
 
-		if (binding_userptr) {
-			kvfree(lobj->user_pages);
-			lobj->user_pages = NULL;
-		}
+		kvfree(lobj->user_pages);
+		lobj->user_pages = NULL;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6614d8a6f4c8..2cdaf3b2a721 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 			continue;
 		}
 
-		for (i = 0; i < num_entities; i++)
+		for (i = 0; i < num_entities; i++) {
+			mutex_lock(&ctx->adev->lock_reset);
 			drm_sched_entity_fini(&ctx->entities[0][i].entity);
+			mutex_unlock(&ctx->adev->lock_reset);
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5a1939dbd4e3..7a6c837c0a85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2885,6 +2885,13 @@ fence_driver_init:
 			DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n");
 	}
 
+	/*
+	 * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost.
+	 * Otherwise the mgpu fan boost feature will be skipped due to the
+	 * gpu instance is counted less.
+	 */
+	amdgpu_register_gpu_instance(adev);
+
 	/* enable clockgating, etc. after ib tests, etc. since some blocks require
 	 * explicit gating rather than handling it automatically.
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 1d4aaa9580f4..82efc1e22e61 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -511,7 +511,7 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 	 * Also, don't allow GTT domain if the BO doens't have USWC falg set.
 	 */
 	if (adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN &&
+	    adev->asic_type < CHIP_RAVEN &&
 	    (adev->flags & AMD_IS_APU) &&
 	    (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
 	    amdgpu_bo_support_uswc(bo_flags) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6f8aaf655a9f..b19157b19fa0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1013,9 +1013,10 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
-	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
@@ -1048,6 +1049,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+#ifdef CONFIG_DRM_AMDGPU_SI
+	if (!amdgpu_si_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	if (!amdgpu_cik_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+
 	/* Get rid of things like offb */
 	ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 6ee4021910e2..6d19183b478b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -289,6 +289,7 @@ struct amdgpu_gfx {
 	uint32_t			mec2_feature_version;
 	bool				mec_fw_write_wait;
 	bool				me_fw_write_wait;
+	bool				cp_fw_write_wait;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9d76e0923a5a..96b2a31ccfed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -218,7 +218,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_job *job;
-	int r;
+	int r = 0;
 
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
@@ -243,6 +243,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	job->fence = dma_fence_get(fence);
 
 	amdgpu_job_free_resources(job);
+
+	fence = r ? ERR_PTR(r) : fence;
 	return fence;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f2c097983f48..a73206784cba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct amdgpu_device *adev;
 	int r, acpi_status;
 
-#ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-
 	adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
 	if (adev == NULL) {
 		return -ENOMEM;
@@ -225,7 +190,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		pm_runtime_put_autosuspend(dev->dev);
 	}
 
-	amdgpu_register_gpu_instance(adev);
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
@@ -685,15 +649,19 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			return -ENOMEM;
 		alloc_size = info->read_mmr_reg.count * sizeof(*regs);
 
-		for (i = 0; i < info->read_mmr_reg.count; i++)
+		amdgpu_gfx_off_ctrl(adev, false);
+		for (i = 0; i < info->read_mmr_reg.count; i++) {
 			if (amdgpu_asic_read_register(adev, se_num, sh_num,
 						      info->read_mmr_reg.dword_offset + i,
 						      &regs[i])) {
 				DRM_DEBUG_KMS("unallowed offset %#x\n",
 					      info->read_mmr_reg.dword_offset + i);
 				kfree(regs);
+				amdgpu_gfx_off_ctrl(adev, true);
 				return -EFAULT;
 			}
+		}
+		amdgpu_gfx_off_ctrl(adev, true);
 		n = copy_to_user(out, regs, min(size, alloc_size));
 		kfree(regs);
 		return n ? -EFAULT : 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 1fead0e8b890..7289e1b4fb60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -453,7 +453,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 		.interruptible = (bp->type != ttm_bo_type_kernel),
 		.no_wait_gpu = false,
 		.resv = bp->resv,
-		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
+		.flags = bp->type != ttm_bo_type_kernel ?
+			TTM_OPT_FLAG_ALLOW_RES_EVICT : 0
 	};
 	struct amdgpu_bo *bo;
 	unsigned long page_align, size = bp->size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 4d71537a960d..a46090071034 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -950,21 +950,7 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 			     struct amdgpu_firmware_info *ucode)
 {
 	struct amdgpu_device *adev = psp->adev;
-	const struct sdma_firmware_header_v1_0 *sdma_hdr =
-		(const struct sdma_firmware_header_v1_0 *)
-		adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
-	const struct gfx_firmware_header_v1_0 *ce_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
-	const struct gfx_firmware_header_v1_0 *pfp_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
-	const struct gfx_firmware_header_v1_0 *me_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
-	const struct gfx_firmware_header_v1_0 *mec_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
-	const struct rlc_firmware_header_v2_0 *rlc_hdr =
-		(const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	const struct smc_firmware_header_v1_0 *smc_hdr =
-		(const struct smc_firmware_header_v1_0 *)adev->pm.fw->data;
+	struct common_firmware_header *hdr;
 
 	switch (ucode->ucode_id) {
 	case AMDGPU_UCODE_ID_SDMA0:
@@ -975,25 +961,33 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 	case AMDGPU_UCODE_ID_SDMA5:
 	case AMDGPU_UCODE_ID_SDMA6:
 	case AMDGPU_UCODE_ID_SDMA7:
-		amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header);
+		hdr = (struct common_firmware_header *)
+			adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
+		amdgpu_ucode_print_sdma_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_CE:
-		amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_PFP:
-		amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_ME:
-		amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.me_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_MEC1:
-		amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_RLC_G:
-		amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data;
+		amdgpu_ucode_print_rlc_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_SMC:
-		amdgpu_ucode_print_smc_hdr(&smc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->pm.fw->data;
+		amdgpu_ucode_print_smc_hdr(hdr);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b70b3c45bb29..65044b1b3d4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -429,13 +429,14 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
  * Open up a stream for HW test
  */
 int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+			      struct amdgpu_bo *bo,
 			      struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 1024;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -444,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib = &job->ibs[0];
 
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	/* stitch together an VCE create msg */
 	ib->length_dw = 0;
@@ -476,8 +477,8 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
@@ -1110,13 +1111,20 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
 int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
 	/* skip vce ring1/2 ib test for now, since it's not reliable */
 	if (ring != &ring->adev->vce.ring[0])
 		return 0;
 
-	r = amdgpu_vce_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 512, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vce_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
@@ -1132,5 +1140,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index 30ea54dd9117..e802f7d9db0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -59,6 +59,7 @@ int amdgpu_vce_entity_init(struct amdgpu_device *adev);
 int amdgpu_vce_suspend(struct amdgpu_device *adev);
 int amdgpu_vce_resume(struct amdgpu_device *adev);
 int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+			      struct amdgpu_bo *bo,
 			      struct dma_fence **fence);
 int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 			       bool direct, struct dma_fence **fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 7a6beb2e7c4e..3199e4a5ff12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -569,13 +569,14 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence)
+					 struct amdgpu_bo *bo,
+					 struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -583,14 +584,14 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -621,13 +622,14 @@ err:
 }
 
 static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					  struct amdgpu_bo *bo,
+					  struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -635,14 +637,14 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -675,13 +677,20 @@ err:
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = amdgpu_vcn_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vcn_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, &fence);
+	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -693,6 +702,8 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 957811b73672..53090eae0082 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -93,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -140,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -179,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -564,6 +564,32 @@ static void gfx_v10_0_free_microcode(struct amdgpu_device *adev)
 	kfree(adev->gfx.rlc.register_list_format);
 }
 
+static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
+{
+	adev->gfx.cp_fw_write_wait = false;
+
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
+		if ((adev->gfx.me_fw_version >= 0x00000046) &&
+		    (adev->gfx.me_feature_version >= 27) &&
+		    (adev->gfx.pfp_fw_version >= 0x00000068) &&
+		    (adev->gfx.pfp_feature_version >= 27) &&
+		    (adev->gfx.mec_fw_version >= 0x0000005b) &&
+		    (adev->gfx.mec_feature_version >= 27))
+			adev->gfx.cp_fw_write_wait = true;
+		break;
+	default:
+		break;
+	}
+
+	if (adev->gfx.cp_fw_write_wait == false)
+		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+			      GRBM requires 1-cycle delay in cp firmware\n");
+}
+
+
 static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
 {
 	const struct rlc_firmware_header_v2_1 *rlc_hdr;
@@ -832,6 +858,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		}
 	}
 
+	gfx_v10_0_check_fw_write_wait(adev);
 out:
 	if (err) {
 		dev_err(adev->dev,
@@ -4765,6 +4792,24 @@ static void gfx_v10_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 	gfx_v10_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
 }
 
+static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						   uint32_t reg0, uint32_t reg1,
+						   uint32_t ref, uint32_t mask)
+{
+	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+	struct amdgpu_device *adev = ring->adev;
+	bool fw_version_ok = false;
+
+	fw_version_ok = adev->gfx.cp_fw_write_wait;
+
+	if (fw_version_ok)
+		gfx_v10_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1,
+				       ref, mask, 0x20);
+	else
+		amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1,
+							   ref, mask);
+}
+
 static void
 gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5155,6 +5200,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_tmz = gfx_v10_0_ring_emit_tmz,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
@@ -5188,6 +5234,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
@@ -5218,6 +5265,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
 	.emit_rreg = gfx_v10_0_ring_emit_rreg,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index dcadc73bffd2..97cf0b536873 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -973,6 +973,13 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 	adev->gfx.me_fw_write_wait = false;
 	adev->gfx.mec_fw_write_wait = false;
 
+	if ((adev->gfx.mec_fw_version < 0x000001a5) ||
+	    (adev->gfx.mec_feature_version < 46) ||
+	    (adev->gfx.pfp_fw_version < 0x000000b7) ||
+	    (adev->gfx.pfp_feature_version < 46))
+		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+			      GRBM requires 1-cycle delay in cp firmware\n");
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 		if ((adev->gfx.me_fw_version >= 0x0000009c) &&
@@ -1031,8 +1038,13 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			&&((adev->gfx.rlc_fw_version != 106 &&
+		/* Disable GFXOFF on original raven.  There are combinations
+		 * of sbios and platforms that are not stable.
+		 */
+		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+			 &&((adev->gfx.rlc_fw_version != 106 &&
 			     adev->gfx.rlc_fw_version < 531) ||
 			    (adev->gfx.rlc_fw_version == 53815) ||
 			    (adev->gfx.rlc_feature_version < 1) ||
@@ -1044,6 +1056,12 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 				AMD_PG_SUPPORT_CP |
 				AMD_PG_SUPPORT_RLC_SMU_HS;
 		break;
+	case CHIP_RENOIR:
+		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
+			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+				AMD_PG_SUPPORT_CP |
+				AMD_PG_SUPPORT_RLC_SMU_HS;
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 8b789f750b72..db10640a3b2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -151,6 +151,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp);
 
 	tmp = mmGCVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp);
 
 	tmp = mmGCVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 241a4e57cf4a..5c7d5f73f54f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -309,6 +309,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo);
 	job->vm_needs_flush = true;
+	job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
@@ -343,11 +344,9 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
 			      upper_32_bits(pd_addr));
 
-	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
-
-	/* wait for the invalidate to complete */
-	amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng,
-				  1 << vmid, 1 << vmid);
+	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
+					    hub->vm_inv_eng0_ack + eng,
+					    req, 1 << vmid);
 
 	return pd_addr;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 3542c203c3c8..b39bea6f54e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -137,6 +137,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp);
 
 	tmp = mmMMVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp);
 
 	tmp = mmMMVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 0cf7ef44b4b5..9ed178fa241c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -219,6 +219,15 @@ static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid)
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 
 	tmp = mmVML2PF0_VM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_CNTL3,
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 78452cf0115d..4554e72c8378 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index fa2f70ce2e2b..8493bfbbc148 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
 	amdgpu_ring_write(ring, seq); /* reference */
-	amdgpu_ring_write(ring, 0xfffffff); /* mask */
+	amdgpu_ring_write(ring, 0xffffffff); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
 }
@@ -1173,6 +1173,16 @@ static void sdma_v5_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
 }
 
+static void sdma_v5_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						   uint32_t reg0, uint32_t reg1,
+						   uint32_t ref, uint32_t mask)
+{
+	amdgpu_ring_emit_wreg(ring, reg0, ref);
+	/* wait for a cycle to reset vm_inv_eng*_ack */
+	amdgpu_ring_emit_reg_wait(ring, reg0, 0, 0);
+	amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
+}
+
 static int sdma_v5_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1588,7 +1598,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
 		6 + /* sdma_v5_0_ring_emit_pipeline_sync */
 		/* sdma_v5_0_ring_emit_vm_flush */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 +
 		10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */
 	.emit_ib = sdma_v5_0_ring_emit_ib,
@@ -1602,6 +1612,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
 	.pad_ib = sdma_v5_0_ring_pad_ib,
 	.emit_wreg = sdma_v5_0_ring_emit_wreg,
 	.emit_reg_wait = sdma_v5_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait,
 	.init_cond_exec = sdma_v5_0_ring_init_cond_exec,
 	.patch_cond_exec = sdma_v5_0_ring_patch_cond_exec,
 	.preempt_ib = sdma_v5_0_ring_preempt_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f8ab80c8801b..4ccfcdf8f16a 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1186,11 +1186,6 @@ static int soc15_common_early_init(void *handle)
 				 AMD_PG_SUPPORT_VCN |
 				 AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 0x91;
-
-		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
-			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
-				AMD_PG_SUPPORT_CP |
-				AMD_PG_SUPPORT_RLC_SMU_HS;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 670784a78512..217084d56ab8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -206,13 +206,14 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -220,15 +221,15 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -268,13 +269,14 @@ err:
  */
 static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 					uint32_t handle,
+					struct amdgpu_bo *bo,
 					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -282,15 +284,15 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -327,13 +329,20 @@ err:
 static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v6_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -345,6 +354,8 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 01f658fa72c6..0995378d8263 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -214,13 +214,14 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -228,15 +229,15 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -275,13 +276,14 @@ err:
  * Close up a stream for HW test or if userspace failed to do so
  */
 static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					struct amdgpu_bo *bo,
+					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -289,15 +291,15 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002;
@@ -334,13 +336,20 @@ err:
 static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -352,6 +361,8 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a52f0b13a2c8..4139f129eafb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -688,7 +688,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	 */
 	if (adev->flags & AMD_IS_APU &&
 	    adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN)
+	    adev->asic_type < CHIP_RAVEN)
 		init_data.flags.gpu_vm_support = true;
 
 	if (amdgpu_dc_feature_mask & DC_FBC_MASK)
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 985633c08a26..26c6d735cdc7 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -24,15 +24,20 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+calcs_ccflags := -mhard-float -msse
 
-calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+calcs_ccflags += -mpreferred-stack-boundary=4
+else
 calcs_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5d1adeda4d90..4b8819c27fcd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -580,6 +580,10 @@ static bool construct(struct dc *dc,
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	// Allocate memory for the vm_helper
 	dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
+	if (!dc->vm_helper) {
+		dm_error("%s: failed to create dc->vm_helper\n", __func__);
+		goto fail;
+	}
 
 #endif
 	memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 505967b48e14..51991bf26a93 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -374,6 +374,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 	enum display_dongle_type *dongle = &sink_cap->dongle_type;
 	uint8_t type2_dongle_buf[DP_ADAPTOR_TYPE2_SIZE];
 	bool is_type2_dongle = false;
+	int retry_count = 2;
 	struct dp_hdmi_dongle_signature_data *dongle_signature;
 
 	/* Assume we have no valid DP passive dongle connected */
@@ -386,13 +387,24 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 		DP_HDMI_DONGLE_ADDRESS,
 		type2_dongle_buf,
 		sizeof(type2_dongle_buf))) {
-		*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
-		sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
+		/* Passive HDMI dongles can sometimes fail here without retrying*/
+		while (retry_count > 0) {
+			if (i2c_read(ddc,
+				DP_HDMI_DONGLE_ADDRESS,
+				type2_dongle_buf,
+				sizeof(type2_dongle_buf)))
+				break;
+			retry_count--;
+		}
+		if (retry_count == 0) {
+			*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
+			sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
 
-		CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
-				"DP-DVI passive dongle %dMhz: ",
-				DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
-		return;
+			CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
+					"DP-DVI passive dongle %dMhz: ",
+					DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
+			return;
+		}
 	}
 
 	/* Check if Type 2 dongle.*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 8f70295179ff..f25ac17f47fa 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -404,6 +404,9 @@ bool resource_are_streams_timing_synchronizable(
 	if (stream1->view_format != stream2->view_format)
 		return false;
 
+	if (stream1->ignore_msa_timing_param || stream2->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 static bool is_dp_and_hdmi_sharable(
@@ -1540,6 +1543,9 @@ bool dc_is_stream_unchanged(
 	if (!are_stream_backends_same(old_stream, stream))
 		return false;
 
+	if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 01c7e30b9ce1..bbd6e01b3eca 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -393,6 +393,10 @@ bool cm_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
@@ -464,13 +468,6 @@ bool cm_helper_translate_curve_to_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
@@ -562,6 +559,10 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
 	corner_points[0].green.x = corner_points[0].red.x;
@@ -624,13 +625,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index ddb8d5649e79..63f3bddba7da 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -10,15 +10,20 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
 endif
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 5a2763daff4d..6b2f2f1a1c9c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -814,7 +814,7 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_audio = 6,
 		.num_stream_encoder = 5,
 		.num_pll = 5,
-		.num_dwb = 0,
+		.num_dwb = 1,
 		.num_ddc = 5,
 };
 
@@ -1107,6 +1107,11 @@ struct stream_encoder *dcn20_stream_encoder_create(
 	if (!enc1)
 		return NULL;
 
+	if (ASICREV_IS_NAVI14_M(ctx->asic_id.hw_internal_rev)) {
+		if (eng_id >= ENGINE_ID_DIGD)
+			eng_id++;
+	}
+
 	dcn20_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id,
 					&stream_enc_regs[eng_id],
 					&se_shift, &se_mask);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index ef673bffc241..ff50ae71fe27 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,15 +3,20 @@
 
 DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 5b2a65b42403..8df251626e22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -24,15 +24,20 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dml_ccflags := -mhard-float -msse
 
-dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dml_ccflags += -mpreferred-stack-boundary=4
+else
 dml_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 649883777f62..6c6c486b774a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index b456cd23c6fa..970737217e53 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -1,15 +1,20 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dsc_ccflags := -mhard-float -msse
 
-dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dsc_ccflags += -mpreferred-stack-boundary=4
+else
 dsc_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 34f95e0e3ea4..203ce4b1028f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -3478,18 +3478,31 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr,
 
 static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int i;
 	u32 tmp = 0;
 
 	if (!query)
 		return -EINVAL;
 
-	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
-	tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
-	*query = tmp;
+	/*
+	 * PPSMC_MSG_GetCurrPkgPwr is not supported on:
+	 *  - Hawaii
+	 *  - Bonaire
+	 *  - Fiji
+	 *  - Tonga
+	 */
+	if ((adev->asic_type != CHIP_HAWAII) &&
+	    (adev->asic_type != CHIP_BONAIRE) &&
+	    (adev->asic_type != CHIP_FIJI) &&
+	    (adev->asic_type != CHIP_TONGA)) {
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
+		tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
+		*query = tmp;
 
-	if (tmp != 0)
-		return 0;
+		if (tmp != 0)
+			return 0;
+	}
 
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart);
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d08493b67b67..beacfffbdc3e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -5098,9 +5098,7 @@ static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
 
 	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
-		for (i = 0; i < podn_vdd_dep->count - 1; i++)
-			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
-		if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc)
+		for (i = 0; i < podn_vdd_dep->count; i++)
 			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
 	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 0b461404af6b..328e258a6895 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -205,7 +205,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_workload_map[PP_SMC_POWER_PROFILE
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING,		WORKLOAD_PPLIB_POWER_SAVING_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_CUSTOM_BIT),
+	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
 };
 
@@ -759,6 +759,12 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 	case SMU_UCLK:
 	case SMU_DCEFCLK:
 	case SMU_FCLK:
+		/* There is only 2 levels for fine grained DPM */
+		if (navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+			soft_max_level = (soft_max_level >= 1 ? 1 : 0);
+			soft_min_level = (soft_min_level >= 1 ? 1 : 0);
+		}
+
 		ret = smu_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
 			return size;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index dc754447f0dd..23c12018dbc1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage =
-				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 7c960b07746f..ae18fbcb26fb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
-					data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+					data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index bbd8ebd58434..92c393f613d3 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -219,7 +219,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_workload_map[PP_SMC_POWER_PROFILE
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING,		WORKLOAD_PPLIB_POWER_SAVING_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_CUSTOM_BIT),
+	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
 };
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 8820ce15ce37..ae274902ff92 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -82,7 +82,8 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, old_state);
 
-	drm_atomic_helper_commit_planes(dev, old_state, 0);
+	drm_atomic_helper_commit_planes(dev, old_state,
+					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index ea26bc9c2d00..b848270e0a1f 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -564,8 +564,8 @@ komeda_splitter_validate(struct komeda_splitter *splitter,
 	}
 
 	if (!in_range(&splitter->vsize, dflow->in_h)) {
-		DRM_DEBUG_ATOMIC("split in_in: %d exceed the acceptable range.\n",
-				 dflow->in_w);
+		DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n",
+				 dflow->in_h);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 3ef2ac52ce94..2dd2cd87cdbb 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1581,8 +1581,11 @@ static void commit_tail(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
 	const struct drm_mode_config_helper_funcs *funcs;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
 	ktime_t start;
 	s64 commit_time_ms;
+	unsigned int i, new_self_refresh_mask = 0;
 
 	funcs = dev->mode_config.helper_private;
 
@@ -1602,6 +1605,15 @@ static void commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_wait_for_dependencies(old_state);
 
+	/*
+	 * We cannot safely access new_crtc_state after
+	 * drm_atomic_helper_commit_hw_done() so figure out which crtc's have
+	 * self-refresh active beforehand:
+	 */
+	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i)
+		if (new_crtc_state->self_refresh_active)
+			new_self_refresh_mask |= BIT(i);
+
 	if (funcs && funcs->atomic_commit_tail)
 		funcs->atomic_commit_tail(old_state);
 	else
@@ -1610,7 +1622,8 @@ static void commit_tail(struct drm_atomic_state *old_state)
 	commit_time_ms = ktime_ms_delta(ktime_get(), start);
 	if (commit_time_ms > 0)
 		drm_self_refresh_helper_update_avg_times(old_state,
-						 (unsigned long)commit_time_ms);
+						 (unsigned long)commit_time_ms,
+						 new_self_refresh_mask);
 
 	drm_atomic_helper_commit_cleanup_done(old_state);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82a4ceed3fcf..6b0177112e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -159,6 +159,9 @@ static const struct edid_quirk {
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
 
+	/* Lenovo G50 */
+	{ "SDC", 18514, EDID_QUIRK_FORCE_6BPC },
+
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 
diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c
index 68f4765a5896..dd33fec5aabd 100644
--- a/drivers/gpu/drm/drm_self_refresh_helper.c
+++ b/drivers/gpu/drm/drm_self_refresh_helper.c
@@ -133,29 +133,33 @@ out_drop_locks:
  * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages
  * @state: the state which has just been applied to hardware
  * @commit_time_ms: the amount of time in ms that this commit took to complete
+ * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in
+ *    new state
  *
  * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will
  * update the average entry/exit self refresh times on self refresh transitions.
  * These averages will be used when calculating how long to delay before
  * entering self refresh mode after activity.
  */
-void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
-					      unsigned int commit_time_ms)
+void
+drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
+					 unsigned int commit_time_ms,
+					 unsigned int new_self_refresh_mask)
 {
 	struct drm_crtc *crtc;
-	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_crtc_state *old_crtc_state;
 	int i;
 
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
-				      new_crtc_state, i) {
+	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
+		bool new_self_refresh_active = new_self_refresh_mask & BIT(i);
 		struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
 		struct ewma_psr_time *time;
 
 		if (old_crtc_state->self_refresh_active ==
-		    new_crtc_state->self_refresh_active)
+		    new_self_refresh_active)
 			continue;
 
-		if (new_crtc_state->self_refresh_active)
+		if (new_self_refresh_active)
 			time = &sr_data->entry_avg_ms;
 		else
 			time = &sr_data->exit_avg_ms;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 698db540972c..648cf0207309 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -180,6 +180,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 			      etnaviv_cmdbuf_get_va(&submit->cmdbuf,
 					&gpu->mmu_context->cmdbuf_mapping));
 
+	mutex_unlock(&gpu->mmu_context->lock);
+
 	/* Reserve space for the bomap */
 	if (n_bomap_pages) {
 		bomap_start = bomap = iter.data;
@@ -221,8 +223,6 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 					 obj->base.size);
 	}
 
-	mutex_unlock(&gpu->mmu_context->lock);
-
 	etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);
 
 	dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 043111a1d60c..f8bf488e9d71 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -155,9 +155,11 @@ static void etnaviv_iommuv2_dump(struct etnaviv_iommu_context *context, void *bu
 
 	memcpy(buf, v2_context->mtlb_cpu, SZ_4K);
 	buf += SZ_4K;
-	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++, buf += SZ_4K)
-		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT)
+	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++)
+		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) {
 			memcpy(buf, v2_context->stlb_cpu[i], SZ_4K);
+			buf += SZ_4K;
+		}
 }
 
 static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 35ebae6a1be7..3607d348c298 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -328,12 +328,23 @@ etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 
 	ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping,
 					  global->memory_base);
-	if (ret) {
-		global->ops->free(ctx);
-		return NULL;
+	if (ret)
+		goto out_free;
+
+	if (global->version == ETNAVIV_IOMMU_V1 &&
+	    ctx->cmdbuf_mapping.iova > 0x80000000) {
+		dev_err(global->dev,
+		        "command buffer outside valid memory window\n");
+		goto out_unmap;
 	}
 
 	return ctx;
+
+out_unmap:
+	etnaviv_cmdbuf_suballoc_unmap(ctx, &ctx->cmdbuf_mapping);
+out_free:
+	global->ops->free(ctx);
+	return NULL;
 }
 
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index d3fb75bb9eb1..7cb2257bbb93 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -201,6 +201,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->update_wm_post = false;
 	crtc_state->fb_changed = false;
 	crtc_state->fifo_changed = false;
+	crtc_state->preload_luts = false;
 	crtc_state->wm.need_postvbl_update = false;
 	crtc_state->fb_bits = 0;
 	crtc_state->update_planes = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..3250c1b8dcca 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
 			      "disabling port %c DVI/HDMI support\n",
 			      port_name(port), info->alternate_ddc_pin,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same ddc bin and
 		 * system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dvi = false;
 		info->supports_hdmi = false;
 		info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
 			      "disabling port %c DP support\n",
 			      port_name(port), info->alternate_aux_channel,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same aux channel
 		 * and system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dp = false;
 		info->alternate_aux_channel = 0;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 71a0201437a9..aa1e2c670bc4 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -990,6 +990,55 @@ void intel_color_commit(const struct intel_crtc_state *crtc_state)
 	dev_priv->display.color_commit(crtc_state);
 }
 
+static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	return !old_crtc_state->base.gamma_lut &&
+		!old_crtc_state->base.degamma_lut;
+}
+
+static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	/*
+	 * CGM_PIPE_MODE is itself single buffered. We'd have to
+	 * somehow split it out from chv_load_luts() if we wanted
+	 * the ability to preload the CGM LUTs/CSC without tearing.
+	 */
+	if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode)
+		return false;
+
+	return !old_crtc_state->base.gamma_lut;
+}
+
+static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	/*
+	 * The hardware degamma is active whenever the pipe
+	 * CSC is active. Thus even if the old state has no
+	 * software degamma we need to avoid clobbering the
+	 * linear hardware degamma mid scanout.
+	 */
+	return !old_crtc_state->csc_enable &&
+		!old_crtc_state->base.gamma_lut;
+}
+
 int intel_color_check(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
@@ -1133,6 +1182,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1185,6 +1236,8 @@ static int chv_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = chv_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1224,6 +1277,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1281,6 +1336,8 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1319,6 +1376,8 @@ static int glk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = glk_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1368,6 +1427,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 	crtc_state->csc_mode = icl_csc_mode(crtc_state);
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index e6e8d4a82044..0a08354a6183 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -864,6 +864,13 @@ load_detect:
 
 out:
 	intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
+
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index aa54bb22796d..af50f05f4e9d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2504,6 +2504,9 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 	 * the highest stride limits of them all.
 	 */
 	crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_A);
+	if (!crtc)
+		return 0;
+
 	plane = to_intel_plane(crtc->base.primary);
 
 	return plane->max_stride(plane, pixel_format, modifier,
@@ -9315,7 +9318,6 @@ static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv,
 static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder;
-	bool pch_ssc_in_use = false;
 	bool has_fdi = false;
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
@@ -9343,22 +9345,24 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 	 * clock hierarchy. That would also allow us to do
 	 * clock bending finally.
 	 */
+	dev_priv->pch_ssc_use = 0;
+
 	if (spll_uses_pch_ssc(dev_priv)) {
 		DRM_DEBUG_KMS("SPLL using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) {
 		DRM_DEBUG_KMS("WRPLL1 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) {
 		DRM_DEBUG_KMS("WRPLL2 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2);
 	}
 
-	if (pch_ssc_in_use)
+	if (dev_priv->pch_ssc_use)
 		return;
 
 	if (has_fdi) {
@@ -13739,6 +13743,11 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 		/* vblanks work again, re-enable pipe CRC. */
 		intel_crtc_enable_pipe_crc(crtc);
 	} else {
+		if (new_crtc_state->preload_luts &&
+		    (new_crtc_state->base.color_mgmt_changed ||
+		     new_crtc_state->update_pipe))
+			intel_color_load_luts(new_crtc_state);
+
 		intel_pre_plane_update(old_crtc_state, new_crtc_state);
 
 		if (new_crtc_state->update_pipe)
@@ -14033,6 +14042,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		if (new_crtc_state->base.active &&
 		    !needs_modeset(new_crtc_state) &&
+		    !new_crtc_state->preload_luts &&
 		    (new_crtc_state->base.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 12099760d99e..c002f234ff31 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4896,6 +4896,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume)
 
 	power_domains->initializing = true;
 
+	/* Must happen before power domain init on VLV/CHV */
+	intel_update_rawclk(i915);
+
 	if (INTEL_GEN(i915) >= 11) {
 		icl_display_core_init(i915, resume);
 	} else if (IS_CANNONLAKE(i915)) {
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 449abaea619f..4075b0387c87 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -761,6 +761,7 @@ struct intel_crtc_state {
 	bool update_wm_pre, update_wm_post; /* watermarks are updated */
 	bool fb_changed; /* fb on any of the planes is changed */
 	bool fifo_changed; /* FIFO split is changed */
+	bool preload_luts;
 
 	/* Pipe source size (ie. panel fitter input size)
 	 * All planes will be positioned inside this space,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 57e9f0ba331b..9b15ac4f2fb6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1256,6 +1256,9 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 				u32 unused)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_i915_private *i915 =
+			to_i915(intel_dig_port->base.base.dev);
+	enum phy phy = intel_port_to_phy(i915, intel_dig_port->base.port);
 	u32 ret;
 
 	ret = DP_AUX_CH_CTL_SEND_BUSY |
@@ -1268,7 +1271,8 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	      DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) |
 	      DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
 
-	if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
+	if (intel_phy_is_tc(i915, phy) &&
+	    intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
 		ret |= DP_AUX_CH_CTL_TBT_IO;
 
 	return ret;
@@ -5436,6 +5440,12 @@ out:
 	if (status != connector_status_connected && !intel_dp->is_mst)
 		intel_dp_unset_edid(intel_dp);
 
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index b8148f838354..d5a298c3c83b 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -525,16 +525,31 @@ static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
 	val = I915_READ(WRPLL_CTL(id));
 	I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE);
 	POSTING_READ(WRPLL_CTL(id));
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
+	enum intel_dpll_id id = pll->info->id;
 	u32 val;
 
 	val = I915_READ(SPLL_CTL);
 	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
 	POSTING_READ(SPLL_CTL);
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index e7588799fce5..104cf6d42333 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -147,11 +147,11 @@ enum intel_dpll_id {
 	 */
 	DPLL_ID_ICL_MGPLL4 = 6,
 	/**
-	 * @DPLL_ID_TGL_TCPLL5: TGL TC PLL port 5 (TC5)
+	 * @DPLL_ID_TGL_MGPLL5: TGL TC PLL port 5 (TC5)
 	 */
 	DPLL_ID_TGL_MGPLL5 = 7,
 	/**
-	 * @DPLL_ID_TGL_TCPLL6: TGL TC PLL port 6 (TC6)
+	 * @DPLL_ID_TGL_MGPLL6: TGL TC PLL port 6 (TC6)
 	 */
 	DPLL_ID_TGL_MGPLL6 = 8,
 };
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index d59eee5c5d9c..b5c588e511dd 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -235,6 +235,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = ggtt->gmadr.start;
 	info->apertures->ranges[0].size = ggtt->mappable_end;
 
+	/* Our framebuffer is the entirety of fbdev's system memory */
+	info->fix.smem_start =
+		(unsigned long)(ggtt->gmadr.start + vma->node.start);
+	info->fix.smem_len = vma->node.size;
+
 	vaddr = i915_vma_pin_iomap(vma);
 	if (IS_ERR(vaddr)) {
 		DRM_ERROR("Failed to remap framebuffer into virtual memory\n");
@@ -244,10 +249,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->screen_base = vaddr;
 	info->screen_size = vma->node.size;
 
-	/* Our framebuffer is the entirety of fbdev's system memory */
-	info->fix.smem_start = (unsigned long)info->screen_base;
-	info->fix.smem_len = info->screen_size;
-
 	drm_fb_helper_fill_info(info, &ifbdev->helper, sizes);
 
 	/* If the object is shmemfs backed, it will have given us zeroed pages.
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index e02f0faecf02..b030f7ae3302 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2565,6 +2565,12 @@ out:
 	if (status != connector_status_connected)
 		cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier);
 
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1cdfe05514c3..e41fd94ae5a9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
+	kfree(ctx->jump_whitelist);
+
 	if (ctx->timeline)
 		intel_timeline_put(ctx->timeline);
 
@@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
+	ctx->jump_whitelist = NULL;
+	ctx->jump_whitelist_cmds = 0;
+
 	return ctx;
 
 err_free:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 260d59cc3de8..00537b9d7006 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -192,6 +192,13 @@ struct i915_gem_context {
 	 * per vm, which may be one per context or shared with the global GTT)
 	 */
 	struct radix_tree_root handles_vma;
+
+	/** jump_whitelist: Bit array for tracking cmds during cmdparsing
+	 *  Guarded by struct_mutex
+	 */
+	unsigned long *jump_whitelist;
+	/** jump_whitelist_cmds: No of cmd slots available */
+	u32 jump_whitelist_cmds;
 };
 
 #endif /* __I915_GEM_CONTEXT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index b5f6937369ea..e635e1e5f4d3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address)
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
-	return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
+	return intel_engine_requires_cmd_parser(eb->engine) ||
+		(intel_engine_using_cmd_parser(eb->engine) &&
+		 eb->args->batch_len);
 }
 
 static int eb_create(struct i915_execbuffer *eb)
@@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	return 0;
 }
 
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
+static struct i915_vma *
+shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *dev_priv = eb->i915;
+	struct i915_vma * const vma = *eb->vma;
+	struct i915_address_space *vm;
+	u64 flags;
+
+	/*
+	 * PPGTT backed shadow buffers must be mapped RO, to prevent
+	 * post-scan tampering
+	 */
+	if (CMDPARSER_USES_GGTT(dev_priv)) {
+		flags = PIN_GLOBAL;
+		vm = &dev_priv->ggtt.vm;
+	} else if (vma->vm->has_read_only) {
+		flags = PIN_USER;
+		vm = vma->vm;
+		i915_gem_object_set_readonly(obj);
+	} else {
+		DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+}
+
+static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
 {
 	struct intel_engine_pool_node *pool;
 	struct i915_vma *vma;
+	u64 batch_start;
+	u64 shadow_batch_start;
 	int err;
 
 	pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
 	if (IS_ERR(pool))
 		return ERR_CAST(pool);
 
-	err = intel_engine_cmd_parser(eb->engine,
+	vma = shadow_batch_pin(eb, pool->obj);
+	if (IS_ERR(vma))
+		goto err;
+
+	batch_start = gen8_canonical_addr(eb->batch->node.start) +
+		      eb->batch_start_offset;
+
+	shadow_batch_start = gen8_canonical_addr(vma->node.start);
+
+	err = intel_engine_cmd_parser(eb->gem_context,
+				      eb->engine,
 				      eb->batch->obj,
-				      pool->obj,
+				      batch_start,
 				      eb->batch_start_offset,
 				      eb->batch_len,
-				      is_master);
+				      pool->obj,
+				      shadow_batch_start);
+
 	if (err) {
-		if (err == -EACCES) /* unhandled chained batch */
+		i915_vma_unpin(vma);
+
+		/*
+		 * Unsafe GGTT-backed buffers can still be submitted safely
+		 * as non-secure.
+		 * For PPGTT backing however, we have no choice but to forcibly
+		 * reject unsafe buffers
+		 */
+		if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
+			/* Execute original buffer non-secure */
 			vma = NULL;
 		else
 			vma = ERR_PTR(err);
 		goto err;
 	}
 
-	vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
-	if (IS_ERR(vma))
-		goto err;
-
 	eb->vma[eb->buffer_count] = i915_vma_get(vma);
 	eb->flags[eb->buffer_count] =
 		__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
 	vma->exec_flags = &eb->flags[eb->buffer_count];
 	eb->buffer_count++;
 
+	eb->batch_start_offset = 0;
+	eb->batch = vma;
+
+	if (CMDPARSER_USES_GGTT(eb->i915))
+		eb->batch_flags |= I915_DISPATCH_SECURE;
+
+	/* eb->batch_len unchanged */
+
 	vma->private = pool;
 	return vma;
 
@@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_i915_gem_exec_object2 *exec,
 		       struct drm_syncobj **fences)
 {
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct dma_fence *exec_fence = NULL;
@@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
 		     ~__EXEC_OBJECT_UNKNOWN_FLAGS);
 
-	eb.i915 = to_i915(dev);
+	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
 	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
@@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
+		if (INTEL_GEN(i915) >= 11)
+			return -ENODEV;
+
+		/* Return -EPERM to trigger fallback code on old binaries. */
+		if (!HAS_SECURE_BATCHES(i915))
+			return -EPERM;
+
 		if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
-		    return -EPERM;
+			return -EPERM;
 
 		eb.batch_flags |= I915_DISPATCH_SECURE;
 	}
@@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_vma;
 	}
 
+	if (eb.batch_len == 0)
+		eb.batch_len = eb.batch->size - eb.batch_start_offset;
+
 	if (eb_use_cmdparser(&eb)) {
 		struct i915_vma *vma;
 
-		vma = eb_parse(&eb, drm_is_current_master(file));
+		vma = eb_parse(&eb);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto err_vma;
 		}
-
-		if (vma) {
-			/*
-			 * Batch parsed and accepted:
-			 *
-			 * Set the DISPATCH_SECURE bit to remove the NON_SECURE
-			 * bit from MI_BATCH_BUFFER_START commands issued in
-			 * the dispatch_execbuffer implementations. We
-			 * specifically don't want that set on batches the
-			 * command parser has accepted.
-			 */
-			eb.batch_flags |= I915_DISPATCH_SECURE;
-			eb.batch_start_offset = 0;
-			eb.batch = vma;
-		}
 	}
 
-	if (eb.batch_len == 0)
-		eb.batch_len = eb.batch->size - eb.batch_start_offset;
-
 	/*
 	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
 	 * batch" bit. Hence we need to pin secure batches into the global gtt.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 91051e178021..05289edbafe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -364,6 +364,7 @@ err:
 		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
+	case -ENODEV: /* bad object, how did you get here! */
 		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
@@ -475,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (!obj)
 		return -ENOENT;
 
+	if (i915_gem_object_never_bind_ggtt(obj)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	ret = create_mmap_offset(obj);
 	if (ret == 0)
 		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
+out:
 	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..ddf3605bea8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -153,6 +153,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 }
 
 static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
+static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
 	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index ede0eb4218a8..646859fea224 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 11b231c187c5..abfbac49b8e8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -671,8 +671,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 		obj->mm.dirty = false;
 
 	for_each_sgt_page(page, sgt_iter, pages) {
-		if (obj->mm.dirty)
+		if (obj->mm.dirty && trylock_page(page)) {
+			/*
+			 * As this may not be anonymous memory (e.g. shmem)
+			 * but exist on a real mapping, we have to lock
+			 * the page in order to dirty it -- holding
+			 * the page reference is not sufficient to
+			 * prevent the inode from being truncated.
+			 * Play safe and take the lock.
+			 *
+			 * However...!
+			 *
+			 * The mmu-notifier can be invalidated for a
+			 * migrate_page, that is alreadying holding the lock
+			 * on the page. Such a try_to_unmap() will result
+			 * in us calling put_pages() and so recursively try
+			 * to lock the page. We avoid that deadlock with
+			 * a trylock_page() and in exchange we risk missing
+			 * some page dirtying.
+			 */
 			set_page_dirty(page);
+			unlock_page(page);
+		}
 
 		mark_page_accessed(page);
 		put_page(page);
@@ -702,6 +722,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_NO_GGTT |
 		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
index 4cd54c569911..379a91780bd4 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
@@ -103,6 +103,8 @@ node_create(struct intel_engine_pool *pool, size_t sz)
 		return ERR_CAST(obj);
 	}
 
+	i915_gem_object_set_readonly(obj);
+
 	node->obj = obj;
 	return node;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index a82cea95c2f2..9dd8c299cb2d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -475,12 +475,13 @@ struct intel_engine_cs {
 
 	struct intel_engine_hangcheck hangcheck;
 
-#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
+#define I915_ENGINE_USING_CMD_PARSER BIT(0)
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
 #define I915_ENGINE_IS_VIRTUAL       BIT(5)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
 	unsigned int flags;
 
 	/*
@@ -541,9 +542,15 @@ struct intel_engine_cs {
 };
 
 static inline bool
-intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
+intel_engine_using_cmd_parser(const struct intel_engine_cs *engine)
 {
-	return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
+	return engine->flags & I915_ENGINE_USING_CMD_PARSER;
+}
+
+static inline bool
+intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER;
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 1363e069ec83..fac75afed35b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 	GEM_BUG_ON(!gt->awake);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
+
 	intel_enable_gt_powersave(i915);
 
 	i915_update_gfx_val(i915);
@@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf)
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
+		i915_rc6_ctx_wa_check(i915);
+		intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+	}
+
 	/* Everything switched off, flush any residual interrupt just in case */
 	intel_synchronize_irq(i915);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bdfcc7bdadbf..06a506c29463 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
 
+static void mark_eio(struct i915_request *rq)
+{
+	if (!i915_request_signaled(rq))
+		dma_fence_set_error(&rq->fence, -EIO);
+	i915_request_mark_complete(rq);
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -1236,6 +1243,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				submit = true;
 				last = rq;
 			}
+			i915_request_put(rq);
 
 			/*
 			 * Hmm, we have a bunch of virtual engine requests,
@@ -2574,12 +2582,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	__execlists_reset(engine, true);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		if (!i915_request_signaled(rq))
-			dma_fence_set_error(&rq->fence, -EIO);
-
-		i915_request_mark_complete(rq);
-	}
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2587,9 +2591,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
+			mark_eio(rq);
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2605,13 +2608,15 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		if (ve->request) {
-			ve->request->engine = engine;
-			__i915_request_submit(ve->request);
-			dma_fence_set_error(&ve->request->fence, -EIO);
-			i915_request_mark_complete(ve->request);
+		rq = fetch_and_zero(&ve->request);
+		if (rq) {
+			mark_eio(rq);
+
+			rq->engine = engine;
+			__i915_request_submit(rq);
+			i915_request_put(rq);
+
 			ve->base.execlists.queue_priority_hint = INT_MIN;
-			ve->request = NULL;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
@@ -3615,6 +3620,8 @@ submit_engine:
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	struct i915_request *old;
+	unsigned long flags;
 
 	GEM_TRACE("%s: rq=%llx:%lld\n",
 		  ve->base.name,
@@ -3623,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	GEM_BUG_ON(ve->request);
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	spin_lock_irqsave(&ve->base.active.lock, flags);
+
+	old = ve->request;
+	if (old) { /* background completion event from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(old));
+		__i915_request_submit(old);
+		i915_request_put(old);
+	}
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
-	WRITE_ONCE(ve->request, rq);
+	if (i915_request_completed(rq)) {
+		__i915_request_submit(rq);
 
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
+		ve->base.execlists.queue_priority_hint = INT_MIN;
+		ve->request = NULL;
+	} else {
+		ve->base.execlists.queue_priority_hint = rq_prio(rq);
+		ve->request = i915_request_get(rq);
+
+		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+		list_move_tail(&rq->sched.link, virtual_queue(ve));
+
+		tasklet_schedule(&ve->base.execlists.tasklet);
+	}
 
-	tasklet_schedule(&ve->base.execlists.tasklet);
+	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
 static struct ve_bond *
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 728704bbbe18..cea184a7dde9 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -199,14 +199,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 	MOCS_ENTRY(15, \
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \
 		   L3_3_WB), \
-	/* Bypass LLC - Uncached (EHL+) */ \
-	MOCS_ENTRY(16, \
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
-		   L3_1_UC), \
-	/* Bypass LLC - L3 (Read-Only) (EHL+) */ \
-	MOCS_ENTRY(17, \
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \
-		   L3_3_WB), \
 	/* Self-Snoop - L3 + LLC */ \
 	MOCS_ENTRY(18, \
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \
@@ -270,7 +262,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
 		   L3_1_UC),
 	/* HW Special Case (Displayable) */
 	MOCS_ENTRY(61,
-		   LE_1_UC | LE_TC_1_LLC | LE_SCF(1),
+		   LE_1_UC | LE_TC_1_LLC,
 		   L3_3_WB),
 };
 
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 13044c027f27..4bfaefdf548d 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -498,8 +498,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
 		goto out_free_gem;
 	}
 
-	i915_gem_object_put(obj);
-
 	ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR);
 	if (ret < 0) {
 		gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret);
@@ -524,6 +522,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
 		    file_count(dmabuf->file),
 		    kref_read(&obj->base.refcount));
 
+	i915_gem_object_put(obj);
+
 	return dmabuf_fd;
 
 out_free_dmabuf:
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 24555102e198..f24096e27bef 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -53,13 +53,11 @@
  * granting userspace undue privileges. There are three categories of privilege.
  *
  * First, commands which are explicitly defined as privileged or which should
- * only be used by the kernel driver. The parser generally rejects such
- * commands, though it may allow some from the drm master process.
+ * only be used by the kernel driver. The parser rejects such commands
  *
  * Second, commands which access registers. To support correct/enhanced
  * userspace functionality, particularly certain OpenGL extensions, the parser
- * provides a whitelist of registers which userspace may safely access (for both
- * normal and drm master processes).
+ * provides a whitelist of registers which userspace may safely access
  *
  * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
  * The parser always rejects such commands.
@@ -84,9 +82,9 @@
  * in the per-engine command tables.
  *
  * Other command table entries map fairly directly to high level categories
- * mentioned above: rejected, master-only, register whitelist. The parser
- * implements a number of checks, including the privileged memory checks, via a
- * general bitmasking mechanism.
+ * mentioned above: rejected, register whitelist. The parser implements a number
+ * of checks, including the privileged memory checks, via a general bitmasking
+ * mechanism.
  */
 
 /*
@@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor {
 	 * CMD_DESC_REJECT: The command is never allowed
 	 * CMD_DESC_REGISTER: The command should be checked against the
 	 *                    register whitelist for the appropriate ring
-	 * CMD_DESC_MASTER: The command is allowed if the submitting process
-	 *                  is the DRM master
 	 */
 	u32 flags;
 #define CMD_DESC_FIXED    (1<<0)
@@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor {
 #define CMD_DESC_REJECT   (1<<2)
 #define CMD_DESC_REGISTER (1<<3)
 #define CMD_DESC_BITMASK  (1<<4)
-#define CMD_DESC_MASTER   (1<<5)
 
 	/*
 	 * The command's unique identification bits and the bitmask to get them.
@@ -194,7 +189,7 @@ struct drm_i915_cmd_table {
 #define CMD(op, opm, f, lm, fl, ...)				\
 	{							\
 		.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0),	\
-		.cmd = { (op), ~0u << (opm) },			\
+		.cmd = { (op & ~0u << (opm)), ~0u << (opm) },	\
 		.length = { (lm) },				\
 		__VA_ARGS__					\
 	}
@@ -209,14 +204,13 @@ struct drm_i915_cmd_table {
 #define R CMD_DESC_REJECT
 #define W CMD_DESC_REGISTER
 #define B CMD_DESC_BITMASK
-#define M CMD_DESC_MASTER
 
 /*            Command                          Mask   Fixed Len   Action
 	      ---------------------------------------------------------- */
-static const struct drm_i915_cmd_descriptor common_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
 	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
 	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      R  ),
-	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      M  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      R  ),
 	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
 	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
 	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
@@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {
 	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
 };
 
-static const struct drm_i915_cmd_descriptor render_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
 	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_PREDICATE,                     SMI,    F,  1,      S  ),
@@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  MI_URB_ATOMIC_ALLOC,              SMI,    F,  1,      S  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
 	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
@@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS,  S3D,   !F,  0x1FF,  S  ),
 };
 
-static const struct drm_i915_cmd_descriptor video_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = {
 	CMD(  MFX_WAIT,                         SMFX,   F,  1,      S  ),
 };
 
-static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
 	      }},						       ),
 };
 
-static const struct drm_i915_cmd_descriptor blt_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
 	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  B,
 	      .bits = {{
@@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = {
 };
 
 static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 };
 
+/*
+ * For Gen9 we can still rely on the h/w to enforce cmd security, and only
+ * need to re-enforce the register access checks. We therefore only need to
+ * teach the cmdparser how to find the end of each command, and identify
+ * register accesses. The table doesn't need to reject any commands, and so
+ * the only commands listed here are:
+ *   1) Those that touch registers
+ *   2) Those that do not have the default 8-bit length
+ *
+ * Note that the default MI length mask chosen for this table is 0xFF, not
+ * the 0x3F used on older devices. This is because the vast majority of MI
+ * cmds on Gen9 use a standard 8-bit Length field.
+ * All the Gen9 blitter instructions are standard 0xFF length mask, and
+ * none allow access to non-general registers, so in fact no BLT cmds are
+ * included in the table at all.
+ *
+ */
+static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
+	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
+	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      S  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      S  ),
+	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
+	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      S  ),
+	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_STORE_REGISTER_MEM_GEN8,       SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_REGISTER_MEM_GEN8,        SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,    !F,  0xFF,  W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
+
+	/*
+	 * We allow BB_START but apply further checks. We just sanitize the
+	 * basic fields here.
+	 */
+#define MI_BB_START_OPERAND_MASK   GENMASK(SMI-1, 0)
+#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
+	CMD(  MI_BATCH_BUFFER_START_GEN8,       SMI,    !F,  0xFF,  B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_BB_START_OPERAND_MASK,
+			.expected = MI_BB_START_OPERAND_EXPECT,
+	      }},						       ),
+};
+
 static const struct drm_i915_cmd_descriptor noop_desc =
 	CMD(MI_NOOP, SMI, F, 1, S);
 
@@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc =
 #undef R
 #undef W
 #undef B
-#undef M
 
-static const struct drm_i915_cmd_table gen7_render_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 	{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_video_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ video_cmds, ARRAY_SIZE(video_cmds) },
+static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ vecs_cmds, ARRAY_SIZE(vecs_cmds) },
+static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
 };
 
+static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
+	{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
+};
+
+
 /*
  * Register whitelists, sorted by increasing register offset.
  */
@@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
 };
 
-static const struct drm_i915_reg_descriptor ivb_master_regs[] = {
-	REG32(FORCEWAKE_MT),
-	REG32(DERRMR),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)),
-};
-
-static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
-	REG32(FORCEWAKE_MT),
-	REG32(DERRMR),
+static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
+	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
+	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
+	REG32(BCS_SWCTRL),
+	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+	REG64_IDX(BCS_GPR, 0),
+	REG64_IDX(BCS_GPR, 1),
+	REG64_IDX(BCS_GPR, 2),
+	REG64_IDX(BCS_GPR, 3),
+	REG64_IDX(BCS_GPR, 4),
+	REG64_IDX(BCS_GPR, 5),
+	REG64_IDX(BCS_GPR, 6),
+	REG64_IDX(BCS_GPR, 7),
+	REG64_IDX(BCS_GPR, 8),
+	REG64_IDX(BCS_GPR, 9),
+	REG64_IDX(BCS_GPR, 10),
+	REG64_IDX(BCS_GPR, 11),
+	REG64_IDX(BCS_GPR, 12),
+	REG64_IDX(BCS_GPR, 13),
+	REG64_IDX(BCS_GPR, 14),
+	REG64_IDX(BCS_GPR, 15),
 };
 
 #undef REG64
@@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
 struct drm_i915_reg_table {
 	const struct drm_i915_reg_descriptor *regs;
 	int num_regs;
-	bool master;
 };
 
 static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
 };
 
 static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
 };
 
 static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
-	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
+	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
 };
 
 static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
+};
+
+static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
+	{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
 };
 
 static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
@@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
+static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
+		return 0xFF;
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
 static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
 				 const struct drm_i915_cmd_table *cmd_tables,
 				 int cmd_table_count)
@@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN(engine->i915, 7))
+	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
+					  engine->class == COPY_ENGINE_CLASS))
 		return;
 
 	switch (engine->class) {
 	case RENDER_CLASS:
 		if (IS_HASWELL(engine->i915)) {
-			cmd_tables = hsw_render_ring_cmds;
+			cmd_tables = hsw_render_ring_cmd_table;
 			cmd_table_count =
-				ARRAY_SIZE(hsw_render_ring_cmds);
+				ARRAY_SIZE(hsw_render_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_render_cmds;
-			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
+			cmd_tables = gen7_render_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
 		}
 
 		if (IS_HASWELL(engine->i915)) {
@@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 			engine->reg_tables = ivb_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
 		}
-
 		engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
 		break;
 	case VIDEO_DECODE_CLASS:
-		cmd_tables = gen7_video_cmds;
-		cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
+		cmd_tables = gen7_video_cmd_table;
+		cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case COPY_ENGINE_CLASS:
-		if (IS_HASWELL(engine->i915)) {
-			cmd_tables = hsw_blt_ring_cmds;
-			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
+		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
+		if (IS_GEN(engine->i915, 9)) {
+			cmd_tables = gen9_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
+			engine->get_cmd_length_mask =
+				gen9_blt_get_cmd_length_mask;
+
+			/* BCS Engine unsafe without parser */
+			engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
+		} else if (IS_HASWELL(engine->i915)) {
+			cmd_tables = hsw_blt_ring_cmd_table;
+			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_blt_cmds;
-			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
+			cmd_tables = gen7_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
 		}
 
-		if (IS_HASWELL(engine->i915)) {
+		if (IS_GEN(engine->i915, 9)) {
+			engine->reg_tables = gen9_blt_reg_tables;
+			engine->reg_table_count =
+				ARRAY_SIZE(gen9_blt_reg_tables);
+		} else if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
 			engine->reg_tables = ivb_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
 		}
-
-		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
 		break;
 	case VIDEO_ENHANCEMENT_CLASS:
-		cmd_tables = hsw_vebox_cmds;
-		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
+		cmd_tables = hsw_vebox_cmd_table;
+		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
 		/* VECS can use the same length_mask function as VCS */
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
@@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		return;
 	}
 
-	engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
+	engine->flags |= I915_ENGINE_USING_CMD_PARSER;
 }
 
 /**
@@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
 {
-	if (!intel_engine_needs_cmd_parser(engine))
+	if (!intel_engine_using_cmd_parser(engine))
 		return;
 
 	fini_hash_table(engine);
@@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
 }
 
 static const struct drm_i915_reg_descriptor *
-find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
+find_reg(const struct intel_engine_cs *engine, u32 addr)
 {
 	const struct drm_i915_reg_table *table = engine->reg_tables;
+	const struct drm_i915_reg_descriptor *reg = NULL;
 	int count = engine->reg_table_count;
 
-	for (; count > 0; ++table, --count) {
-		if (!table->master || is_master) {
-			const struct drm_i915_reg_descriptor *reg;
+	for (; !reg && (count > 0); ++table, --count)
+		reg = __find_reg(table->regs, table->num_regs, addr);
 
-			reg = __find_reg(table->regs, table->num_regs, addr);
-			if (reg != NULL)
-				return reg;
-		}
-	}
-
-	return NULL;
+	return reg;
 }
 
 /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
@@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
-		      const u32 *cmd, u32 length,
-		      const bool is_master)
+		      const u32 *cmd, u32 length)
 {
 	if (desc->flags & CMD_DESC_SKIP)
 		return true;
@@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		return false;
 	}
 
-	if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
-		DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
-				 *cmd);
-		return false;
-	}
-
 	if (desc->flags & CMD_DESC_REGISTER) {
 		/*
 		 * Get the distance between individual register offset
@@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		     offset += step) {
 			const u32 reg_addr = cmd[offset] & desc->reg.mask;
 			const struct drm_i915_reg_descriptor *reg =
-				find_reg(engine, is_master, reg_addr);
+				find_reg(engine, reg_addr);
 
 			if (!reg) {
 				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
@@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 	return true;
 }
 
+static int check_bbstart(const struct i915_gem_context *ctx,
+			 u32 *cmd, u32 offset, u32 length,
+			 u32 batch_len,
+			 u64 batch_start,
+			 u64 shadow_batch_start)
+{
+	u64 jump_offset, jump_target;
+	u32 target_cmd_offset, target_cmd_index;
+
+	/* For igt compatibility on older platforms */
+	if (CMDPARSER_USES_GGTT(ctx->i915)) {
+		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
+		return -EACCES;
+	}
+
+	if (length != 3) {
+		DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
+			  length);
+		return -EINVAL;
+	}
+
+	jump_target = *(u64*)(cmd+1);
+	jump_offset = jump_target - batch_start;
+
+	/*
+	 * Any underflow of jump_target is guaranteed to be outside the range
+	 * of a u32, so >= test catches both too large and too small
+	 */
+	if (jump_offset >= batch_len) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	/*
+	 * This cannot overflow a u32 because we already checked jump_offset
+	 * is within the BB, and the batch_len is a u32
+	 */
+	target_cmd_offset = lower_32_bits(jump_offset);
+	target_cmd_index = target_cmd_offset / sizeof(u32);
+
+	*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+
+	if (target_cmd_index == offset)
+		return 0;
+
+	if (ctx->jump_whitelist_cmds <= target_cmd_index) {
+		DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
+		return -EINVAL;
+	} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+{
+	const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
+	const u32 exact_size = BITS_TO_LONGS(batch_cmds);
+	u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
+	unsigned long *next_whitelist;
+
+	if (CMDPARSER_USES_GGTT(ctx->i915))
+		return;
+
+	if (batch_cmds <= ctx->jump_whitelist_cmds) {
+		bitmap_zero(ctx->jump_whitelist, batch_cmds);
+		return;
+	}
+
+again:
+	next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
+	if (next_whitelist) {
+		kfree(ctx->jump_whitelist);
+		ctx->jump_whitelist = next_whitelist;
+		ctx->jump_whitelist_cmds =
+			next_size * BITS_PER_BYTE * sizeof(long);
+		return;
+	}
+
+	if (next_size > exact_size) {
+		next_size = exact_size;
+		goto again;
+	}
+
+	DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
+	bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+
+	return;
+}
+
 #define LENGTH_BIAS 2
 
 /**
  * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
+ * @ctx: the context in which the batch is to execute
  * @engine: the engine on which the batch is to execute
  * @batch_obj: the batch buffer in question
- * @shadow_batch_obj: copy of the batch buffer in question
+ * @batch_start: Canonical base address of batch
  * @batch_start_offset: byte offset in the batch at which execution starts
  * @batch_len: length of the commands in batch_obj
- * @is_master: is the submitting process the drm master?
+ * @shadow_batch_obj: copy of the batch buffer in question
+ * @shadow_batch_start: Canonical base address of shadow_batch_obj
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+
+int intel_engine_cmd_parser(struct i915_gem_context *ctx,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master)
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start)
 {
-	u32 *cmd, *batch_end;
+	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
 	bool needs_clflush_after = false;
@@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 		return PTR_ERR(cmd);
 	}
 
+	init_whitelist(ctx, batch_len);
+
 	/*
 	 * We use the batch length as size because the shadow object is as
 	 * large or larger and copy_batch() will write MI_NOPs to the extra
@@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 	do {
 		u32 length;
 
-		if (*cmd == MI_BATCH_BUFFER_END) {
-			if (needs_clflush_after) {
-				void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
-				drm_clflush_virt_range(ptr,
-						       (void *)(cmd + 1) - ptr);
-			}
+		if (*cmd == MI_BATCH_BUFFER_END)
 			break;
-		}
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
 			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
 					 *cmd);
 			ret = -EINVAL;
-			break;
-		}
-
-		/*
-		 * If the batch buffer contains a chained batch, return an
-		 * error that tells the caller to abort and dispatch the
-		 * workload as a non-secure batch.
-		 */
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
-			ret = -EACCES;
-			break;
+			goto err;
 		}
 
 		if (desc->flags & CMD_DESC_FIXED)
@@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 					 length,
 					 batch_end - cmd);
 			ret = -EINVAL;
-			break;
+			goto err;
 		}
 
-		if (!check_cmd(engine, desc, cmd, length, is_master)) {
+		if (!check_cmd(engine, desc, cmd, length)) {
 			ret = -EACCES;
+			goto err;
+		}
+
+		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+			ret = check_bbstart(ctx, cmd, offset, length,
+					    batch_len, batch_start,
+					    shadow_batch_start);
+
+			if (ret)
+				goto err;
 			break;
 		}
 
+		if (ctx->jump_whitelist_cmds > offset)
+			set_bit(offset, ctx->jump_whitelist);
+
 		cmd += length;
+		offset += length;
 		if  (cmd >= batch_end) {
 			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 			ret = -EINVAL;
-			break;
+			goto err;
 		}
 	} while (1);
 
+	if (needs_clflush_after) {
+		void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+
+		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
+	}
+
+err:
 	i915_gem_object_unpin_map(shadow_batch_obj);
 	return ret;
 }
@@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 
 	/* If the command parser is not enabled, report 0 - unsupported */
 	for_each_uabi_engine(engine, dev_priv) {
-		if (intel_engine_needs_cmd_parser(engine)) {
+		if (intel_engine_using_cmd_parser(engine)) {
 			active = true;
 			break;
 		}
@@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 	 *    the parser enabled.
 	 * 9. Don't whitelist or handle oacontrol specially, as ownership
 	 *    for oacontrol state is moving to i915-perf.
+	 * 10. Support for Gen9 BCS Parsing
 	 */
-	return 9;
+	return 10;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index bb6f86c7067a..3d717e282908 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -364,9 +364,6 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 	if (ret)
 		goto cleanup_vga_client;
 
-	/* must happen before intel_power_domains_init_hw() on VLV/CHV */
-	intel_update_rawclk(dev_priv);
-
 	intel_power_domains_init_hw(dev_priv, false);
 
 	intel_csr_ucode_init(dev_priv);
@@ -1850,6 +1847,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 	i915_gem_suspend_late(dev_priv);
 
+	i915_rc6_ctx_wa_suspend(dev_priv);
+
 	intel_uncore_suspend(&dev_priv->uncore);
 
 	intel_power_domains_suspend(dev_priv,
@@ -2053,6 +2052,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	intel_power_domains_resume(dev_priv);
 
+	i915_rc6_ctx_wa_resume(dev_priv);
+
 	intel_gt_sanitize(&dev_priv->gt, true);
 
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 772154e4073e..89b6112bd66b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -593,6 +593,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	bool ctx_corrupted;
+	intel_wakeref_t ctx_corrupted_wakeref;
 	u64 prev_hw_residency[4];
 	u64 cur_residency[4];
 };
@@ -1723,6 +1725,8 @@ struct drm_i915_private {
 		struct work_struct idle_work;
 	} gem;
 
+	u8 pch_ssc_use;
+
 	/* For i945gm vblank irq vs. C3 workaround */
 	struct {
 		struct work_struct work;
@@ -2073,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define VEBOX_MASK(dev_priv) \
 	ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS)
 
+/*
+ * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution
+ * All later gens can run the final buffer from the ppgtt
+ */
+#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7)
+
 #define HAS_LLC(dev_priv)	(INTEL_INFO(dev_priv)->has_llc)
 #define HAS_SNOOP(dev_priv)	(INTEL_INFO(dev_priv)->has_snoop)
 #define HAS_EDRAM(dev_priv)	((dev_priv)->edram_size_mb)
+#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6)
 #define HAS_WT(dev_priv)	((IS_HASWELL(dev_priv) || \
 				 IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv))
 
@@ -2108,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev_priv)	(IS_I830(dev_priv) || IS_I845G(dev_priv))
 
+#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)	\
+	(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
+
 /* WaRsDisableCoarsePowerGating:skl,cnl */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || \
-	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
+	(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
@@ -2282,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
 
+struct i915_vma * __must_check
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags);
+
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
 static inline int __must_check
@@ -2391,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+int intel_engine_cmd_parser(struct i915_gem_context *cxt,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 user_batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master);
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start);
 
 /* intel_device_info.c */
 static inline struct intel_device_info *
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..98305d987ac1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -964,11 +964,28 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_address_space *vm = &dev_priv->ggtt.vm;
+
+	return i915_gem_object_pin(obj, vm, view, size, alignment,
+				   flags | PIN_GLOBAL);
+}
+
+struct i915_vma *
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags)
+{
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	int ret;
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
+	if (i915_gem_object_never_bind_ggtt(obj))
+		return ERR_PTR(-ENODEV);
+
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
 		/* If the required space is larger than the available
@@ -1035,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	ret = i915_vma_pin(vma, size, alignment, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 5d9101376a3d..9f1517af5b7f 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES);
 		break;
 	case I915_PARAM_HAS_SECURE_BATCHES:
-		value = capable(CAP_SYS_ADMIN);
+		value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN);
 		break;
 	case I915_PARAM_CMD_PARSER_VERSION:
 		value = i915_cmd_parser_get_version(i915);
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 8e251e719390..212acaef581e 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -843,8 +843,8 @@ create_event_attributes(struct i915_pmu *pmu)
 		const char *name;
 		const char *unit;
 	} events[] = {
-		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"),
-		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"),
+		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"),
+		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"),
 		__event(I915_PMU_INTERRUPTS, "interrupts", NULL),
 		__event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"),
 	};
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2abd199093c5..f8ee9aba3955 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
+#define GEN8_RC6_CTX_INFO		_MMIO(0x8504)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1 << 13)
 #define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
@@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  */
 #define BCS_SWCTRL _MMIO(0x22200)
 
+/* There are 16 GPR registers */
+#define BCS_GPR(n)	_MMIO(0x22600 + (n) * 8)
+#define BCS_GPR_UDW(n)	_MMIO(0x22600 + (n) * 8 + 4)
+
 #define GPGPU_THREADS_DISPATCHED        _MMIO(0x2290)
 #define GPGPU_THREADS_DISPATCHED_UDW	_MMIO(0x2290 + 4)
 #define HS_INVOCATION_COUNT             _MMIO(0x2300)
@@ -7211,6 +7217,10 @@ enum {
 #define TGL_DMC_DEBUG_DC5_COUNT	_MMIO(0x101084)
 #define TGL_DMC_DEBUG_DC6_COUNT	_MMIO(0x101088)
 
+/* Display Internal Timeout Register */
+#define RM_TIMEOUT		_MMIO(0x42060)
+#define  MMIO_TIMEOUT_US(us)	((us) << 0)
+
 /* interrupts */
 #define DE_MASTER_IRQ_CONTROL   (1 << 31)
 #define DE_SPRITEB_FLIP_DONE    (1 << 29)
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 7b84ebca2901..3eba8a2b39c2 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -177,9 +177,37 @@ static inline int rq_prio(const struct i915_request *rq)
 	return rq->sched.attr.priority | __NO_PREEMPTION;
 }
 
-static void kick_submission(struct intel_engine_cs *engine, int prio)
+static inline bool need_preempt(int prio, int active)
 {
-	const struct i915_request *inflight = *engine->execlists.active;
+	/*
+	 * Allow preemption of low -> normal -> high, but we do
+	 * not allow low priority tasks to preempt other low priority
+	 * tasks under the impression that latency for low priority
+	 * tasks does not matter (as much as background throughput),
+	 * so kiss.
+	 */
+	return prio >= max(I915_PRIORITY_NORMAL, active);
+}
+
+static void kick_submission(struct intel_engine_cs *engine,
+			    const struct i915_request *rq,
+			    int prio)
+{
+	const struct i915_request *inflight;
+
+	/*
+	 * We only need to kick the tasklet once for the high priority
+	 * new context we add into the queue.
+	 */
+	if (prio <= engine->execlists.queue_priority_hint)
+		return;
+
+	rcu_read_lock();
+
+	/* Nothing currently active? We're overdue for a submission! */
+	inflight = execlists_active(&engine->execlists);
+	if (!inflight)
+		goto unlock;
 
 	/*
 	 * If we are already the currently executing context, don't
@@ -188,10 +216,15 @@ static void kick_submission(struct intel_engine_cs *engine, int prio)
 	 * tasklet, i.e. we have not change the priority queue
 	 * sufficiently to oust the running context.
 	 */
-	if (!inflight || !i915_scheduler_need_preempt(prio, rq_prio(inflight)))
-		return;
+	if (inflight->hw_context == rq->hw_context)
+		goto unlock;
 
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	engine->execlists.queue_priority_hint = prio;
+	if (need_preempt(prio, rq_prio(inflight)))
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+
+unlock:
+	rcu_read_unlock();
 }
 
 static void __i915_schedule(struct i915_sched_node *node,
@@ -317,13 +350,8 @@ static void __i915_schedule(struct i915_sched_node *node,
 			list_move_tail(&node->link, cache.priolist);
 		}
 
-		if (prio <= engine->execlists.queue_priority_hint)
-			continue;
-
-		engine->execlists.queue_priority_hint = prio;
-
 		/* Defer (tasklet) submission until after all of our updates. */
-		kick_submission(engine, prio);
+		kick_submission(engine, node_to_request(node), prio);
 	}
 
 	spin_unlock(&engine->active.lock);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ee027abb80..2efe1d12d5a9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 		   PWM1_GATING_DIS | PWM2_GATING_DIS);
+
+	/*
+	 * Lower the display internal timeout.
+	 * This is needed to avoid any hard hangs when DSI port PLL
+	 * is off and a MMIO access is attempted by any privilege
+	 * application, using batch buffers or any other means.
+	 */
+	I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
 }
 
 static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
 	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
+static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
+{
+	return !I915_READ(GEN8_RC6_CTX_INFO);
+}
+
+static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
+		i915->gt_pm.rc6.ctx_corrupted = true;
+		i915->gt_pm.rc6.ctx_corrupted_wakeref =
+			intel_runtime_pm_get(&i915->runtime_pm);
+	}
+}
+
+static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted) {
+		intel_runtime_pm_put(&i915->runtime_pm,
+				     i915->gt_pm.rc6.ctx_corrupted_wakeref);
+		i915->gt_pm.rc6.ctx_corrupted = false;
+	}
+}
+
+/**
+ * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to clean up the RC6 CTX WA before system suspend.
+ */
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		intel_runtime_pm_put(&i915->runtime_pm,
+				     i915->gt_pm.rc6.ctx_corrupted_wakeref);
+}
+
+/**
+ * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to re-init the RC6 CTX WA after system resume.
+ */
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
+{
+	if (!i915->gt_pm.rc6.ctx_corrupted)
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		i915->gt_pm.rc6.ctx_corrupted_wakeref =
+			intel_runtime_pm_get(&i915->runtime_pm);
+		return;
+	}
+
+	DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
+	i915->gt_pm.rc6.ctx_corrupted = false;
+}
+
+static void intel_disable_rc6(struct drm_i915_private *dev_priv);
+
+/**
+ * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
+ * @i915: i915 device
+ *
+ * Check if an RC6 CTX corruption has happened since the last check and if so
+ * disable RC6 and runtime power management.
+ *
+ * Return false if no context corruption has happened since the last call of
+ * this function, true otherwise.
+*/
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return false;
+
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		return false;
+
+	if (!i915_rc6_ctx_corrupted(i915))
+		return false;
+
+	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+
+	intel_disable_rc6(i915);
+	i915->gt_pm.rc6.ctx_corrupted = true;
+	i915->gt_pm.rc6.ctx_corrupted_wakeref =
+		intel_runtime_pm_get_noresume(&i915->runtime_pm);
+
+	return true;
+}
+
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 		pm_runtime_get(&dev_priv->drm.pdev->dev);
 	}
 
+	i915_rc6_ctx_wa_init(dev_priv);
+
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_init_gt_powersave(dev_priv);
@@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 	if (IS_VALLEYVIEW(dev_priv))
 		valleyview_cleanup_gt_powersave(dev_priv);
 
+	i915_rc6_ctx_wa_cleanup(dev_priv);
+
 	if (!HAS_RC6(dev_priv))
 		pm_runtime_put(&dev_priv->drm.pdev->dev);
 }
@@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 	i915->gt_pm.llc_pstate.enabled = false;
 }
 
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
 
@@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
 	dev_priv->gt_pm.rc6.enabled = false;
 }
 
+static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+
+	mutex_lock(&rps->lock);
+	__intel_disable_rc6(dev_priv);
+	mutex_unlock(&rps->lock);
+}
+
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	intel_disable_rc6(dev_priv);
+	__intel_disable_rc6(dev_priv);
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
@@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv)
 	if (dev_priv->gt_pm.rc6.enabled)
 		return;
 
+	if (dev_priv->gt_pm.rc6.ctx_corrupted)
+		return;
+
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_enable_rc6(dev_priv);
 	else if (IS_VALLEYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index e3573e1e16e3..0f7390c850ec 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915);
 void gen6_rps_busy(struct drm_i915_private *dev_priv);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
 void gen6_rps_boost(struct i915_request *rq);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 663ff9f4fac9..1e7b1be25bb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -26,6 +26,8 @@
 #include "dsi_cfg.h"
 #include "msm_kms.h"
 
+#define DSI_RESET_TOGGLE_DELAY_MS 20
+
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
 	u32 ver;
@@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host)
 	wmb(); /* clocks need to be enabled before reset */
 
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb(); /* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 }
 
@@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
 
 	/* dsi controller can only be reset while clocks are running */
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb();	/* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 	wmb();	/* controller out of reset */
 	dsi_write(msm_host, REG_DSI_CTRL, data0);
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index bc2ddeb55f5d..f21bc8a7ee3a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -556,11 +556,11 @@ static int panfrost_probe(struct platform_device *pdev)
 	return 0;
 
 err_out2:
+	pm_runtime_disable(pfdev->dev);
 	panfrost_devfreq_fini(pfdev);
 err_out1:
 	panfrost_device_fini(pfdev);
 err_out0:
-	pm_runtime_disable(pfdev->dev);
 	drm_dev_put(ddev);
 	return err;
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f67ed925c0ef..8822ec13a0d6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
 	pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES);
 	pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES);
 	pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES);
+	pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
+	pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
+	pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
 	pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
 	for (i = 0; i < 4; i++)
 		pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..21f34d44aac2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	mutex_lock(&pfdev->reset_lock);
+	if (!mutex_trylock(&pfdev->reset_lock))
+		return;
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+		drm_sched_stop(sched, sched_job);
+		if (js != i)
+			/* Ensure any timeouts on other slots have finished */
+			cancel_delayed_work_sync(&sched->work_tdr);
+	}
 
-	if (sched_job)
-		drm_sched_increase_karma(sched_job);
+	drm_sched_increase_karma(sched_job);
 
 	spin_lock_irqsave(&pfdev->js->job_lock, flags);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index bdd990568476..a3ed64a1f15e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -224,9 +224,9 @@ static size_t get_pgsize(u64 addr, size_t size)
 	return SZ_2M;
 }
 
-void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
-			      struct panfrost_mmu *mmu,
-			      u64 iova, size_t size)
+static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
+				     struct panfrost_mmu *mmu,
+				     u64 iova, size_t size)
 {
 	if (mmu->as < 0)
 		return;
@@ -406,11 +406,11 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
 	spin_lock(&pfdev->as_lock);
 	list_for_each_entry(mmu, &pfdev->as_lru_list, list) {
 		if (as == mmu->as)
-			break;
+			goto found_mmu;
 	}
-	if (as != mmu->as)
-		goto out;
+	goto out;
 
+found_mmu:
 	priv = container_of(mmu, struct panfrost_file_priv, mmu);
 
 	spin_lock(&priv->mm_lock);
@@ -432,7 +432,8 @@ out:
 
 #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
 
-int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
+static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
+				       u64 addr)
 {
 	int ret, i;
 	struct panfrost_gem_object *bo;
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 83c57d325ca8..2dba192bf198 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -16,6 +16,7 @@
 #include "panfrost_issues.h"
 #include "panfrost_job.h"
 #include "panfrost_mmu.h"
+#include "panfrost_perfcnt.h"
 #include "panfrost_regs.h"
 
 #define COUNTERS_PER_BLOCK		64
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d0bc91ed7c90..4528f4dc0b2d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -379,7 +379,9 @@ radeon_pci_remove(struct pci_dev *pdev)
 static void
 radeon_pci_shutdown(struct pci_dev *pdev)
 {
+#ifdef CONFIG_PPC64
 	struct drm_device *ddev = pci_get_drvdata(pdev);
+#endif
 
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown
@@ -387,11 +389,15 @@ radeon_pci_shutdown(struct pci_dev *pdev)
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
 
+#ifdef CONFIG_PPC64
 	/* Some adapters need to be suspended before a
-	* shutdown occurs in order to prevent an error
-	* during kexec.
-	*/
+	 * shutdown occurs in order to prevent an error
+	 * during kexec.
+	 * Make this power specific becauase it breaks
+	 * some non-power boards.
+	 */
 	radeon_suspend_kms(ddev, true, true, false);
+#endif
 }
 
 static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 460fd98e40a7..a0b382a637a6 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -1958,6 +1958,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 		case 0x682C:
 			si_pi->cac_weights = cac_weights_cape_verde_pro;
 			si_pi->dte_data = dte_data_sun_xt;
+			update_dte_from_pl2 = true;
 			break;
 		case 0x6825:
 		case 0x6827:
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74d82dc..f39b97ed4ade 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			s_job->s_fence->parent = NULL;
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 04c721d0d3b9..b89439ed210d 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 
 	WARN_ON(!tcon->quirks->has_channel_0);
 
-	tcon->dclk_min_div = 6;
+	tcon->dclk_min_div = 1;
 	tcon->dclk_max_div = 127;
 	sun4i_tcon0_mode_set_common(tcon, mode);
 
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 504763423d46..a46ac284dd5e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -63,7 +63,6 @@ config TINYDRM_REPAPER
 	depends on DRM && SPI
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
-	depends on THERMAL || !THERMAL
 	help
 	  DRM driver for the following Pervasive Displays panels:
 	  1.44" TFT EPD Panel (E1144CS021)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20ff56f27aa4..98819462f025 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 	kref_get(&bo->list_kref);
 
-	if (bo->ttm && !(bo->ttm->page_flags &
-			 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
+	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
+				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
 		kref_get(&bo->list_kref);
 	}
@@ -878,11 +879,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	if (!bo) {
 		if (busy_bo)
-			ttm_bo_get(busy_bo);
+			kref_get(&busy_bo->list_kref);
 		spin_unlock(&glob->lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
-			ttm_bo_put(busy_bo);
+			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 76eedb963693..46dc3de7e81b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		else
 			ret = vmf_insert_pfn(&cvma, address, pfn);
 
-		/*
-		 * Somebody beat us to this PTE or prefaulting to
-		 * an already populated PTE, or prefaulting error.
-		 */
-
-		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
-			break;
-		else if (unlikely(ret & VM_FAULT_ERROR))
-			goto out_io_unlock;
+		/* Never error on prefaulted PTEs */
+		if (unlikely((ret & VM_FAULT_ERROR))) {
+			if (i == 0)
+				goto out_io_unlock;
+			else
+				break;
+		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 5d80507b539b..19c092d75266 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -557,13 +557,16 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	if (args->bcl_start != args->bcl_end) {
 		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
-		if (!bin)
+		if (!bin) {
+			v3d_job_put(&render->base);
 			return -ENOMEM;
+		}
 
 		ret = v3d_job_init(v3d, file_priv, &bin->base,
 				   v3d_job_free, args->in_sync_bcl);
 		if (ret) {
 			v3d_job_put(&render->base);
+			kfree(bin);
 			return ret;
 		}
 
diff --git a/drivers/hid/hid-axff.c b/drivers/hid/hid-axff.c
index 6654c1550e2e..fbe4e16ab029 100644
--- a/drivers/hid/hid-axff.c
+++ b/drivers/hid/hid-axff.c
@@ -63,13 +63,20 @@ static int axff_init(struct hid_device *hid)
 {
 	struct axff_device *axff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int field_count = 0;
 	int i, j;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3eaee2c37931..63fdbf09b044 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1139,6 +1139,7 @@ int hid_open_report(struct hid_device *device)
 	__u8 *start;
 	__u8 *buf;
 	__u8 *end;
+	__u8 *next;
 	int ret;
 	static int (*dispatch_type[])(struct hid_parser *parser,
 				      struct hid_item *item) = {
@@ -1192,7 +1193,8 @@ int hid_open_report(struct hid_device *device)
 	device->collection_size = HID_DEFAULT_NUM_COLLECTIONS;
 
 	ret = -EINVAL;
-	while ((start = fetch_item(start, end, &item)) != NULL) {
+	while ((next = fetch_item(start, end, &item)) != NULL) {
+		start = next;
 
 		if (item.format != HID_ITEM_FORMAT_SHORT) {
 			hid_err(device, "unexpected long global item\n");
@@ -1230,7 +1232,8 @@ int hid_open_report(struct hid_device *device)
 		}
 	}
 
-	hid_err(device, "item fetching failed at offset %d\n", (int)(end - start));
+	hid_err(device, "item fetching failed at offset %u/%u\n",
+		size - (unsigned int)(end - start), size);
 err:
 	kfree(parser->collection_stack);
 alloc_err:
diff --git a/drivers/hid/hid-dr.c b/drivers/hid/hid-dr.c
index 17e17f9a597b..947f19f8685f 100644
--- a/drivers/hid/hid-dr.c
+++ b/drivers/hid/hid-dr.c
@@ -75,13 +75,19 @@ static int drff_init(struct hid_device *hid)
 {
 	struct drff_device *drff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-emsff.c b/drivers/hid/hid-emsff.c
index 7cd5651872d3..c34f2e5a049f 100644
--- a/drivers/hid/hid-emsff.c
+++ b/drivers/hid/hid-emsff.c
@@ -47,13 +47,19 @@ static int emsff_init(struct hid_device *hid)
 {
 	struct emsff_device *emsff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-gaff.c b/drivers/hid/hid-gaff.c
index 0f95c96b70f8..ecbd3995a4eb 100644
--- a/drivers/hid/hid-gaff.c
+++ b/drivers/hid/hid-gaff.c
@@ -64,14 +64,20 @@ static int gaff_init(struct hid_device *hid)
 {
 	struct gaff_device *gaff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct list_head *report_ptr = report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 84f8c127ebdc..d86a9189e88f 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -470,6 +470,10 @@ static const struct hid_device_id hammer_devices[] = {
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) },
diff --git a/drivers/hid/hid-holtekff.c b/drivers/hid/hid-holtekff.c
index 10a720558830..8619b80c834c 100644
--- a/drivers/hid/hid-holtekff.c
+++ b/drivers/hid/hid-holtekff.c
@@ -124,13 +124,19 @@ static int holtekff_init(struct hid_device *hid)
 {
 	struct holtekff_device *holtekff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output report found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 76969a22b0f2..447e8db21174 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -476,6 +476,8 @@
 #define USB_DEVICE_ID_GOOGLE_STAFF	0x502b
 #define USB_DEVICE_ID_GOOGLE_WAND	0x502d
 #define USB_DEVICE_ID_GOOGLE_WHISKERS	0x5030
+#define USB_DEVICE_ID_GOOGLE_MASTERBALL	0x503c
+#define USB_DEVICE_ID_GOOGLE_MAGNEMITE	0x503d
 
 #define USB_VENDOR_ID_GOTOP		0x08f2
 #define USB_DEVICE_ID_SUPER_Q2		0x007f
diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c
index dd1a6c3a7de6..73d07e35f12a 100644
--- a/drivers/hid/hid-lg2ff.c
+++ b/drivers/hid/hid-lg2ff.c
@@ -50,11 +50,17 @@ int lg2ff_init(struct hid_device *hid)
 {
 	struct lg2ff_device *lg2ff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7);
 	if (!report)
diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c
index 9ecb6fd06203..b7e1949f3cf7 100644
--- a/drivers/hid/hid-lg3ff.c
+++ b/drivers/hid/hid-lg3ff.c
@@ -117,12 +117,19 @@ static const signed short ff3_joystick_ac[] = {
 
 int lg3ff_init(struct hid_device *hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const signed short *ff_bits = ff3_joystick_ac;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35))
 		return -ENODEV;
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 03f0220062ca..5e6a0cef2a06 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -1253,8 +1253,8 @@ static int lg4ff_handle_multimode_wheel(struct hid_device *hid, u16 *real_produc
 
 int lg4ff_init(struct hid_device *hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
@@ -1266,6 +1266,13 @@ int lg4ff_init(struct hid_device *hid)
 	int mmode_ret, mmode_idx = -1;
 	u16 real_product_id;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c
index c79a6ec43745..aed4ddc397a9 100644
--- a/drivers/hid/hid-lgff.c
+++ b/drivers/hid/hid-lgff.c
@@ -115,12 +115,19 @@ static void hid_lgff_set_autocenter(struct input_dev *dev, u16 magnitude)
 
 int lgff_init(struct hid_device* hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const signed short *ff_bits = ff_joystick;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -ENODEV;
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 0179f7ed77e5..8e91e2f06cb4 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -1669,6 +1669,7 @@ static void hidpp_touchpad_raw_xy_event(struct hidpp_device *hidpp_dev,
 
 #define HIDPP_FF_EFFECTID_NONE		-1
 #define HIDPP_FF_EFFECTID_AUTOCENTER	-2
+#define HIDPP_AUTOCENTER_PARAMS_LENGTH	18
 
 #define HIDPP_FF_MAX_PARAMS	20
 #define HIDPP_FF_RESERVED_SLOTS	1
@@ -2009,7 +2010,7 @@ static int hidpp_ff_erase_effect(struct input_dev *dev, int effect_id)
 static void hidpp_ff_set_autocenter(struct input_dev *dev, u16 magnitude)
 {
 	struct hidpp_ff_private_data *data = dev->ff->private;
-	u8 params[18];
+	u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH];
 
 	dbg_hid("Setting autocenter to %d.\n", magnitude);
 
@@ -2077,23 +2078,34 @@ static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, hidpp
 static void hidpp_ff_destroy(struct ff_device *ff)
 {
 	struct hidpp_ff_private_data *data = ff->private;
+	struct hid_device *hid = data->hidpp->hid_dev;
 
+	hid_info(hid, "Unloading HID++ force feedback.\n");
+
+	device_remove_file(&hid->dev, &dev_attr_range);
+	destroy_workqueue(data->wq);
 	kfree(data->effect_ids);
 }
 
-static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
+static int hidpp_ff_init(struct hidpp_device *hidpp,
+			 struct hidpp_ff_private_data *data)
 {
 	struct hid_device *hid = hidpp->hid_dev;
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
 	const u16 bcdDevice = le16_to_cpu(udesc->bcdDevice);
 	struct ff_device *ff;
-	struct hidpp_report response;
-	struct hidpp_ff_private_data *data;
-	int error, j, num_slots;
+	int error, j, num_slots = data->num_effects;
 	u8 version;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (!dev) {
 		hid_err(hid, "Struct input_dev not set!\n");
 		return -EINVAL;
@@ -2109,27 +2121,17 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 		for (j = 0; hidpp_ff_effects_v2[j] >= 0; j++)
 			set_bit(hidpp_ff_effects_v2[j], dev->ffbit);
 
-	/* Read number of slots available in device */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_INFO, NULL, 0, &response);
-	if (error) {
-		if (error < 0)
-			return error;
-		hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n",
-			__func__, error);
-		return -EPROTO;
-	}
-
-	num_slots = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS;
-
 	error = input_ff_create(dev, num_slots);
 
 	if (error) {
 		hid_err(dev, "Failed to create FF device!\n");
 		return error;
 	}
-
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	/*
+	 * Create a copy of passed data, so we can transfer memory
+	 * ownership to FF core
+	 */
+	data = kmemdup(data, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 	data->effect_ids = kcalloc(num_slots, sizeof(int), GFP_KERNEL);
@@ -2145,10 +2147,7 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 	}
 
 	data->hidpp = hidpp;
-	data->feature_index = feature_index;
 	data->version = version;
-	data->slot_autocenter = 0;
-	data->num_effects = num_slots;
 	for (j = 0; j < num_slots; j++)
 		data->effect_ids[j] = -1;
 
@@ -2162,68 +2161,20 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 	ff->set_autocenter = hidpp_ff_set_autocenter;
 	ff->destroy = hidpp_ff_destroy;
 
-
-	/* reset all forces */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_RESET_ALL, NULL, 0, &response);
-
-	/* Read current Range */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_APERTURE, NULL, 0, &response);
-	if (error)
-		hid_warn(hidpp->hid_dev, "Failed to read range from device!\n");
-	data->range = error ? 900 : get_unaligned_be16(&response.fap.params[0]);
-
 	/* Create sysfs interface */
 	error = device_create_file(&(hidpp->hid_dev->dev), &dev_attr_range);
 	if (error)
 		hid_warn(hidpp->hid_dev, "Unable to create sysfs interface for \"range\", errno %d!\n", error);
 
-	/* Read the current gain values */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_GLOBAL_GAINS, NULL, 0, &response);
-	if (error)
-		hid_warn(hidpp->hid_dev, "Failed to read gain values from device!\n");
-	data->gain = error ? 0xffff : get_unaligned_be16(&response.fap.params[0]);
-	/* ignore boost value at response.fap.params[2] */
-
 	/* init the hardware command queue */
 	atomic_set(&data->workqueue_size, 0);
 
-	/* initialize with zero autocenter to get wheel in usable state */
-	hidpp_ff_set_autocenter(dev, 0);
-
 	hid_info(hid, "Force feedback support loaded (firmware release %d).\n",
 		 version);
 
 	return 0;
 }
 
-static int hidpp_ff_deinit(struct hid_device *hid)
-{
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
-	struct hidpp_ff_private_data *data;
-
-	if (!dev) {
-		hid_err(hid, "Struct input_dev not found!\n");
-		return -EINVAL;
-	}
-
-	hid_info(hid, "Unloading HID++ force feedback.\n");
-	data = dev->ff->private;
-	if (!data) {
-		hid_err(hid, "Private data not found!\n");
-		return -EINVAL;
-	}
-
-	destroy_workqueue(data->wq);
-	device_remove_file(&hid->dev, &dev_attr_range);
-
-	return 0;
-}
-
-
 /* ************************************************************************** */
 /*                                                                            */
 /* Device Support                                                             */
@@ -2725,24 +2676,93 @@ static int k400_connect(struct hid_device *hdev, bool connected)
 
 #define HIDPP_PAGE_G920_FORCE_FEEDBACK			0x8123
 
-static int g920_get_config(struct hidpp_device *hidpp)
+static int g920_ff_set_autocenter(struct hidpp_device *hidpp,
+				  struct hidpp_ff_private_data *data)
 {
+	struct hidpp_report response;
+	u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH] = {
+		[1] = HIDPP_FF_EFFECT_SPRING | HIDPP_FF_EFFECT_AUTOSTART,
+	};
+	int ret;
+
+	/* initialize with zero autocenter to get wheel in usable state */
+
+	dbg_hid("Setting autocenter to 0.\n");
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_DOWNLOAD_EFFECT,
+					  params, ARRAY_SIZE(params),
+					  &response);
+	if (ret)
+		hid_warn(hidpp->hid_dev, "Failed to autocenter device!\n");
+	else
+		data->slot_autocenter = response.fap.params[0];
+
+	return ret;
+}
+
+static int g920_get_config(struct hidpp_device *hidpp,
+			   struct hidpp_ff_private_data *data)
+{
+	struct hidpp_report response;
 	u8 feature_type;
-	u8 feature_index;
 	int ret;
 
+	memset(data, 0, sizeof(*data));
+
 	/* Find feature and store for later use */
 	ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_G920_FORCE_FEEDBACK,
-		&feature_index, &feature_type);
+				     &data->feature_index, &feature_type);
 	if (ret)
 		return ret;
 
-	ret = hidpp_ff_init(hidpp, feature_index);
+	/* Read number of slots available in device */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_INFO,
+					  NULL, 0,
+					  &response);
+	if (ret) {
+		if (ret < 0)
+			return ret;
+		hid_err(hidpp->hid_dev,
+			"%s: received protocol error 0x%02x\n", __func__, ret);
+		return -EPROTO;
+	}
+
+	data->num_effects = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS;
+
+	/* reset all forces */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_RESET_ALL,
+					  NULL, 0,
+					  &response);
 	if (ret)
-		hid_warn(hidpp->hid_dev, "Unable to initialize force feedback support, errno %d\n",
-				ret);
+		hid_warn(hidpp->hid_dev, "Failed to reset all forces!\n");
 
-	return 0;
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_APERTURE,
+					  NULL, 0,
+					  &response);
+	if (ret) {
+		hid_warn(hidpp->hid_dev,
+			 "Failed to read range from device!\n");
+	}
+	data->range = ret ?
+		900 : get_unaligned_be16(&response.fap.params[0]);
+
+	/* Read the current gain values */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_GLOBAL_GAINS,
+					  NULL, 0,
+					  &response);
+	if (ret)
+		hid_warn(hidpp->hid_dev,
+			 "Failed to read gain values from device!\n");
+	data->gain = ret ?
+		0xffff : get_unaligned_be16(&response.fap.params[0]);
+
+	/* ignore boost value at response.fap.params[2] */
+
+	return g920_ff_set_autocenter(hidpp, data);
 }
 
 /* -------------------------------------------------------------------------- */
@@ -3458,34 +3478,45 @@ static int hidpp_get_report_length(struct hid_device *hdev, int id)
 	return report->field[0]->report_count + 1;
 }
 
-static bool hidpp_validate_report(struct hid_device *hdev, int id,
-				  int expected_length, bool optional)
+static bool hidpp_validate_device(struct hid_device *hdev)
 {
-	int report_length;
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	int id, report_length, supported_reports = 0;
 
-	if (id >= HID_MAX_IDS || id < 0) {
-		hid_err(hdev, "invalid HID report id %u\n", id);
-		return false;
+	id = REPORT_ID_HIDPP_SHORT;
+	report_length = hidpp_get_report_length(hdev, id);
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_SHORT_LENGTH)
+			goto bad_device;
+
+		supported_reports++;
 	}
 
+	id = REPORT_ID_HIDPP_LONG;
 	report_length = hidpp_get_report_length(hdev, id);
-	if (!report_length)
-		return optional;
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_LONG_LENGTH)
+			goto bad_device;
 
-	if (report_length < expected_length) {
-		hid_warn(hdev, "not enough values in hidpp report %d\n", id);
-		return false;
+		supported_reports++;
 	}
 
-	return true;
-}
+	id = REPORT_ID_HIDPP_VERY_LONG;
+	report_length = hidpp_get_report_length(hdev, id);
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_LONG_LENGTH ||
+		    report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH)
+			goto bad_device;
 
-static bool hidpp_validate_device(struct hid_device *hdev)
-{
-	return hidpp_validate_report(hdev, REPORT_ID_HIDPP_SHORT,
-				     HIDPP_REPORT_SHORT_LENGTH, false) &&
-	       hidpp_validate_report(hdev, REPORT_ID_HIDPP_LONG,
-				     HIDPP_REPORT_LONG_LENGTH, true);
+		supported_reports++;
+		hidpp->very_long_report_length = report_length;
+	}
+
+	return supported_reports;
+
+bad_device:
+	hid_warn(hdev, "not enough values in hidpp report %d\n", id);
+	return false;
 }
 
 static bool hidpp_application_equals(struct hid_device *hdev,
@@ -3505,6 +3536,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	int ret;
 	bool connected;
 	unsigned int connect_mask = HID_CONNECT_DEFAULT;
+	struct hidpp_ff_private_data data;
 
 	/* report_fixup needs drvdata to be set before we call hid_parse */
 	hidpp = devm_kzalloc(&hdev->dev, sizeof(*hidpp), GFP_KERNEL);
@@ -3531,11 +3563,6 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	}
 
-	hidpp->very_long_report_length =
-		hidpp_get_report_length(hdev, REPORT_ID_HIDPP_VERY_LONG);
-	if (hidpp->very_long_report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH)
-		hidpp->very_long_report_length = HIDPP_REPORT_VERY_LONG_MAX_LENGTH;
-
 	if (id->group == HID_GROUP_LOGITECH_DJ_DEVICE)
 		hidpp->quirks |= HIDPP_QUIRK_UNIFYING;
 
@@ -3614,7 +3641,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		if (ret)
 			goto hid_hw_init_fail;
 	} else if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)) {
-		ret = g920_get_config(hidpp);
+		ret = g920_get_config(hidpp, &data);
 		if (ret)
 			goto hid_hw_init_fail;
 	}
@@ -3636,6 +3663,14 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		goto hid_hw_start_fail;
 	}
 
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) {
+		ret = hidpp_ff_init(hidpp, &data);
+		if (ret)
+			hid_warn(hidpp->hid_dev,
+		     "Unable to initialize force feedback support, errno %d\n",
+				 ret);
+	}
+
 	return ret;
 
 hid_hw_init_fail:
@@ -3658,9 +3693,6 @@ static void hidpp_remove(struct hid_device *hdev)
 
 	sysfs_remove_group(&hdev->dev.kobj, &ps_attribute_group);
 
-	if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)
-		hidpp_ff_deinit(hdev);
-
 	hid_hw_stop(hdev);
 	cancel_work_sync(&hidpp->work);
 	mutex_destroy(&hidpp->send_mutex);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 2cf83856f2e4..2d8b589201a4 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -328,11 +328,17 @@ static int ms_play_effect(struct input_dev *dev, void *data,
 
 static int ms_init_ff(struct hid_device *hdev)
 {
-	struct hid_input *hidinput = list_entry(hdev->inputs.next,
-						struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
 	struct ms_data *ms = hid_get_drvdata(hdev);
 
+	if (list_empty(&hdev->inputs)) {
+		hid_err(hdev, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hdev->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
+
 	if (!(ms->quirks & MS_QUIRK_FF))
 		return 0;
 
diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c
index 5a3b3d974d84..2666af02d5c1 100644
--- a/drivers/hid/hid-prodikeys.c
+++ b/drivers/hid/hid-prodikeys.c
@@ -516,7 +516,7 @@ static void pcmidi_setup_extra_keys(
 		MY PICTURES =>	KEY_WORDPROCESSOR
 		MY MUSIC=>	KEY_SPREADSHEET
 	*/
-	unsigned int keys[] = {
+	static const unsigned int keys[] = {
 		KEY_FN,
 		KEY_MESSENGER, KEY_CALENDAR,
 		KEY_ADDRESSBOOK, KEY_DOCUMENTS,
@@ -532,7 +532,7 @@ static void pcmidi_setup_extra_keys(
 		0
 	};
 
-	unsigned int *pkeys = &keys[0];
+	const unsigned int *pkeys = &keys[0];
 	unsigned short i;
 
 	if (pm->ifnum != 1)  /* only set up ONCE for interace 1 */
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 73c0f7a95e2d..4c6ed6ef31f1 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -2254,9 +2254,15 @@ static int sony_play_effect(struct input_dev *dev, void *data,
 
 static int sony_init_ff(struct sony_sc *sc)
 {
-	struct hid_input *hidinput = list_entry(sc->hdev->inputs.next,
-						struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
+
+	if (list_empty(&sc->hdev->inputs)) {
+		hid_err(sc->hdev, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(sc->hdev->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
 
 	input_set_capability(input_dev, EV_FF, FF_RUMBLE);
 	return input_ff_create_memless(input_dev, NULL, sony_play_effect);
diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c
index bdfc5ff3b2c5..90acef304536 100644
--- a/drivers/hid/hid-tmff.c
+++ b/drivers/hid/hid-tmff.c
@@ -124,12 +124,18 @@ static int tmff_init(struct hid_device *hid, const signed short *ff_bits)
 	struct tmff_device *tmff;
 	struct hid_report *report;
 	struct list_head *report_list;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-							struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
+
 	tmff = kzalloc(sizeof(struct tmff_device), GFP_KERNEL);
 	if (!tmff)
 		return -ENOMEM;
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index f90959e94028..3abaca045869 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -54,11 +54,17 @@ static int zpff_init(struct hid_device *hid)
 {
 	struct zpff_device *zpff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	int i, error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	for (i = 0; i < 4; i++) {
 		report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1);
 		if (!report)
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 2a7c6e33bb1c..04c088131e04 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -26,7 +26,6 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/pm.h>
-#include <linux/pm_runtime.h>
 #include <linux/device.h>
 #include <linux/wait.h>
 #include <linux/err.h>
@@ -48,8 +47,6 @@
 /* quirks to control the device */
 #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV	BIT(0)
 #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET	BIT(1)
-#define I2C_HID_QUIRK_NO_RUNTIME_PM		BIT(2)
-#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP		BIT(3)
 #define I2C_HID_QUIRK_BOGUS_IRQ			BIT(4)
 
 /* flags */
@@ -172,14 +169,7 @@ static const struct i2c_hid_quirks {
 	{ USB_VENDOR_ID_WEIDA, HID_ANY_ID,
 		I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
 	{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
-		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET |
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
-	{ I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33,
-		I2C_HID_QUIRK_DELAY_AFTER_SLEEP },
-	{ USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_8001,
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
-	{ I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_01F0,
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
+		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
 		 I2C_HID_QUIRK_BOGUS_IRQ },
 	{ 0, 0 }
@@ -397,7 +387,6 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 {
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	int ret;
-	unsigned long now, delay;
 
 	i2c_hid_dbg(ihid, "%s\n", __func__);
 
@@ -415,22 +404,9 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 			goto set_pwr_exit;
 	}
 
-	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
-	    power_state == I2C_HID_PWR_ON) {
-		now = jiffies;
-		if (time_after(ihid->sleep_delay, now)) {
-			delay = jiffies_to_usecs(ihid->sleep_delay - now);
-			usleep_range(delay, delay + 1);
-		}
-	}
-
 	ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state,
 		0, NULL, 0, NULL, 0);
 
-	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
-	    power_state == I2C_HID_PWR_SLEEP)
-		ihid->sleep_delay = jiffies + msecs_to_jiffies(20);
-
 	if (ret)
 		dev_err(&client->dev, "failed to change power setting.\n");
 
@@ -471,8 +447,12 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret) {
 		dev_err(&client->dev, "failed to reset device.\n");
 		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+		goto out_unlock;
 	}
 
+	/* At least some SIS devices need this after reset */
+	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+
 out_unlock:
 	mutex_unlock(&ihid->reset_lock);
 	return ret;
@@ -791,11 +771,6 @@ static int i2c_hid_open(struct hid_device *hid)
 {
 	struct i2c_client *client = hid->driver_data;
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
-	int ret = 0;
-
-	ret = pm_runtime_get_sync(&client->dev);
-	if (ret < 0)
-		return ret;
 
 	set_bit(I2C_HID_STARTED, &ihid->flags);
 	return 0;
@@ -807,27 +782,6 @@ static void i2c_hid_close(struct hid_device *hid)
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 
 	clear_bit(I2C_HID_STARTED, &ihid->flags);
-
-	/* Save some power */
-	pm_runtime_put(&client->dev);
-}
-
-static int i2c_hid_power(struct hid_device *hid, int lvl)
-{
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-
-	i2c_hid_dbg(ihid, "%s lvl:%d\n", __func__, lvl);
-
-	switch (lvl) {
-	case PM_HINT_FULLON:
-		pm_runtime_get_sync(&client->dev);
-		break;
-	case PM_HINT_NORMAL:
-		pm_runtime_put(&client->dev);
-		break;
-	}
-	return 0;
 }
 
 struct hid_ll_driver i2c_hid_ll_driver = {
@@ -836,7 +790,6 @@ struct hid_ll_driver i2c_hid_ll_driver = {
 	.stop = i2c_hid_stop,
 	.open = i2c_hid_open,
 	.close = i2c_hid_close,
-	.power = i2c_hid_power,
 	.output_report = i2c_hid_output_report,
 	.raw_request = i2c_hid_raw_request,
 };
@@ -1104,9 +1057,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 
 	i2c_hid_acpi_fix_up_power(&client->dev);
 
-	pm_runtime_get_noresume(&client->dev);
-	pm_runtime_set_active(&client->dev);
-	pm_runtime_enable(&client->dev);
 	device_enable_async_suspend(&client->dev);
 
 	/* Make sure there is something at this address */
@@ -1114,16 +1064,16 @@ static int i2c_hid_probe(struct i2c_client *client,
 	if (ret < 0) {
 		dev_dbg(&client->dev, "nothing at this address: %d\n", ret);
 		ret = -ENXIO;
-		goto err_pm;
+		goto err_regulator;
 	}
 
 	ret = i2c_hid_fetch_hid_descriptor(ihid);
 	if (ret < 0)
-		goto err_pm;
+		goto err_regulator;
 
 	ret = i2c_hid_init_irq(client);
 	if (ret < 0)
-		goto err_pm;
+		goto err_regulator;
 
 	hid = hid_allocate_device();
 	if (IS_ERR(hid)) {
@@ -1154,9 +1104,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 		goto err_mem_free;
 	}
 
-	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
-		pm_runtime_put(&client->dev);
-
 	return 0;
 
 err_mem_free:
@@ -1165,10 +1112,6 @@ err_mem_free:
 err_irq:
 	free_irq(client->irq, ihid);
 
-err_pm:
-	pm_runtime_put_noidle(&client->dev);
-	pm_runtime_disable(&client->dev);
-
 err_regulator:
 	regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies),
 			       ihid->pdata.supplies);
@@ -1181,12 +1124,6 @@ static int i2c_hid_remove(struct i2c_client *client)
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	struct hid_device *hid;
 
-	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
-		pm_runtime_get_sync(&client->dev);
-	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
-	pm_runtime_put_noidle(&client->dev);
-
 	hid = ihid->hid;
 	hid_destroy_device(hid);
 
@@ -1219,25 +1156,15 @@ static int i2c_hid_suspend(struct device *dev)
 	int wake_status;
 
 	if (hid->driver && hid->driver->suspend) {
-		/*
-		 * Wake up the device so that IO issues in
-		 * HID driver's suspend code can succeed.
-		 */
-		ret = pm_runtime_resume(dev);
-		if (ret < 0)
-			return ret;
-
 		ret = hid->driver->suspend(hid, PMSG_SUSPEND);
 		if (ret < 0)
 			return ret;
 	}
 
-	if (!pm_runtime_suspended(dev)) {
-		/* Save some power */
-		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+	/* Save some power */
+	i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
 
-		disable_irq(client->irq);
-	}
+	disable_irq(client->irq);
 
 	if (device_may_wakeup(&client->dev)) {
 		wake_status = enable_irq_wake(client->irq);
@@ -1279,11 +1206,6 @@ static int i2c_hid_resume(struct device *dev)
 				wake_status);
 	}
 
-	/* We'll resume to full power */
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-
 	enable_irq(client->irq);
 
 	/* Instead of resetting device, simply powers the device on. This
@@ -1304,30 +1226,8 @@ static int i2c_hid_resume(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_PM
-static int i2c_hid_runtime_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
-	disable_irq(client->irq);
-	return 0;
-}
-
-static int i2c_hid_runtime_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	enable_irq(client->irq);
-	i2c_hid_set_power(client, I2C_HID_PWR_ON);
-	return 0;
-}
-#endif
-
 static const struct dev_pm_ops i2c_hid_pm = {
 	SET_SYSTEM_SLEEP_PM_OPS(i2c_hid_suspend, i2c_hid_resume)
-	SET_RUNTIME_PM_OPS(i2c_hid_runtime_suspend, i2c_hid_runtime_resume,
-			   NULL)
 };
 
 static const struct i2c_device_id i2c_hid_id_table[] = {
diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
index 75078c83be1a..d31ea82b84c1 100644
--- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
@@ -323,6 +323,25 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		/*
+		 * There are at least 2 Primebook C11B versions, the older
+		 * version has a product-name of "Primebook C11B", and a
+		 * bios version / release / firmware revision of:
+		 * V2.1.2 / 05/03/2018 / 18.2
+		 * The new version has "PRIMEBOOK C11B" as product-name and a
+		 * bios version / release / firmware revision of:
+		 * CFALKSW05_BIOS_V1.1.2 / 11/19/2018 / 19.2
+		 * Only the older version needs this quirk, note the newer
+		 * version will not match as it has a different product-name.
+		 */
+		.ident = "Trekstor Primebook C11B",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C11B"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Direkt-Tek DTLAPY116-2",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"),
diff --git a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
index 1b0a0cc605e7..513d7a4a1b8a 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
@@ -84,7 +84,7 @@ int ishtp_cl_alloc_tx_ring(struct ishtp_cl *cl)
 	return	0;
 out:
 	dev_err(&cl->device->dev, "error in allocating Tx pool\n");
-	ishtp_cl_free_rx_ring(cl);
+	ishtp_cl_free_tx_ring(cl);
 	return	-ENOMEM;
 }
 
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 4a7f8d363220..203d27d198b8 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -202,6 +202,21 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac,
 	}
 }
 
+/*
+ * Convert a signed 32-bit integer to an unsigned n-bit integer. Undoes
+ * the normally-helpful work of 'hid_snto32' for fields that use signed
+ * ranges for questionable reasons.
+ */
+static inline __u32 wacom_s32tou(s32 value, __u8 n)
+{
+	switch (n) {
+	case 8:  return ((__u8)value);
+	case 16: return ((__u16)value);
+	case 32: return ((__u32)value);
+	}
+	return value & (1 << (n - 1)) ? value & (~(~0U << n)) : value;
+}
+
 extern const struct hid_device_id wacom_ids[];
 
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 2b0a5b8ca6e6..ccb74529bc78 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2303,7 +2303,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 	case HID_DG_TOOLSERIALNUMBER:
 		if (value) {
 			wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
-			wacom_wac->serial[0] |= (__u32)value;
+			wacom_wac->serial[0] |= wacom_s32tou(value, field->report_size);
 		}
 		return;
 	case HID_DG_TWIST:
@@ -2319,15 +2319,17 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		return;
 	case WACOM_HID_WD_SERIALHI:
 		if (value) {
+			__u32 raw_value = wacom_s32tou(value, field->report_size);
+
 			wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF);
-			wacom_wac->serial[0] |= ((__u64)value) << 32;
+			wacom_wac->serial[0] |= ((__u64)raw_value) << 32;
 			/*
 			 * Non-USI EMR devices may contain additional tool type
 			 * information here. See WACOM_HID_WD_TOOLTYPE case for
 			 * more details.
 			 */
 			if (value >> 20 == 1) {
-				wacom_wac->id[0] |= value & 0xFFFFF;
+				wacom_wac->id[0] |= raw_value & 0xFFFFF;
 			}
 		}
 		return;
@@ -2339,7 +2341,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		 * bitwise OR so the complete value can be built
 		 * up over time :(
 		 */
-		wacom_wac->id[0] |= value;
+		wacom_wac->id[0] |= wacom_s32tou(value, field->report_size);
 		return;
 	case WACOM_HID_WD_OFFSETLEFT:
 		if (features->offset_left && value != features->offset_left)
diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c
index 0037e2bdacd6..8a51dcf055ea 100644
--- a/drivers/hwmon/ina3221.c
+++ b/drivers/hwmon/ina3221.c
@@ -170,7 +170,7 @@ static inline int ina3221_wait_for_data(struct ina3221_data *ina)
 
 	/* Polling the CVRF bit to make sure read data is ready */
 	return regmap_field_read_poll_timeout(ina->fields[F_CVRF],
-					      cvrf, cvrf, wait, 100000);
+					      cvrf, cvrf, wait, wait * 2);
 }
 
 static int ina3221_read_value(struct ina3221_data *ina, unsigned int reg,
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b26419dbe840..281c81edabc6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -82,6 +82,10 @@
 #define FANCTL1_FMR_REG		0x00	/* Bank 3; 1 reg per channel */
 #define FANCTL1_OUT_REG		0x10	/* Bank 3; 1 reg per channel */
 
+#define VOLT_MONITOR_MODE	0x0
+#define THERMAL_DIODE_MODE	0x1
+#define THERMISTOR_MODE		0x3
+
 #define ENABLE_TSI	BIT(1)
 
 static const unsigned short normal_i2c[] = {
@@ -935,11 +939,16 @@ static int nct7904_probe(struct i2c_client *client,
 	for (i = 0; i < 4; i++) {
 		val = (ret >> (i * 2)) & 0x03;
 		bit = (1 << i);
-		if (val == 0) {
+		if (val == VOLT_MONITOR_MODE) {
 			data->tcpu_mask &= ~bit;
+		} else if (val == THERMAL_DIODE_MODE && i < 2) {
+			data->temp_mode |= bit;
+			data->vsen_mask &= ~(0x06 << (i * 2));
+		} else if (val == THERMISTOR_MODE) {
+			data->vsen_mask &= ~(0x02 << (i * 2));
 		} else {
-			if (val == 0x1 || val == 0x2)
-				data->temp_mode |= bit;
+			/* Reserved */
+			data->tcpu_mask &= ~bit;
 			data->vsen_mask &= ~(0x06 << (i * 2));
 		}
 	}
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index fa9d34af87ac..f72803a02391 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -626,6 +626,9 @@ static void intel_th_gth_switch(struct intel_th_device *thdev,
 	if (!count)
 		dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n");
 
+	/* De-assert the trigger */
+	iowrite32(0, gth->base + REG_CTS_CTL);
+
 	intel_th_gth_stop(gth, output, false);
 	intel_th_gth_start(gth, output);
 }
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index fc9f15f36ad4..6d240dfae9d9 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -164,7 +164,7 @@ struct msc {
 };
 
 static LIST_HEAD(msu_buffer_list);
-static struct mutex msu_buffer_mutex;
+static DEFINE_MUTEX(msu_buffer_mutex);
 
 /**
  * struct msu_buffer_entry - internal MSU buffer bookkeeping
@@ -327,7 +327,7 @@ static size_t msc_win_total_sz(struct msc_window *win)
 		struct msc_block_desc *bdesc = sg_virt(sg);
 
 		if (msc_block_wrapped(bdesc))
-			return win->nr_blocks << PAGE_SHIFT;
+			return (size_t)win->nr_blocks << PAGE_SHIFT;
 
 		size += msc_total_sz(bdesc);
 		if (msc_block_last_written(bdesc))
@@ -1848,9 +1848,14 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf,
 		len = cp - buf;
 
 	mode = kstrndup(buf, len, GFP_KERNEL);
+	if (!mode)
+		return -ENOMEM;
+
 	i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode);
-	if (i >= 0)
+	if (i >= 0) {
+		kfree(mode);
 		goto found;
+	}
 
 	/* Buffer sinks only work with a usable IRQ */
 	if (!msc->do_irq) {
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 91dfeba62485..03ca5b1bef9f 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -200,6 +200,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Comet Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Ice Lake NNPI */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
@@ -209,6 +214,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Jasper Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index fa66951b05d0..7b098ff5f5dd 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -108,6 +108,12 @@
 #define ASPEED_I2CD_S_TX_CMD				BIT(2)
 #define ASPEED_I2CD_M_TX_CMD				BIT(1)
 #define ASPEED_I2CD_M_START_CMD				BIT(0)
+#define ASPEED_I2CD_MASTER_CMDS_MASK					       \
+		(ASPEED_I2CD_M_STOP_CMD |				       \
+		 ASPEED_I2CD_M_S_RX_CMD_LAST |				       \
+		 ASPEED_I2CD_M_RX_CMD |					       \
+		 ASPEED_I2CD_M_TX_CMD |					       \
+		 ASPEED_I2CD_M_START_CMD)
 
 /* 0x18 : I2CD Slave Device Address Register   */
 #define ASPEED_I2CD_DEV_ADDR_MASK			GENMASK(6, 0)
@@ -336,18 +342,19 @@ static void aspeed_i2c_do_start(struct aspeed_i2c_bus *bus)
 	struct i2c_msg *msg = &bus->msgs[bus->msgs_index];
 	u8 slave_addr = i2c_8bit_addr_from_msg(msg);
 
-	bus->master_state = ASPEED_I2C_MASTER_START;
-
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 	/*
 	 * If it's requested in the middle of a slave session, set the master
 	 * state to 'pending' then H/W will continue handling this master
 	 * command when the bus comes back to the idle state.
 	 */
-	if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE)
+	if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE) {
 		bus->master_state = ASPEED_I2C_MASTER_PENDING;
+		return;
+	}
 #endif /* CONFIG_I2C_SLAVE */
 
+	bus->master_state = ASPEED_I2C_MASTER_START;
 	bus->buf_index = 0;
 
 	if (msg->flags & I2C_M_RD) {
@@ -422,20 +429,6 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		}
 	}
 
-#if IS_ENABLED(CONFIG_I2C_SLAVE)
-	/*
-	 * A pending master command will be started by H/W when the bus comes
-	 * back to idle state after completing a slave operation so change the
-	 * master state from 'pending' to 'start' at here if slave is inactive.
-	 */
-	if (bus->master_state == ASPEED_I2C_MASTER_PENDING) {
-		if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE)
-			goto out_no_complete;
-
-		bus->master_state = ASPEED_I2C_MASTER_START;
-	}
-#endif /* CONFIG_I2C_SLAVE */
-
 	/* Master is not currently active, irq was for someone else. */
 	if (bus->master_state == ASPEED_I2C_MASTER_INACTIVE ||
 	    bus->master_state == ASPEED_I2C_MASTER_PENDING)
@@ -462,11 +455,15 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 		/*
 		 * If a peer master starts a xfer immediately after it queues a
-		 * master command, change its state to 'pending' then H/W will
-		 * continue the queued master xfer just after completing the
-		 * slave mode session.
+		 * master command, clear the queued master command and change
+		 * its state to 'pending'. To simplify handling of pending
+		 * cases, it uses S/W solution instead of H/W command queue
+		 * handling.
 		 */
 		if (unlikely(irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH)) {
+			writel(readl(bus->base + ASPEED_I2C_CMD_REG) &
+				~ASPEED_I2CD_MASTER_CMDS_MASK,
+			       bus->base + ASPEED_I2C_CMD_REG);
 			bus->master_state = ASPEED_I2C_MASTER_PENDING;
 			dev_dbg(bus->dev,
 				"master goes pending due to a slave start\n");
@@ -629,6 +626,14 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 			irq_handled |= aspeed_i2c_master_irq(bus,
 							     irq_remaining);
 	}
+
+	/*
+	 * Start a pending master command at here if a slave operation is
+	 * completed.
+	 */
+	if (bus->master_state == ASPEED_I2C_MASTER_PENDING &&
+	    bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE)
+		aspeed_i2c_do_start(bus);
 #else
 	irq_handled = aspeed_i2c_master_irq(bus, irq_remaining);
 #endif /* CONFIG_I2C_SLAVE */
@@ -691,6 +696,15 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap,
 		     ASPEED_I2CD_BUS_BUSY_STS))
 			aspeed_i2c_recover_bus(bus);
 
+		/*
+		 * If timed out and the state is still pending, drop the pending
+		 * master command.
+		 */
+		spin_lock_irqsave(&bus->lock, flags);
+		if (bus->master_state == ASPEED_I2C_MASTER_PENDING)
+			bus->master_state = ASPEED_I2C_MASTER_INACTIVE;
+		spin_unlock_irqrestore(&bus->lock, flags);
+
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 29eae1bf4f86..2152ec5f535c 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -875,7 +875,7 @@ static irqreturn_t mtk_i2c_irq(int irqno, void *dev_id)
 
 static u32 mtk_i2c_functionality(struct i2c_adapter *adap)
 {
-	if (adap->quirks->flags & I2C_AQ_NO_ZERO_LEN)
+	if (i2c_check_quirks(adap, I2C_AQ_NO_ZERO_LEN))
 		return I2C_FUNC_I2C |
 			(I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
 	else
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index d36cf08461f7..b24e7b937f21 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -305,7 +305,7 @@ struct stm32f7_i2c_dev {
 	struct regmap *regmap;
 };
 
-/**
+/*
  * All these values are coming from I2C Specification, Version 6.0, 4th of
  * April 2014.
  *
@@ -1192,6 +1192,8 @@ static void stm32f7_i2c_slave_start(struct stm32f7_i2c_dev *i2c_dev)
 			STM32F7_I2C_CR1_TXIE;
 		stm32f7_i2c_set_bits(base + STM32F7_I2C_CR1, mask);
 
+		/* Write 1st data byte */
+		writel_relaxed(value, base + STM32F7_I2C_TXDR);
 	} else {
 		/* Notify i2c slave that new write transfer is starting */
 		i2c_slave_event(slave, I2C_SLAVE_WRITE_REQUESTED, &value);
@@ -1501,7 +1503,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
 	void __iomem *base = i2c_dev->base;
 	struct device *dev = i2c_dev->dev;
 	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	u32 mask, status;
+	u32 status;
 
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
@@ -1526,12 +1528,15 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
 		f7_msg->result = -EINVAL;
 	}
 
-	/* Disable interrupts */
-	if (stm32f7_i2c_is_slave_registered(i2c_dev))
-		mask = STM32F7_I2C_XFER_IRQ_MASK;
-	else
-		mask = STM32F7_I2C_ALL_IRQ_MASK;
-	stm32f7_i2c_disable_irq(i2c_dev, mask);
+	if (!i2c_dev->slave_running) {
+		u32 mask;
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
+		else
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
+	}
 
 	/* Disable dma */
 	if (i2c_dev->use_dma) {
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index 9cb2aa1e20ef..62a1c92ab803 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -39,6 +39,7 @@ struct i2c_acpi_lookup {
 	int index;
 	u32 speed;
 	u32 min_speed;
+	u32 force_speed;
 };
 
 /**
@@ -285,6 +286,19 @@ i2c_acpi_match_device(const struct acpi_device_id *matches,
 	return acpi_match_device(matches, &client->dev);
 }
 
+static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = {
+	/*
+	 * These Silead touchscreen controllers only work at 400KHz, for
+	 * some reason they do not work at 100KHz. On some devices the ACPI
+	 * tables list another device at their bus as only being capable
+	 * of 100KHz, testing has shown that these other devices work fine
+	 * at 400KHz (as can be expected of any recent i2c hw) so we force
+	 * the speed of the bus to 400 KHz if a Silead device is present.
+	 */
+	{ "MSSL1680", 0 },
+	{}
+};
+
 static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level,
 					   void *data, void **return_value)
 {
@@ -303,6 +317,9 @@ static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level,
 	if (lookup->speed <= lookup->min_speed)
 		lookup->min_speed = lookup->speed;
 
+	if (acpi_match_device_ids(adev, i2c_acpi_force_400khz_device_ids) == 0)
+		lookup->force_speed = 400000;
+
 	return AE_OK;
 }
 
@@ -340,7 +357,16 @@ u32 i2c_acpi_find_bus_speed(struct device *dev)
 		return 0;
 	}
 
-	return lookup.min_speed != UINT_MAX ? lookup.min_speed : 0;
+	if (lookup.force_speed) {
+		if (lookup.force_speed != lookup.min_speed)
+			dev_warn(dev, FW_BUG "DSDT uses known not-working I2C bus speed %d, forcing it to %d\n",
+				 lookup.min_speed, lookup.force_speed);
+		return lookup.force_speed;
+	} else if (lookup.min_speed != UINT_MAX) {
+		return lookup.min_speed;
+	} else {
+		return 0;
+	}
 }
 EXPORT_SYMBOL_GPL(i2c_acpi_find_bus_speed);
 
diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c
index 6f632d543fcc..7eb41990bd6d 100644
--- a/drivers/i2c/i2c-core-of.c
+++ b/drivers/i2c/i2c-core-of.c
@@ -245,14 +245,14 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action,
 		}
 
 		client = of_i2c_register_device(adap, rd->dn);
-		put_device(&adap->dev);
-
 		if (IS_ERR(client)) {
 			dev_err(&adap->dev, "failed to create client for '%pOF'\n",
 				 rd->dn);
+			put_device(&adap->dev);
 			of_node_clear_flag(rd->dn, OF_POPULATED);
 			return notifier_from_errno(PTR_ERR(client));
 		}
+		put_device(&adap->dev);
 		break;
 	case OF_RECONFIG_CHANGE_REMOVE:
 		/* already depopulated? */
diff --git a/drivers/ide/falconide.c b/drivers/ide/falconide.c
index a5a07ccb81a7..dbeb2605e5f6 100644
--- a/drivers/ide/falconide.c
+++ b/drivers/ide/falconide.c
@@ -15,6 +15,7 @@
 #include <linux/blkdev.h>
 #include <linux/ide.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
 
 #include <asm/setup.h>
 #include <asm/atarihw.h>
@@ -25,13 +26,7 @@
 #define DRV_NAME "falconide"
 
     /*
-     *  Base of the IDE interface
-     */
-
-#define ATA_HD_BASE	0xfff00000
-
-    /*
-     *  Offsets from the above base
+     *  Offsets from base address
      */
 
 #define ATA_HD_CONTROL	0x39
@@ -114,18 +109,18 @@ static const struct ide_port_info falconide_port_info = {
 	.chipset		= ide_generic,
 };
 
-static void __init falconide_setup_ports(struct ide_hw *hw)
+static void __init falconide_setup_ports(struct ide_hw *hw, unsigned long base)
 {
 	int i;
 
 	memset(hw, 0, sizeof(*hw));
 
-	hw->io_ports.data_addr = ATA_HD_BASE;
+	hw->io_ports.data_addr = base;
 
 	for (i = 1; i < 8; i++)
-		hw->io_ports_array[i] = ATA_HD_BASE + 1 + i * 4;
+		hw->io_ports_array[i] = base + 1 + i * 4;
 
-	hw->io_ports.ctl_addr = ATA_HD_BASE + ATA_HD_CONTROL;
+	hw->io_ports.ctl_addr = base + ATA_HD_CONTROL;
 
 	hw->irq = IRQ_MFP_IDE;
 }
@@ -134,23 +129,29 @@ static void __init falconide_setup_ports(struct ide_hw *hw)
      *  Probe for a Falcon IDE interface
      */
 
-static int __init falconide_init(void)
+static int __init falconide_init(struct platform_device *pdev)
 {
+	struct resource *res;
 	struct ide_host *host;
 	struct ide_hw hw, *hws[] = { &hw };
+	unsigned long base;
 	int rc;
 
-	if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE))
-		return -ENODEV;
+	dev_info(&pdev->dev, "Atari Falcon IDE controller\n");
 
-	printk(KERN_INFO "ide: Falcon IDE controller\n");
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
 
-	if (!request_mem_region(ATA_HD_BASE, 0x40, DRV_NAME)) {
-		printk(KERN_ERR "%s: resources busy\n", DRV_NAME);
+	if (!devm_request_mem_region(&pdev->dev, res->start,
+				     resource_size(res), DRV_NAME)) {
+		dev_err(&pdev->dev, "resources busy\n");
 		return -EBUSY;
 	}
 
-	falconide_setup_ports(&hw);
+	base = (unsigned long)res->start;
+
+	falconide_setup_ports(&hw, base);
 
 	host = ide_host_alloc(&falconide_port_info, hws, 1);
 	if (host == NULL) {
@@ -169,10 +170,29 @@ static int __init falconide_init(void)
 err_free:
 	ide_host_free(host);
 err:
-	release_mem_region(ATA_HD_BASE, 0x40);
+	release_mem_region(res->start, resource_size(res));
 	return rc;
 }
 
-module_init(falconide_init);
+static int falconide_remove(struct platform_device *pdev)
+{
+	struct ide_host *host = dev_get_drvdata(&pdev->dev);
+
+	ide_host_remove(host);
+
+	return 0;
+}
+
+static struct platform_driver ide_falcon_driver = {
+	.remove = falconide_remove,
+	.driver   = {
+		.name	= "atari-falcon-ide",
+	},
+};
+
+module_platform_driver_probe(ide_falcon_driver, falconide_init);
 
+MODULE_AUTHOR("Geert Uytterhoeven");
+MODULE_DESCRIPTION("low-level driver for Atari Falcon IDE");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:atari-falcon-ide");
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 663f8a5012d6..73aee5949b6b 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1399,7 +1399,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev)
 	cookie = dmaengine_submit(desc);
 	ret = dma_submit_error(cookie);
 	if (ret) {
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 		return ret;
 	}
 
@@ -1477,7 +1477,7 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
 		stm32_adc_conv_irq_disable(adc);
 
 	if (adc->dma_chan)
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 
 	if (stm32_adc_set_trig(indio_dev, NULL))
 		dev_err(&indio_dev->dev, "Can't clear trigger\n");
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
index b99d73887c9f..8743b2f376e2 100644
--- a/drivers/iio/imu/adis16480.c
+++ b/drivers/iio/imu/adis16480.c
@@ -317,8 +317,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2)
 	struct adis16480 *st = iio_priv(indio_dev);
 	unsigned int t, reg;
 
+	if (val < 0 || val2 < 0)
+		return -EINVAL;
+
 	t =  val * 1000 + val2 / 1000;
-	if (t <= 0)
+	if (t == 0)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index b17f060b52fc..868281b8adb0 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -114,54 +114,63 @@ static const struct inv_mpu6050_hw hw_info[] = {
 		.name = "MPU6050",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU6500_WHOAMI_VALUE,
 		.name = "MPU6500",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6515_WHOAMI_VALUE,
 		.name = "MPU6515",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6000_WHOAMI_VALUE,
 		.name = "MPU6000",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9150_WHOAMI_VALUE,
 		.name = "MPU9150",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9250_WHOAMI_VALUE,
 		.name = "MPU9250",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU9255_WHOAMI_VALUE,
 		.name = "MPU9255",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20608_WHOAMI_VALUE,
 		.name = "ICM20608",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20602_WHOAMI_VALUE,
 		.name = "ICM20602",
 		.reg = &reg_set_icm20602,
 		.config = &chip_config_6050,
+		.fifo_size = 1008,
 	},
 };
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
index db1c6904388b..51235677c534 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
@@ -100,12 +100,14 @@ struct inv_mpu6050_chip_config {
  *  @name:      name of the chip.
  *  @reg:   register map of the chip.
  *  @config:    configuration of the chip.
+ *  @fifo_size:	size of the FIFO in bytes.
  */
 struct inv_mpu6050_hw {
 	u8 whoami;
 	u8 *name;
 	const struct inv_mpu6050_reg_map *reg;
 	const struct inv_mpu6050_chip_config *config;
+	size_t fifo_size;
 };
 
 /*
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 5f9a5de0bab4..72d8c5790076 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -180,9 +180,6 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 			"failed to ack interrupt\n");
 		goto flush_fifo;
 	}
-	/* handle fifo overflow by reseting fifo */
-	if (int_status & INV_MPU6050_BIT_FIFO_OVERFLOW_INT)
-		goto flush_fifo;
 	if (!(int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT)) {
 		dev_warn(regmap_get_device(st->map),
 			"spurious interrupt with status 0x%x\n", int_status);
@@ -211,6 +208,18 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	if (result)
 		goto end_session;
 	fifo_count = get_unaligned_be16(&data[0]);
+
+	/*
+	 * Handle fifo overflow by resetting fifo.
+	 * Reset if there is only 3 data set free remaining to mitigate
+	 * possible delay between reading fifo count and fifo data.
+	 */
+	nb = 3 * bytes_per_datum;
+	if (fifo_count >= st->hw->fifo_size - nb) {
+		dev_warn(regmap_get_device(st->map), "fifo overflow reset\n");
+		goto flush_fifo;
+	}
+
 	/* compute and process all complete datum */
 	nb = fifo_count / bytes_per_datum;
 	inv_mpu6050_update_period(st, pf->timestamp, nb);
diff --git a/drivers/iio/proximity/srf04.c b/drivers/iio/proximity/srf04.c
index 8b50d56b0a03..01eb8cc63076 100644
--- a/drivers/iio/proximity/srf04.c
+++ b/drivers/iio/proximity/srf04.c
@@ -110,7 +110,7 @@ static int srf04_read(struct srf04_data *data)
 	udelay(data->cfg->trigger_pulse_us);
 	gpiod_set_value(data->gpiod_trig, 0);
 
-	/* it cannot take more than 20 ms */
+	/* it should not take more than 20 ms until echo is rising */
 	ret = wait_for_completion_killable_timeout(&data->rising, HZ/50);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
@@ -120,7 +120,8 @@ static int srf04_read(struct srf04_data *data)
 		return -ETIMEDOUT;
 	}
 
-	ret = wait_for_completion_killable_timeout(&data->falling, HZ/50);
+	/* it cannot take more than 50 ms until echo is falling */
+	ret = wait_for_completion_killable_timeout(&data->falling, HZ/20);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
 		return ret;
@@ -135,19 +136,19 @@ static int srf04_read(struct srf04_data *data)
 
 	dt_ns = ktime_to_ns(ktime_dt);
 	/*
-	 * measuring more than 3 meters is beyond the capabilities of
-	 * the sensor
+	 * measuring more than 6,45 meters is beyond the capabilities of
+	 * the supported sensors
 	 * ==> filter out invalid results for not measuring echos of
 	 *     another us sensor
 	 *
 	 * formula:
-	 *         distance       3 m
-	 * time = ---------- = --------- = 9404389 ns
-	 *          speed       319 m/s
+	 *         distance     6,45 * 2 m
+	 * time = ---------- = ------------ = 40438871 ns
+	 *          speed         319 m/s
 	 *
 	 * using a minimum speed at -20 °C of 319 m/s
 	 */
-	if (dt_ns > 9404389)
+	if (dt_ns > 40438871)
 		return -EIO;
 
 	time_ns = dt_ns;
@@ -159,20 +160,20 @@ static int srf04_read(struct srf04_data *data)
 	 *   with Temp in °C
 	 *   and speed in m/s
 	 *
-	 * use 343 m/s as ultrasonic speed at 20 °C here in absence of the
+	 * use 343,5 m/s as ultrasonic speed at 20 °C here in absence of the
 	 * temperature
 	 *
 	 * therefore:
-	 *             time     343
-	 * distance = ------ * -----
-	 *             10^6       2
+	 *             time     343,5     time * 106
+	 * distance = ------ * ------- = ------------
+	 *             10^6         2         617176
 	 *   with time in ns
 	 *   and distance in mm (one way)
 	 *
-	 * because we limit to 3 meters the multiplication with 343 just
+	 * because we limit to 6,45 meters the multiplication with 106 just
 	 * fits into 32 bit
 	 */
-	distance_mm = time_ns * 343 / 2000000;
+	distance_mm = time_ns * 106 / 617176;
 
 	return distance_mm;
 }
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 3a8b0911c3bc..9d07378b5b42 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -199,6 +199,7 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
+void rdma_nl_init(void);
 void rdma_nl_exit(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2dd2cfe9b561..50a92442c4f7 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2716,6 +2716,8 @@ static int __init ib_core_init(void)
 		goto err_comp_unbound;
 	}
 
+	rdma_nl_init();
+
 	ret = addr_init();
 	if (ret) {
 		pr_warn("Could't init IB address resolution\n");
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 72141c5b7c95..ade71823370f 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -372,6 +372,7 @@ EXPORT_SYMBOL(iw_cm_disconnect);
 static void destroy_cm_id(struct iw_cm_id *cm_id)
 {
 	struct iwcm_id_private *cm_id_priv;
+	struct ib_qp *qp;
 	unsigned long flags;
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
@@ -389,6 +390,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 	set_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags);
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
+
 	switch (cm_id_priv->state) {
 	case IW_CM_STATE_LISTEN:
 		cm_id_priv->state = IW_CM_STATE_DESTROYING;
@@ -401,7 +405,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 		cm_id_priv->state = IW_CM_STATE_DESTROYING;
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 		/* Abrupt close of the connection */
-		(void)iwcm_modify_qp_err(cm_id_priv->qp);
+		(void)iwcm_modify_qp_err(qp);
 		spin_lock_irqsave(&cm_id_priv->lock, flags);
 		break;
 	case IW_CM_STATE_IDLE:
@@ -426,11 +430,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 		BUG();
 		break;
 	}
-	if (cm_id_priv->qp) {
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
-		cm_id_priv->qp = NULL;
-	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
 
 	if (cm_id->mapped) {
 		iwpm_remove_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr);
@@ -671,11 +673,11 @@ int iw_cm_accept(struct iw_cm_id *cm_id,
 		BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_RECV);
 		cm_id_priv->state = IW_CM_STATE_IDLE;
 		spin_lock_irqsave(&cm_id_priv->lock, flags);
-		if (cm_id_priv->qp) {
-			cm_id->device->ops.iw_rem_ref(qp);
-			cm_id_priv->qp = NULL;
-		}
+		qp = cm_id_priv->qp;
+		cm_id_priv->qp = NULL;
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+		if (qp)
+			cm_id->device->ops.iw_rem_ref(qp);
 		clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
 		wake_up_all(&cm_id_priv->connect_wait);
 	}
@@ -696,7 +698,7 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param)
 	struct iwcm_id_private *cm_id_priv;
 	int ret;
 	unsigned long flags;
-	struct ib_qp *qp;
+	struct ib_qp *qp = NULL;
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
 
@@ -730,13 +732,13 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param)
 		return 0;	/* success */
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
-	if (cm_id_priv->qp) {
-		cm_id->device->ops.iw_rem_ref(qp);
-		cm_id_priv->qp = NULL;
-	}
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
 	cm_id_priv->state = IW_CM_STATE_IDLE;
 err:
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id->device->ops.iw_rem_ref(qp);
 	clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
 	wake_up_all(&cm_id_priv->connect_wait);
 	return ret;
@@ -878,6 +880,7 @@ static int cm_conn_est_handler(struct iwcm_id_private *cm_id_priv,
 static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv,
 			       struct iw_cm_event *iw_event)
 {
+	struct ib_qp *qp = NULL;
 	unsigned long flags;
 	int ret;
 
@@ -896,11 +899,13 @@ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv,
 		cm_id_priv->state = IW_CM_STATE_ESTABLISHED;
 	} else {
 		/* REJECTED or RESET */
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
+		qp = cm_id_priv->qp;
 		cm_id_priv->qp = NULL;
 		cm_id_priv->state = IW_CM_STATE_IDLE;
 	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
 	ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
 
 	if (iw_event->private_data_len)
@@ -942,21 +947,18 @@ static void cm_disconnect_handler(struct iwcm_id_private *cm_id_priv,
 static int cm_close_handler(struct iwcm_id_private *cm_id_priv,
 				  struct iw_cm_event *iw_event)
 {
+	struct ib_qp *qp;
 	unsigned long flags;
-	int ret = 0;
+	int ret = 0, notify_event = 0;
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
 
-	if (cm_id_priv->qp) {
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
-		cm_id_priv->qp = NULL;
-	}
 	switch (cm_id_priv->state) {
 	case IW_CM_STATE_ESTABLISHED:
 	case IW_CM_STATE_CLOSING:
 		cm_id_priv->state = IW_CM_STATE_IDLE;
-		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-		ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
-		spin_lock_irqsave(&cm_id_priv->lock, flags);
+		notify_event = 1;
 		break;
 	case IW_CM_STATE_DESTROYING:
 		break;
@@ -965,6 +967,10 @@ static int cm_close_handler(struct iwcm_id_private *cm_id_priv,
 	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
+	if (notify_event)
+		ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 81dbd5f41bed..8cd31ef25eff 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -42,9 +42,12 @@
 #include <linux/module.h>
 #include "core_priv.h"
 
-static DEFINE_MUTEX(rdma_nl_mutex);
 static struct {
-	const struct rdma_nl_cbs   *cb_table;
+	const struct rdma_nl_cbs *cb_table;
+	/* Synchronizes between ongoing netlink commands and netlink client
+	 * unregistration.
+	 */
+	struct rw_semaphore sem;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 bool rdma_nl_chk_listeners(unsigned int group)
@@ -75,70 +78,53 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 	return (op < max_num_ops[type]) ? true : false;
 }
 
-static bool
-is_nl_valid(const struct sk_buff *skb, unsigned int type, unsigned int op)
+static const struct rdma_nl_cbs *
+get_cb_table(const struct sk_buff *skb, unsigned int type, unsigned int op)
 {
 	const struct rdma_nl_cbs *cb_table;
 
-	if (!is_nl_msg_valid(type, op))
-		return false;
-
 	/*
 	 * Currently only NLDEV client is supporting netlink commands in
 	 * non init_net net namespace.
 	 */
 	if (sock_net(skb->sk) != &init_net && type != RDMA_NL_NLDEV)
-		return false;
+		return NULL;
 
-	if (!rdma_nl_types[type].cb_table) {
-		mutex_unlock(&rdma_nl_mutex);
-		request_module("rdma-netlink-subsys-%d", type);
-		mutex_lock(&rdma_nl_mutex);
-	}
+	cb_table = READ_ONCE(rdma_nl_types[type].cb_table);
+	if (!cb_table) {
+		/*
+		 * Didn't get valid reference of the table, attempt module
+		 * load once.
+		 */
+		up_read(&rdma_nl_types[type].sem);
 
-	cb_table = rdma_nl_types[type].cb_table;
+		request_module("rdma-netlink-subsys-%d", type);
 
+		down_read(&rdma_nl_types[type].sem);
+		cb_table = READ_ONCE(rdma_nl_types[type].cb_table);
+	}
 	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
-		return false;
-	return true;
+		return NULL;
+	return cb_table;
 }
 
 void rdma_nl_register(unsigned int index,
 		      const struct rdma_nl_cbs cb_table[])
 {
-	mutex_lock(&rdma_nl_mutex);
-	if (!is_nl_msg_valid(index, 0)) {
-		/*
-		 * All clients are not interesting in success/failure of
-		 * this call. They want to see the print to error log and
-		 * continue their initialization. Print warning for them,
-		 * because it is programmer's error to be here.
-		 */
-		mutex_unlock(&rdma_nl_mutex);
-		WARN(true,
-		     "The not-valid %u index was supplied to RDMA netlink\n",
-		     index);
+	if (WARN_ON(!is_nl_msg_valid(index, 0)) ||
+	    WARN_ON(READ_ONCE(rdma_nl_types[index].cb_table)))
 		return;
-	}
-
-	if (rdma_nl_types[index].cb_table) {
-		mutex_unlock(&rdma_nl_mutex);
-		WARN(true,
-		     "The %u index is already registered in RDMA netlink\n",
-		     index);
-		return;
-	}
 
-	rdma_nl_types[index].cb_table = cb_table;
-	mutex_unlock(&rdma_nl_mutex);
+	/* Pairs with the READ_ONCE in is_nl_valid() */
+	smp_store_release(&rdma_nl_types[index].cb_table, cb_table);
 }
 EXPORT_SYMBOL(rdma_nl_register);
 
 void rdma_nl_unregister(unsigned int index)
 {
-	mutex_lock(&rdma_nl_mutex);
+	down_write(&rdma_nl_types[index].sem);
 	rdma_nl_types[index].cb_table = NULL;
-	mutex_unlock(&rdma_nl_mutex);
+	up_write(&rdma_nl_types[index].sem);
 }
 EXPORT_SYMBOL(rdma_nl_unregister);
 
@@ -170,15 +156,21 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
 	const struct rdma_nl_cbs *cb_table;
+	int err = -EINVAL;
 
-	if (!is_nl_valid(skb, index, op))
+	if (!is_nl_msg_valid(index, op))
 		return -EINVAL;
 
-	cb_table = rdma_nl_types[index].cb_table;
+	down_read(&rdma_nl_types[index].sem);
+	cb_table = get_cb_table(skb, index, op);
+	if (!cb_table)
+		goto done;
 
 	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
-	    !netlink_capable(skb, CAP_NET_ADMIN))
-		return -EPERM;
+	    !netlink_capable(skb, CAP_NET_ADMIN)) {
+		err = -EPERM;
+		goto done;
+	}
 
 	/*
 	 * LS responses overload the 0x100 (NLM_F_ROOT) flag.  Don't
@@ -186,8 +178,8 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 */
 	if (index == RDMA_NL_LS) {
 		if (cb_table[op].doit)
-			return cb_table[op].doit(skb, nlh, extack);
-		return -EINVAL;
+			err = cb_table[op].doit(skb, nlh, extack);
+		goto done;
 	}
 	/* FIXME: Convert IWCM to properly handle doit callbacks */
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_IWCM) {
@@ -195,14 +187,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			.dump = cb_table[op].dump,
 		};
 		if (c.dump)
-			return netlink_dump_start(skb->sk, skb, nlh, &c);
-		return -EINVAL;
+			err = netlink_dump_start(skb->sk, skb, nlh, &c);
+		goto done;
 	}
 
 	if (cb_table[op].doit)
-		return cb_table[op].doit(skb, nlh, extack);
-
-	return 0;
+		err = cb_table[op].doit(skb, nlh, extack);
+done:
+	up_read(&rdma_nl_types[index].sem);
+	return err;
 }
 
 /*
@@ -263,9 +256,7 @@ skip:
 
 static void rdma_nl_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&rdma_nl_mutex);
 	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
-	mutex_unlock(&rdma_nl_mutex);
 }
 
 int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid)
@@ -297,6 +288,14 @@ int rdma_nl_multicast(struct net *net, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(rdma_nl_multicast);
 
+void rdma_nl_init(void)
+{
+	int idx;
+
+	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
+		init_rwsem(&rdma_nl_types[idx].sem);
+}
+
 void rdma_nl_exit(void)
 {
 	int idx;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 65b36548bc17..c03af08b80e7 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -778,7 +778,7 @@ static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin,
 		container_of(res, struct rdma_counter, res);
 
 	if (port && port != counter->port)
-		return 0;
+		return -EAGAIN;
 
 	/* Dump it even query failed */
 	rdma_counter_query_stats(counter);
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 1e5aeb39f774..63f7f7db5902 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -98,7 +98,7 @@ ib_uverbs_init_udata_buf_or_null(struct ib_udata *udata,
 
 struct ib_uverbs_device {
 	atomic_t				refcount;
-	int					num_comp_vectors;
+	u32					num_comp_vectors;
 	struct completion			comp;
 	struct device				dev;
 	/* First group for device attributes, NULL terminated array */
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index f974b6854224..35c2841a569e 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -662,16 +662,17 @@ static bool find_gid_index(const union ib_gid *gid,
 			   void *context)
 {
 	struct find_gid_index_context *ctx = context;
+	u16 vlan_id = 0xffff;
+	int ret;
 
 	if (ctx->gid_type != gid_attr->gid_type)
 		return false;
 
-	if ((!!(ctx->vlan_id != 0xffff) == !is_vlan_dev(gid_attr->ndev)) ||
-	    (is_vlan_dev(gid_attr->ndev) &&
-	     vlan_dev_vlan_id(gid_attr->ndev) != ctx->vlan_id))
+	ret = rdma_read_gid_l2_fields(gid_attr, &vlan_id, NULL);
+	if (ret)
 		return false;
 
-	return true;
+	return ctx->vlan_id == vlan_id;
 }
 
 static const struct ib_gid_attr *
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index e87fc0408470..347dc242fb88 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -495,7 +495,6 @@ static int _put_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb)
 
 	ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
 	release_ep_resources(ep);
-	kfree_skb(skb);
 	return 0;
 }
 
@@ -506,7 +505,6 @@ static int _put_pass_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
 	c4iw_put_ep(&ep->parent_ep->com);
 	release_ep_resources(ep);
-	kfree_skb(skb);
 	return 0;
 }
 
@@ -2424,20 +2422,6 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 	enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type;
 
 	pr_debug("ep %p tid %u\n", ep, ep->hwtid);
-
-	skb_get(skb);
-	rpl = cplhdr(skb);
-	if (!is_t4(adapter_type)) {
-		skb_trim(skb, roundup(sizeof(*rpl5), 16));
-		rpl5 = (void *)rpl;
-		INIT_TP_WR(rpl5, ep->hwtid);
-	} else {
-		skb_trim(skb, sizeof(*rpl));
-		INIT_TP_WR(rpl, ep->hwtid);
-	}
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
-						    ep->hwtid));
-
 	cxgb_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
 		      enable_tcp_timestamps && req->tcpopt.tstamp,
 		      (ep->com.remote_addr.ss_family == AF_INET) ? 0 : 1);
@@ -2483,6 +2467,20 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 		if (tcph->ece && tcph->cwr)
 			opt2 |= CCTRL_ECN_V(1);
 	}
+
+	skb_get(skb);
+	rpl = cplhdr(skb);
+	if (!is_t4(adapter_type)) {
+		skb_trim(skb, roundup(sizeof(*rpl5), 16));
+		rpl5 = (void *)rpl;
+		INIT_TP_WR(rpl5, ep->hwtid);
+	} else {
+		skb_trim(skb, sizeof(*rpl));
+		INIT_TP_WR(rpl, ep->hwtid);
+	}
+	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
+						    ep->hwtid));
+
 	if (CHELSIO_CHIP_VERSION(adapter_type) > CHELSIO_T4) {
 		u32 isn = (prandom_u32() & ~7UL) - 1;
 		opt2 |= T5_OPT_2_VALID_F;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 71cb9525c074..26b792bb1027 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1489,7 +1489,6 @@ static int __init hfi1_mod_init(void)
 		goto bail_dev;
 	}
 
-	hfi1_compute_tid_rdma_flow_wt();
 	/*
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 61aa5504d7c3..61362bd6d3ce 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -319,7 +319,9 @@ int pcie_speeds(struct hfi1_devdata *dd)
 	/*
 	 * bus->max_bus_speed is set from the bridge's linkcap Max Link Speed
 	 */
-	if (parent && dd->pcidev->bus->max_bus_speed != PCIE_SPEED_8_0GT) {
+	if (parent &&
+	    (dd->pcidev->bus->max_bus_speed == PCIE_SPEED_2_5GT ||
+	     dd->pcidev->bus->max_bus_speed == PCIE_SPEED_5_0GT)) {
 		dd_dev_info(dd, "Parent PCIe bridge does not support Gen3\n");
 		dd->link_gen3_capable = 0;
 	}
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 513a8aac9ccd..1a3c647675a7 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -2209,15 +2209,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 		if (qp->s_flags & RVT_S_WAIT_RNR)
 			goto bail_stop;
 		rdi = ib_to_rvt(qp->ibqp.device);
-		if (qp->s_rnr_retry == 0 &&
-		    !((rdi->post_parms[wqe->wr.opcode].flags &
-		      RVT_OPERATION_IGN_RNR_CNT) &&
-		      qp->s_rnr_retry_cnt == 0)) {
-			status = IB_WC_RNR_RETRY_EXC_ERR;
-			goto class_b;
+		if (!(rdi->post_parms[wqe->wr.opcode].flags &
+		       RVT_OPERATION_IGN_RNR_CNT)) {
+			if (qp->s_rnr_retry == 0) {
+				status = IB_WC_RNR_RETRY_EXC_ERR;
+				goto class_b;
+			}
+			if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
+				qp->s_rnr_retry--;
 		}
-		if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
-			qp->s_rnr_retry--;
 
 		/*
 		 * The last valid PSN is the previous PSN. For TID RDMA WRITE
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 2ed7bfd5feea..c61b6022575e 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -65,6 +65,7 @@
 #define SDMA_DESCQ_CNT 2048
 #define SDMA_DESC_INTR 64
 #define INVALID_TAIL 0xffff
+#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32))
 
 static uint sdma_descq_cnt = SDMA_DESCQ_CNT;
 module_param(sdma_descq_cnt, uint, S_IRUGO);
@@ -1296,7 +1297,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
 	struct sdma_engine *sde;
 
 	if (dd->sdma_pad_dma) {
-		dma_free_coherent(&dd->pcidev->dev, 4,
+		dma_free_coherent(&dd->pcidev->dev, SDMA_PAD,
 				  (void *)dd->sdma_pad_dma,
 				  dd->sdma_pad_phys);
 		dd->sdma_pad_dma = NULL;
@@ -1491,7 +1492,7 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 	}
 
 	/* Allocate memory for pad */
-	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32),
+	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD,
 					      &dd->sdma_pad_phys, GFP_KERNEL);
 	if (!dd->sdma_pad_dma) {
 		dd_dev_err(dd, "failed to allocate SendDMA pad memory\n");
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index b4dcc4d29f84..e53f542b60af 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -107,8 +107,6 @@ static u32 mask_generation(u32 a)
  * C - Capcode
  */
 
-static u32 tid_rdma_flow_wt;
-
 static void tid_rdma_trigger_resume(struct work_struct *work);
 static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req);
 static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req,
@@ -136,6 +134,26 @@ static void update_r_next_psn_fecn(struct hfi1_packet *packet,
 				   struct tid_rdma_flow *flow,
 				   bool fecn);
 
+static void validate_r_tid_ack(struct hfi1_qp_priv *priv)
+{
+	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
+		priv->r_tid_ack = priv->r_tid_tail;
+}
+
+static void tid_rdma_schedule_ack(struct rvt_qp *qp)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	priv->s_flags |= RVT_S_ACK_PENDING;
+	hfi1_schedule_tid_send(qp);
+}
+
+static void tid_rdma_trigger_ack(struct rvt_qp *qp)
+{
+	validate_r_tid_ack(qp->priv);
+	tid_rdma_schedule_ack(qp);
+}
+
 static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p)
 {
 	return
@@ -2736,11 +2754,6 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd,
 				diff = cmp_psn(psn,
 					       flow->flow_state.r_next_psn);
 				if (diff > 0) {
-					if (!(qp->r_flags & RVT_R_RDMAR_SEQ))
-						restart_tid_rdma_read_req(rcd,
-									  qp,
-									  wqe);
-
 					/* Drop the packet.*/
 					goto s_unlock;
 				} else if (diff < 0) {
@@ -3010,10 +3023,7 @@ nak_psn:
 		qpriv->s_nak_state = IB_NAK_PSN_ERROR;
 		/* We are NAK'ing the next expected PSN */
 		qpriv->s_nak_psn = mask_psn(flow->flow_state.r_next_psn);
-		qpriv->s_flags |= RVT_S_ACK_PENDING;
-		if (qpriv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			qpriv->r_tid_ack = qpriv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
+		tid_rdma_trigger_ack(qp);
 	}
 	goto unlock;
 }
@@ -3376,18 +3386,17 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32);
 }
 
-void hfi1_compute_tid_rdma_flow_wt(void)
+static u32 hfi1_compute_tid_rdma_flow_wt(struct rvt_qp *qp)
 {
 	/*
 	 * Heuristic for computing the RNR timeout when waiting on the flow
 	 * queue. Rather than a computationaly expensive exact estimate of when
 	 * a flow will be available, we assume that if a QP is at position N in
 	 * the flow queue it has to wait approximately (N + 1) * (number of
-	 * segments between two sync points), assuming PMTU of 4K. The rationale
-	 * for this is that flows are released and recycled at each sync point.
+	 * segments between two sync points). The rationale for this is that
+	 * flows are released and recycled at each sync point.
 	 */
-	tid_rdma_flow_wt = MAX_TID_FLOW_PSN * enum_to_mtu(OPA_MTU_4096) /
-		TID_RDMA_MAX_SEGMENT_SIZE;
+	return (MAX_TID_FLOW_PSN * qp->pmtu) >> TID_RDMA_SEGMENT_SHIFT;
 }
 
 static u32 position_in_queue(struct hfi1_qp_priv *qpriv,
@@ -3510,7 +3519,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		if (qpriv->flow_state.index >= RXE_NUM_TID_FLOWS) {
 			ret = hfi1_kern_setup_hw_flow(qpriv->rcd, qp);
 			if (ret) {
-				to_seg = tid_rdma_flow_wt *
+				to_seg = hfi1_compute_tid_rdma_flow_wt(qp) *
 					position_in_queue(qpriv,
 							  &rcd->flow_queue);
 				break;
@@ -3531,7 +3540,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		/*
 		 * If overtaking req->acked_tail, send an RNR NAK. Because the
 		 * QP is not queued in this case, and the issue can only be
-		 * caused due a delay in scheduling the second leg which we
+		 * caused by a delay in scheduling the second leg which we
 		 * cannot estimate, we use a rather arbitrary RNR timeout of
 		 * (MAX_FLOWS / 2) segments
 		 */
@@ -3539,8 +3548,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 				MAX_FLOWS)) {
 			ret = -EAGAIN;
 			to_seg = MAX_FLOWS >> 1;
-			qpriv->s_flags |= RVT_S_ACK_PENDING;
-			hfi1_schedule_tid_send(qp);
+			tid_rdma_trigger_ack(qp);
 			break;
 		}
 
@@ -4340,8 +4348,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	trace_hfi1_tid_req_rcv_write_data(qp, 0, e->opcode, e->psn, e->lpsn,
 					  req);
 	trace_hfi1_tid_write_rsp_rcv_data(qp);
-	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
-		priv->r_tid_ack = priv->r_tid_tail;
+	validate_r_tid_ack(priv);
 
 	if (opcode == TID_OP(WRITE_DATA_LAST)) {
 		release_rdma_sge_mr(e);
@@ -4380,8 +4387,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	}
 
 done:
-	priv->s_flags |= RVT_S_ACK_PENDING;
-	hfi1_schedule_tid_send(qp);
+	tid_rdma_schedule_ack(qp);
 exit:
 	priv->r_next_psn_kdeth = flow->flow_state.r_next_psn;
 	if (fecn)
@@ -4393,10 +4399,7 @@ send_nak:
 	if (!priv->s_nak_state) {
 		priv->s_nak_state = IB_NAK_PSN_ERROR;
 		priv->s_nak_psn = flow->flow_state.r_next_psn;
-		priv->s_flags |= RVT_S_ACK_PENDING;
-		if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			priv->r_tid_ack = priv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
+		tid_rdma_trigger_ack(qp);
 	}
 	goto done;
 }
@@ -4944,8 +4947,7 @@ void hfi1_rc_rcv_tid_rdma_resync(struct hfi1_packet *packet)
 	qpriv->resync = true;
 	/* RESYNC request always gets a TID RDMA ACK. */
 	qpriv->s_nak_state = 0;
-	qpriv->s_flags |= RVT_S_ACK_PENDING;
-	hfi1_schedule_tid_send(qp);
+	tid_rdma_trigger_ack(qp);
 bail:
 	if (fecn)
 		qp->s_flags |= RVT_S_ECN;
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h
index 1c536185261e..6e82df2190b7 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.h
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.h
@@ -17,6 +17,7 @@
 #define TID_RDMA_MIN_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_PAGES              (BIT(18) >> PAGE_SHIFT)
+#define TID_RDMA_SEGMENT_SHIFT		18
 
 /*
  * Bit definitions for priv->s_flags.
@@ -274,8 +275,6 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 				  struct ib_other_headers *ohdr,
 				  u32 *bth1, u32 *bth2, u32 *len);
 
-void hfi1_compute_tid_rdma_flow_wt(void);
-
 void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet);
 
 u32 hfi1_build_tid_rdma_write_resp(struct rvt_qp *qp, struct rvt_ack_entry *e,
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 7bff0a1e713d..089e201d7550 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -147,9 +147,6 @@ static int pio_wait(struct rvt_qp *qp,
 /* Length of buffer to create verbs txreq cache name */
 #define TXREQ_NAME_LEN 24
 
-/* 16B trailing buffer */
-static const u8 trail_buf[MAX_16B_PADDING];
-
 static uint wss_threshold = 80;
 module_param(wss_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
@@ -820,8 +817,8 @@ static int build_verbs_tx_desc(
 
 	/* add icrc, lt byte, and padding to flit */
 	if (extra_bytes)
-		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
-					(void *)trail_buf, extra_bytes);
+		ret = sdma_txadd_daddr(sde->dd, &tx->txreq,
+				       sde->dd->sdma_pad_phys, extra_bytes);
 
 bail_txadd:
 	return ret;
@@ -1089,7 +1086,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 		/* add icrc, lt byte, and padding to flit */
 		if (extra_bytes)
-			seg_pio_copy_mid(pbuf, trail_buf, extra_bytes);
+			seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma,
+					 extra_bytes);
 
 		seg_pio_copy_end(pbuf);
 	}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h
index 86783276fb1f..3bb8f78fb7b0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.h
@@ -59,7 +59,7 @@ enum {
 
 #define HNS_ROCE_HEM_CHUNK_LEN	\
 	 ((256 - sizeof(struct list_head) - 2 * sizeof(int)) /	 \
-	 (sizeof(struct scatterlist)))
+	 (sizeof(struct scatterlist) + sizeof(void *)))
 
 #define check_whether_bt_num_3(type, hop_num) \
 	(type < HEM_TYPE_MTT && hop_num == 2)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 7a89d669f8bf..e82567fcdeb7 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -5389,9 +5389,9 @@ static void hns_roce_v2_free_eq(struct hns_roce_dev *hr_dev,
 		return;
 	}
 
-	if (eq->buf_list)
-		dma_free_coherent(hr_dev->dev, buf_chk_sz,
-				  eq->buf_list->buf, eq->buf_list->map);
+	dma_free_coherent(hr_dev->dev, buf_chk_sz, eq->buf_list->buf,
+			  eq->buf_list->map);
+	kfree(eq->buf_list);
 }
 
 static void hns_roce_config_eqc(struct hns_roce_dev *hr_dev,
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index 9591457eb768..43ea2c13b212 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -376,7 +376,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq,
 	srq->max = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1);
 	srq->max_gs = srq_init_attr->attr.max_sge;
 
-	srq_desc_size = max(16, 16 * srq->max_gs);
+	srq_desc_size = roundup_pow_of_two(max(16, 16 * srq->max_gs));
 
 	srq->wqe_shift = ilog2(srq_desc_size);
 
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 630599311586..7019c12005f4 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1967,8 +1967,8 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 	int err;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		xa_erase(&dev->mdev->priv.mkey_table,
-			 mlx5_base_mkey(mmw->mmkey.key));
+		xa_erase_irq(&dev->mdev->priv.mkey_table,
+			     mlx5_base_mkey(mmw->mmkey.key));
 		/*
 		 * pagefault_single_data_segment() may be accessing mmw under
 		 * SRCU if the user bound an ODP MR to this MW.
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8937d72ddcf6..5fd071c05944 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3249,10 +3249,12 @@ static int modify_raw_packet_qp_sq(
 	}
 
 	/* Only remove the old rate after new rate was set */
-	if ((old_rl.rate &&
-	     !mlx5_rl_are_equal(&old_rl, &new_rl)) ||
-	    (new_state != MLX5_SQC_STATE_RDY))
+	if ((old_rl.rate && !mlx5_rl_are_equal(&old_rl, &new_rl)) ||
+	    (new_state != MLX5_SQC_STATE_RDY)) {
 		mlx5_rl_remove_rate(dev, &old_rl);
+		if (new_state != MLX5_SQC_STATE_RDY)
+			memset(&new_rl, 0, sizeof(new_rl));
+	}
 
 	ibqp->rl = new_rl;
 	sq->state = new_state;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 5136b835e1ba..dc71b6e16a07 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -76,7 +76,7 @@ static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str)
 	struct qedr_dev *qedr = get_qedr_dev(ibdev);
 	u32 fw_ver = (u32)qedr->attr.fw_ver;
 
-	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d",
 		 (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
 		 (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
 }
diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c
index 52d402f39df9..b4317480cee7 100644
--- a/drivers/infiniband/sw/siw/siw_qp.c
+++ b/drivers/infiniband/sw/siw/siw_qp.c
@@ -1312,6 +1312,7 @@ int siw_qp_add(struct siw_device *sdev, struct siw_qp *qp)
 void siw_free_qp(struct kref *ref)
 {
 	struct siw_qp *found, *qp = container_of(ref, struct siw_qp, ref);
+	struct siw_base_qp *siw_base_qp = to_siw_base_qp(qp->ib_qp);
 	struct siw_device *sdev = qp->sdev;
 	unsigned long flags;
 
@@ -1334,4 +1335,5 @@ void siw_free_qp(struct kref *ref)
 	atomic_dec(&sdev->num_qp);
 	siw_dbg_qp(qp, "free QP\n");
 	kfree_rcu(qp, rcu);
+	kfree(siw_base_qp);
 }
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 869e02b69a01..b18a677832e1 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -604,7 +604,6 @@ out:
 int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata)
 {
 	struct siw_qp *qp = to_siw_qp(base_qp);
-	struct siw_base_qp *siw_base_qp = to_siw_base_qp(base_qp);
 	struct siw_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct siw_ucontext,
 					  base_ucontext);
@@ -641,7 +640,6 @@ int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata)
 	qp->scq = qp->rcq = NULL;
 
 	siw_qp_put(qp);
-	kfree(siw_base_qp);
 
 	return 0;
 }
diff --git a/drivers/input/ff-memless.c b/drivers/input/ff-memless.c
index 1cb40c7475af..8229a9006917 100644
--- a/drivers/input/ff-memless.c
+++ b/drivers/input/ff-memless.c
@@ -489,6 +489,15 @@ static void ml_ff_destroy(struct ff_device *ff)
 {
 	struct ml_device *ml = ff->private;
 
+	/*
+	 * Even though we stop all playing effects when tearing down
+	 * an input device (via input_device_flush() that calls into
+	 * input_ff_flush() that stops and erases all effects), we
+	 * do not actually stop the timer, and therefore we should
+	 * do it here.
+	 */
+	del_timer_sync(&ml->timer);
+
 	kfree(ml->private);
 }
 
diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index dace8577fa43..79851923ee57 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -232,10 +232,7 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 	onkey->input->phys = onkey->phys;
 	onkey->input->dev.parent = &pdev->dev;
 
-	if (onkey->key_power)
-		input_set_capability(onkey->input, EV_KEY, KEY_POWER);
-
-	input_set_capability(onkey->input, EV_KEY, KEY_SLEEP);
+	input_set_capability(onkey->input, EV_KEY, KEY_POWER);
 
 	INIT_DELAYED_WORK(&onkey->work, da9063_poll_on);
 
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 97e3639e99d0..08520b3a18b8 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -92,11 +92,18 @@ soc_button_device_create(struct platform_device *pdev,
 			continue;
 
 		gpio = soc_button_lookup_gpio(&pdev->dev, info->acpi_index);
-		if (gpio < 0 && gpio != -ENOENT) {
-			error = gpio;
-			goto err_free_mem;
-		} else if (!gpio_is_valid(gpio)) {
-			/* Skip GPIO if not present */
+		if (!gpio_is_valid(gpio)) {
+			/*
+			 * Skip GPIO if not present. Note we deliberately
+			 * ignore -EPROBE_DEFER errors here. On some devices
+			 * Intel is using so called virtual GPIOs which are not
+			 * GPIOs at all but some way for AML code to check some
+			 * random status bits without need a custom opregion.
+			 * In some cases the resources table we parse points to
+			 * such a virtual GPIO, since these are not real GPIOs
+			 * we do not have a driver for these so they will never
+			 * show up, therefore we ignore -EPROBE_DEFER.
+			 */
 			continue;
 		}
 
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 04fe43440a3c..2d8434b7b623 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1827,31 +1827,6 @@ static int elantech_create_smbus(struct psmouse *psmouse,
 				  leave_breadcrumbs);
 }
 
-static bool elantech_use_host_notify(struct psmouse *psmouse,
-				     struct elantech_device_info *info)
-{
-	if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
-		return true;
-
-	switch (info->bus) {
-	case ETP_BUS_PS2_ONLY:
-		/* expected case */
-		break;
-	case ETP_BUS_SMB_HST_NTFY_ONLY:
-	case ETP_BUS_PS2_SMB_HST_NTFY:
-		/* SMbus implementation is stable since 2018 */
-		if (dmi_get_bios_year() >= 2018)
-			return true;
-		/* fall through */
-	default:
-		psmouse_dbg(psmouse,
-			    "Ignoring SMBus bus provider %d\n", info->bus);
-		break;
-	}
-
-	return false;
-}
-
 /**
  * elantech_setup_smbus - called once the PS/2 devices are enumerated
  * and decides to instantiate a SMBus InterTouch device.
@@ -1871,7 +1846,7 @@ static int elantech_setup_smbus(struct psmouse *psmouse,
 		 * i2c_blacklist_pnp_ids.
 		 * Old ICs are up to the user to decide.
 		 */
-		if (!elantech_use_host_notify(psmouse, info) ||
+		if (!ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version) ||
 		    psmouse_matches_pnp_id(psmouse, i2c_blacklist_pnp_ids))
 			return -ENXIO;
 	}
@@ -1891,6 +1866,34 @@ static int elantech_setup_smbus(struct psmouse *psmouse,
 	return 0;
 }
 
+static bool elantech_use_host_notify(struct psmouse *psmouse,
+				     struct elantech_device_info *info)
+{
+	if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
+		return true;
+
+	switch (info->bus) {
+	case ETP_BUS_PS2_ONLY:
+		/* expected case */
+		break;
+	case ETP_BUS_SMB_ALERT_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_ALERT:
+		psmouse_dbg(psmouse, "Ignoring SMBus provider through alert protocol.\n");
+		break;
+	case ETP_BUS_SMB_HST_NTFY_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_HST_NTFY:
+		return true;
+	default:
+		psmouse_dbg(psmouse,
+			    "Ignoring SMBus bus provider %d.\n",
+			    info->bus);
+	}
+
+	return false;
+}
+
 int elantech_init_smbus(struct psmouse *psmouse)
 {
 	struct elantech_device_info info;
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 772493b1f665..190b9974526b 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -146,7 +146,7 @@ static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
 	}
 
 	mutex_lock(&data->irq_mutex);
-	bitmap_and(data->irq_status, data->irq_status, data->current_irq_mask,
+	bitmap_and(data->irq_status, data->irq_status, data->fn_irq_bits,
 	       data->irq_count);
 	/*
 	 * At this point, irq_status has all bits that are set in the
@@ -385,6 +385,8 @@ static int rmi_driver_set_irq_bits(struct rmi_device *rmi_dev,
 	bitmap_copy(data->current_irq_mask, data->new_irq_mask,
 		    data->num_of_irq_regs);
 
+	bitmap_or(data->fn_irq_bits, data->fn_irq_bits, mask, data->irq_count);
+
 error_unlock:
 	mutex_unlock(&data->irq_mutex);
 	return error;
@@ -398,6 +400,8 @@ static int rmi_driver_clear_irq_bits(struct rmi_device *rmi_dev,
 	struct device *dev = &rmi_dev->dev;
 
 	mutex_lock(&data->irq_mutex);
+	bitmap_andnot(data->fn_irq_bits,
+		      data->fn_irq_bits, mask, data->irq_count);
 	bitmap_andnot(data->new_irq_mask,
 		  data->current_irq_mask, mask, data->irq_count);
 
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index f28a7158b2ef..bbf9ae9f3f0c 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -510,7 +510,6 @@ struct f11_data {
 	struct rmi_2d_sensor_platform_data sensor_pdata;
 	unsigned long *abs_mask;
 	unsigned long *rel_mask;
-	unsigned long *result_bits;
 };
 
 enum f11_finger_state {
@@ -1057,7 +1056,7 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 	/*
 	** init instance data, fill in values and create any sysfs files
 	*/
-	f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 3,
+	f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 2,
 			GFP_KERNEL);
 	if (!f11)
 		return -ENOMEM;
@@ -1076,8 +1075,6 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 			+ sizeof(struct f11_data));
 	f11->rel_mask = (unsigned long *)((char *)f11
 			+ sizeof(struct f11_data) + mask_size);
-	f11->result_bits = (unsigned long *)((char *)f11
-			+ sizeof(struct f11_data) + mask_size * 2);
 
 	set_bit(fn->irq_pos, f11->abs_mask);
 	set_bit(fn->irq_pos + 1, f11->rel_mask);
@@ -1284,8 +1281,8 @@ static irqreturn_t rmi_f11_attention(int irq, void *ctx)
 			valid_bytes = f11->sensor.attn_size;
 		memcpy(f11->sensor.data_pkt, drvdata->attn_data.data,
 			valid_bytes);
-		drvdata->attn_data.data += f11->sensor.attn_size;
-		drvdata->attn_data.size -= f11->sensor.attn_size;
+		drvdata->attn_data.data += valid_bytes;
+		drvdata->attn_data.size -= valid_bytes;
 	} else {
 		error = rmi_read_block(rmi_dev,
 				data_base_addr, f11->sensor.data_pkt,
diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c
index d20a5d6780d1..7e97944f7616 100644
--- a/drivers/input/rmi4/rmi_f12.c
+++ b/drivers/input/rmi4/rmi_f12.c
@@ -55,6 +55,9 @@ struct f12_data {
 
 	const struct rmi_register_desc_item *data15;
 	u16 data15_offset;
+
+	unsigned long *abs_mask;
+	unsigned long *rel_mask;
 };
 
 static int rmi_f12_read_sensor_tuning(struct f12_data *f12)
@@ -209,8 +212,8 @@ static irqreturn_t rmi_f12_attention(int irq, void *ctx)
 			valid_bytes = sensor->attn_size;
 		memcpy(sensor->data_pkt, drvdata->attn_data.data,
 			valid_bytes);
-		drvdata->attn_data.data += sensor->attn_size;
-		drvdata->attn_data.size -= sensor->attn_size;
+		drvdata->attn_data.data += valid_bytes;
+		drvdata->attn_data.size -= valid_bytes;
 	} else {
 		retval = rmi_read_block(rmi_dev, f12->data_addr,
 					sensor->data_pkt, sensor->pkt_size);
@@ -291,9 +294,18 @@ static int rmi_f12_write_control_regs(struct rmi_function *fn)
 static int rmi_f12_config(struct rmi_function *fn)
 {
 	struct rmi_driver *drv = fn->rmi_dev->driver;
+	struct f12_data *f12 = dev_get_drvdata(&fn->dev);
+	struct rmi_2d_sensor *sensor;
 	int ret;
 
-	drv->set_irq_bits(fn->rmi_dev, fn->irq_mask);
+	sensor = &f12->sensor;
+
+	if (!sensor->report_abs)
+		drv->clear_irq_bits(fn->rmi_dev, f12->abs_mask);
+	else
+		drv->set_irq_bits(fn->rmi_dev, f12->abs_mask);
+
+	drv->clear_irq_bits(fn->rmi_dev, f12->rel_mask);
 
 	ret = rmi_f12_write_control_regs(fn);
 	if (ret)
@@ -315,9 +327,12 @@ static int rmi_f12_probe(struct rmi_function *fn)
 	struct rmi_device_platform_data *pdata = rmi_get_platform_data(rmi_dev);
 	struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev);
 	u16 data_offset = 0;
+	int mask_size;
 
 	rmi_dbg(RMI_DEBUG_FN, &fn->dev, "%s\n", __func__);
 
+	mask_size = BITS_TO_LONGS(drvdata->irq_count) * sizeof(unsigned long);
+
 	ret = rmi_read(fn->rmi_dev, query_addr, &buf);
 	if (ret < 0) {
 		dev_err(&fn->dev, "Failed to read general info register: %d\n",
@@ -332,10 +347,19 @@ static int rmi_f12_probe(struct rmi_function *fn)
 		return -ENODEV;
 	}
 
-	f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data), GFP_KERNEL);
+	f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data) + mask_size * 2,
+			GFP_KERNEL);
 	if (!f12)
 		return -ENOMEM;
 
+	f12->abs_mask = (unsigned long *)((char *)f12
+			+ sizeof(struct f12_data));
+	f12->rel_mask = (unsigned long *)((char *)f12
+			+ sizeof(struct f12_data) + mask_size);
+
+	set_bit(fn->irq_pos, f12->abs_mask);
+	set_bit(fn->irq_pos + 1, f12->rel_mask);
+
 	f12->has_dribble = !!(buf & BIT(3));
 
 	if (fn->dev.of_node) {
diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
index 710b02595486..897105b9a98b 100644
--- a/drivers/input/rmi4/rmi_f54.c
+++ b/drivers/input/rmi4/rmi_f54.c
@@ -359,7 +359,7 @@ static const struct vb2_ops rmi_f54_queue_ops = {
 static const struct vb2_queue rmi_f54_queue = {
 	.type = V4L2_BUF_TYPE_VIDEO_CAPTURE,
 	.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ,
-	.buf_struct_size = sizeof(struct vb2_buffer),
+	.buf_struct_size = sizeof(struct vb2_v4l2_buffer),
 	.ops = &rmi_f54_queue_ops,
 	.mem_ops = &vb2_vmalloc_memops,
 	.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC,
@@ -601,7 +601,7 @@ static int rmi_f54_config(struct rmi_function *fn)
 {
 	struct rmi_driver *drv = fn->rmi_dev->driver;
 
-	drv->set_irq_bits(fn->rmi_dev, fn->irq_mask);
+	drv->clear_irq_bits(fn->rmi_dev, fn->irq_mask);
 
 	return 0;
 }
@@ -730,6 +730,7 @@ static void rmi_f54_remove(struct rmi_function *fn)
 
 	video_unregister_device(&f54->vdev);
 	v4l2_device_unregister(&f54->v4l2);
+	destroy_workqueue(f54->workqueue);
 }
 
 struct rmi_function_handler rmi_f54_handler = {
diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c
index 4b22d49a0f49..6bcffc930384 100644
--- a/drivers/input/touchscreen/cyttsp4_core.c
+++ b/drivers/input/touchscreen/cyttsp4_core.c
@@ -1990,11 +1990,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd)
 
 	/* get sysinfo */
 	md->si = &cd->sysinfo;
-	if (!md->si) {
-		dev_err(dev, "%s: Fail get sysinfo pointer from core p=%p\n",
-			__func__, md->si);
-		goto error_get_sysinfo;
-	}
 
 	rc = cyttsp4_setup_input_device(cd);
 	if (rc)
@@ -2004,8 +1999,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd)
 
 error_init_input:
 	input_free_device(md->input);
-error_get_sysinfo:
-	input_set_drvdata(md->input, NULL);
 error_alloc_failed:
 	dev_err(dev, "%s failed.\n", __func__);
 	return rc;
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 5178ea8b5f30..fb43aa708660 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -53,6 +53,7 @@ struct goodix_ts_data {
 	const char *cfg_name;
 	struct completion firmware_loading_complete;
 	unsigned long irq_flags;
+	unsigned int contact_size;
 };
 
 #define GOODIX_GPIO_INT_NAME		"irq"
@@ -62,6 +63,7 @@ struct goodix_ts_data {
 #define GOODIX_MAX_WIDTH		4096
 #define GOODIX_INT_TRIGGER		1
 #define GOODIX_CONTACT_SIZE		8
+#define GOODIX_MAX_CONTACT_SIZE		9
 #define GOODIX_MAX_CONTACTS		10
 
 #define GOODIX_CONFIG_MAX_LENGTH	240
@@ -144,6 +146,19 @@ static const struct dmi_system_id rotated_screen[] = {
 	{}
 };
 
+static const struct dmi_system_id nine_bytes_report[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		.ident = "Lenovo YogaBook",
+		/* YB1-X91L/F and YB1-X90L/F */
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9")
+		}
+	},
+#endif
+	{}
+};
+
 /**
  * goodix_i2c_read - read data from a register of the i2c slave device.
  *
@@ -249,7 +264,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 	max_timeout = jiffies + msecs_to_jiffies(GOODIX_BUFFER_STATUS_TIMEOUT);
 	do {
 		error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR,
-					data, GOODIX_CONTACT_SIZE + 1);
+					data, ts->contact_size + 1);
 		if (error) {
 			dev_err(&ts->client->dev, "I2C transfer error: %d\n",
 					error);
@@ -262,12 +277,12 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 				return -EPROTO;
 
 			if (touch_num > 1) {
-				data += 1 + GOODIX_CONTACT_SIZE;
+				data += 1 + ts->contact_size;
 				error = goodix_i2c_read(ts->client,
 						GOODIX_READ_COOR_ADDR +
-							1 + GOODIX_CONTACT_SIZE,
+							1 + ts->contact_size,
 						data,
-						GOODIX_CONTACT_SIZE *
+						ts->contact_size *
 							(touch_num - 1));
 				if (error)
 					return error;
@@ -286,7 +301,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 	return 0;
 }
 
-static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
+static void goodix_ts_report_touch_8b(struct goodix_ts_data *ts, u8 *coor_data)
 {
 	int id = coor_data[0] & 0x0F;
 	int input_x = get_unaligned_le16(&coor_data[1]);
@@ -301,6 +316,21 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
 	input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w);
 }
 
+static void goodix_ts_report_touch_9b(struct goodix_ts_data *ts, u8 *coor_data)
+{
+	int id = coor_data[1] & 0x0F;
+	int input_x = get_unaligned_le16(&coor_data[3]);
+	int input_y = get_unaligned_le16(&coor_data[5]);
+	int input_w = get_unaligned_le16(&coor_data[7]);
+
+	input_mt_slot(ts->input_dev, id);
+	input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, true);
+	touchscreen_report_pos(ts->input_dev, &ts->prop,
+			       input_x, input_y, true);
+	input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, input_w);
+	input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w);
+}
+
 /**
  * goodix_process_events - Process incoming events
  *
@@ -311,7 +341,7 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
  */
 static void goodix_process_events(struct goodix_ts_data *ts)
 {
-	u8  point_data[1 + GOODIX_CONTACT_SIZE * GOODIX_MAX_CONTACTS];
+	u8  point_data[1 + GOODIX_MAX_CONTACT_SIZE * GOODIX_MAX_CONTACTS];
 	int touch_num;
 	int i;
 
@@ -326,8 +356,12 @@ static void goodix_process_events(struct goodix_ts_data *ts)
 	input_report_key(ts->input_dev, KEY_LEFTMETA, point_data[0] & BIT(4));
 
 	for (i = 0; i < touch_num; i++)
-		goodix_ts_report_touch(ts,
-				&point_data[1 + GOODIX_CONTACT_SIZE * i]);
+		if (ts->contact_size == 9)
+			goodix_ts_report_touch_9b(ts,
+				&point_data[1 + ts->contact_size * i]);
+		else
+			goodix_ts_report_touch_8b(ts,
+				&point_data[1 + ts->contact_size * i]);
 
 	input_mt_sync_frame(ts->input_dev);
 	input_sync(ts->input_dev);
@@ -730,6 +764,13 @@ static int goodix_configure_dev(struct goodix_ts_data *ts)
 			"Applying '180 degrees rotated screen' quirk\n");
 	}
 
+	if (dmi_check_system(nine_bytes_report)) {
+		ts->contact_size = 9;
+
+		dev_dbg(&ts->client->dev,
+			"Non-standard 9-bytes report format quirk\n");
+	}
+
 	error = input_mt_init_slots(ts->input_dev, ts->max_touch_num,
 				    INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
 	if (error) {
@@ -810,6 +851,7 @@ static int goodix_ts_probe(struct i2c_client *client,
 	ts->client = client;
 	i2c_set_clientdata(client, ts);
 	init_completion(&ts->firmware_loading_complete);
+	ts->contact_size = GOODIX_CONTACT_SIZE;
 
 	error = goodix_get_gpio_config(ts);
 	if (error)
diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c
index 34923399ece4..1139714e72e2 100644
--- a/drivers/input/touchscreen/st1232.c
+++ b/drivers/input/touchscreen/st1232.c
@@ -81,8 +81,10 @@ static int st1232_ts_read_data(struct st1232_ts_data *ts)
 	for (i = 0, y = 0; i < ts->chip_info->max_fingers; i++, y += 3) {
 		finger[i].is_valid = buf[i + y] >> 7;
 		if (finger[i].is_valid) {
-			finger[i].x = ((buf[i + y] & 0x0070) << 4) | buf[i + 1];
-			finger[i].y = ((buf[i + y] & 0x0007) << 8) | buf[i + 2];
+			finger[i].x = ((buf[i + y] & 0x0070) << 4) |
+					buf[i + y + 1];
+			finger[i].y = ((buf[i + y] & 0x0007) << 8) |
+					buf[i + y + 2];
 
 			/* st1232 includes a z-axis / touch strength */
 			if (ts->chip_info->have_z)
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 7b971228df38..c498796adc07 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -405,8 +405,12 @@ void icc_set_tag(struct icc_path *path, u32 tag)
 	if (!path)
 		return;
 
+	mutex_lock(&icc_lock);
+
 	for (i = 0; i < path->num_nodes; i++)
 		path->reqs[i].tag = tag;
+
+	mutex_unlock(&icc_lock);
 }
 EXPORT_SYMBOL_GPL(icc_set_tag);
 
diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c
index 910081d6ddc0..b4966d8f3348 100644
--- a/drivers/interconnect/qcom/qcs404.c
+++ b/drivers/interconnect/qcom/qcs404.c
@@ -433,7 +433,8 @@ static int qnoc_probe(struct platform_device *pdev)
 	if (!qp)
 		return -ENOMEM;
 
-	data = devm_kcalloc(dev, num_nodes, sizeof(*node), GFP_KERNEL);
+	data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes),
+			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c
index 57955596bb59..502a6c22b41e 100644
--- a/drivers/interconnect/qcom/sdm845.c
+++ b/drivers/interconnect/qcom/sdm845.c
@@ -790,7 +790,8 @@ static int qnoc_probe(struct platform_device *pdev)
 	if (!qp)
 		return -ENOMEM;
 
-	data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL);
+	data = devm_kzalloc(&pdev->dev, struct_size(data, nodes, num_nodes),
+			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2369b8af81f3..dd555078258c 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -583,7 +583,8 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
 	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	pasid   = PPR_PASID(*(u64 *)&event[0]);
+	pasid   = (event[0] & EVENT_DOMID_MASK_HI) |
+		  (event[1] & EVENT_DOMID_MASK_LO);
 	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	address = (u64)(((u64)event[3]) << 32) | event[2];
 
@@ -616,7 +617,7 @@ retry:
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
@@ -1463,6 +1464,7 @@ static void free_pagetable(struct protection_domain *domain)
  * to 64 bits.
  */
 static bool increase_address_space(struct protection_domain *domain,
+				   unsigned long address,
 				   gfp_t gfp)
 {
 	unsigned long flags;
@@ -1471,8 +1473,8 @@ static bool increase_address_space(struct protection_domain *domain,
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
-		/* address space already 64 bit large */
+	if (address <= PM_LEVEL_SIZE(domain->mode) ||
+	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
@@ -1505,7 +1507,7 @@ static u64 *alloc_pte(struct protection_domain *domain,
 	BUG_ON(!is_power_of_2(page_size));
 
 	while (address > PM_LEVEL_SIZE(domain->mode))
-		*updated = increase_address_space(domain, gfp) || *updated;
+		*updated = increase_address_space(domain, address, gfp) || *updated;
 
 	level   = domain->mode - 1;
 	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
diff --git a/drivers/iommu/amd_iommu_quirks.c b/drivers/iommu/amd_iommu_quirks.c
index c235f79b7a20..5120ce4fdce3 100644
--- a/drivers/iommu/amd_iommu_quirks.c
+++ b/drivers/iommu/amd_iommu_quirks.c
@@ -74,6 +74,19 @@ static const struct dmi_system_id ivrs_quirks[] __initconst = {
 		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
 	},
 	{
+		/*
+		 * Acer Aspire A315-41 requires the very same workaround as
+		 * Dell Latitude 5495
+		 */
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Acer Aspire A315-41",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
 		.callback = ivrs_ioapic_quirk_cb,
 		.ident = "Lenovo ideapad 330S-15ARR",
 		.matches = {
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index c9c1612d52e0..17bd5a349119 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -130,8 +130,8 @@
 #define EVENT_TYPE_INV_PPR_REQ	0x9
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
-#define EVENT_DOMID_MASK	0xffff
-#define EVENT_DOMID_SHIFT	0
+#define EVENT_DOMID_MASK_LO	0xffff
+#define EVENT_DOMID_MASK_HI	0xf0000
 #define EVENT_FLAGS_MASK	0xfff
 #define EVENT_FLAGS_SHIFT	0x10
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b18aac4c105e..7c503a6bc585 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -812,6 +812,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	return 0;
 
 out_clear_smmu:
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
 	smmu_domain->smmu = NULL;
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 3f974919d3bd..6db6d969e31c 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2794,7 +2794,7 @@ static int identity_mapping(struct device *dev)
 	struct device_domain_info *info;
 
 	info = dev->archdata.iommu;
-	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
 		return (info->domain == si_domain);
 
 	return 0;
@@ -3471,7 +3471,7 @@ static bool iommu_need_mapping(struct device *dev)
 		if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
 			dma_mask = dev->coherent_dma_mask;
 
-		if (dma_mask >= dma_get_required_mask(dev))
+		if (dma_mask >= dma_direct_get_required_mask(dev))
 			return false;
 
 		/*
@@ -3775,6 +3775,13 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	return nelems;
 }
 
+static u64 intel_get_required_mask(struct device *dev)
+{
+	if (!iommu_need_mapping(dev))
+		return dma_direct_get_required_mask(dev);
+	return DMA_BIT_MASK(32);
+}
+
 static const struct dma_map_ops intel_dma_ops = {
 	.alloc = intel_alloc_coherent,
 	.free = intel_free_coherent,
@@ -3787,6 +3794,7 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.get_required_mask = intel_get_required_mask,
 };
 
 static void
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 4c91359057c5..ca51036aa53c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -166,6 +166,9 @@
 #define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
 #define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
 
+#define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
+#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
+
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
@@ -1015,27 +1018,56 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 static struct io_pgtable *
 arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
+	struct arm_lpae_io_pgtable *data;
 
-	if (cfg->ias != 48 || cfg->oas > 40)
+	/* No quirks for Mali (hopefully) */
+	if (cfg->quirks)
+		return NULL;
+
+	if (cfg->ias > 48 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		u64 mair, ttbr;
 
-		/* Copy values as union fields overlap */
-		mair = cfg->arm_lpae_s1_cfg.mair[0];
-		ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
 
-		cfg->arm_mali_lpae_cfg.memattr = mair;
-		cfg->arm_mali_lpae_cfg.transtab = ttbr |
-			ARM_MALI_LPAE_TTBR_READ_INNER |
-			ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	/* Mali seems to need a full 4-level table regardless of IAS */
+	if (data->levels < ARM_LPAE_MAX_LEVELS) {
+		data->levels = ARM_LPAE_MAX_LEVELS;
+		data->pgd_size = sizeof(arm_lpae_iopte);
 	}
+	/*
+	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
+	 * best we can do is mimic the out-of-tree driver and hope that the
+	 * "implementation-defined caching policy" is good enough. Similarly,
+	 * we'll use it for the sake of a valid attribute for our 'device'
+	 * index, although callers should never request that in practice.
+	 */
+	cfg->arm_mali_lpae_cfg.memattr =
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+		(ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
-	return iop;
+	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before TRANSTAB can be written */
+	wmb();
+
+	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
+					  ARM_MALI_LPAE_TTBR_READ_INNER |
+					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9da8309f7170..2639fc718117 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1086,8 +1086,6 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts);
 
-	irq = platform_get_irq(pdev, 0);
-
 	/*
 	 * Determine if this IPMMU instance is a root device by checking for
 	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
@@ -1106,10 +1104,9 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	/* Root devices have mandatory IRQs */
 	if (ipmmu_is_root(mmu)) {
-		if (irq < 0) {
-			dev_err(&pdev->dev, "no IRQ found\n");
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0)
 			return irq;
-		}
 
 		ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
 				       dev_name(&pdev->dev), mmu);
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 26290f310f90..4dcbf68dfda4 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -100,6 +100,7 @@ struct rk_iommu {
 	struct device *dev;
 	void __iomem **bases;
 	int num_mmu;
+	int num_irq;
 	struct clk_bulk_data *clocks;
 	int num_clocks;
 	bool reset_disabled;
@@ -1136,7 +1137,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct rk_iommu *iommu;
 	struct resource *res;
 	int num_res = pdev->num_resources;
-	int err, i, irq;
+	int err, i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
@@ -1163,6 +1164,10 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (iommu->num_mmu == 0)
 		return PTR_ERR(iommu->bases[0]);
 
+	iommu->num_irq = platform_irq_count(pdev);
+	if (iommu->num_irq < 0)
+		return iommu->num_irq;
+
 	iommu->reset_disabled = device_property_read_bool(dev,
 					"rockchip,disable-mmu-reset");
 
@@ -1219,8 +1224,9 @@ static int rk_iommu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	i = 0;
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) {
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
 		if (irq < 0)
 			return irq;
 
@@ -1245,10 +1251,13 @@ err_unprepare_clocks:
 static void rk_iommu_shutdown(struct platform_device *pdev)
 {
 	struct rk_iommu *iommu = platform_get_drvdata(pdev);
-	int i = 0, irq;
+	int i;
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
 
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO)
 		devm_free_irq(iommu->dev, irq, iommu);
+	}
 
 	pm_runtime_force_suspend(&pdev->dev);
 }
diff --git a/drivers/irqchip/irq-al-fic.c b/drivers/irqchip/irq-al-fic.c
index 1a57cee3efab..0b0a73739756 100644
--- a/drivers/irqchip/irq-al-fic.c
+++ b/drivers/irqchip/irq-al-fic.c
@@ -15,6 +15,7 @@
 
 /* FIC Registers */
 #define AL_FIC_CAUSE		0x00
+#define AL_FIC_SET_CAUSE	0x08
 #define AL_FIC_MASK		0x10
 #define AL_FIC_CONTROL		0x28
 
@@ -126,6 +127,16 @@ static void al_fic_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(irqchip, desc);
 }
 
+static int al_fic_irq_retrigger(struct irq_data *data)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	struct al_fic *fic = gc->private;
+
+	writel_relaxed(BIT(data->hwirq), fic->base + AL_FIC_SET_CAUSE);
+
+	return 1;
+}
+
 static int al_fic_register(struct device_node *node,
 			   struct al_fic *fic)
 {
@@ -159,6 +170,7 @@ static int al_fic_register(struct device_node *node,
 	gc->chip_types->chip.irq_unmask = irq_gc_mask_clr_bit;
 	gc->chip_types->chip.irq_ack = irq_gc_ack_clr_bit;
 	gc->chip_types->chip.irq_set_type = al_fic_irq_set_type;
+	gc->chip_types->chip.irq_retrigger = al_fic_irq_retrigger;
 	gc->chip_types->chip.flags = IRQCHIP_SKIP_SET_WAKE;
 	gc->private = fic;
 
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 6acad2ea0fb3..29333497ba10 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -313,6 +313,7 @@ static void __init sama5d3_aic_irq_fixup(void)
 static const struct of_device_id aic5_irq_fixups[] __initconst = {
 	{ .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup },
 	{ .compatible = "atmel,sama5d4", .data = sama5d3_aic_irq_fixup },
+	{ .compatible = "microchip,sam9x60", .data = sama5d3_aic_irq_fixup },
 	{ /* sentinel */ },
 };
 
@@ -390,3 +391,12 @@ static int __init sama5d4_aic5_of_init(struct device_node *node,
 	return aic5_of_init(node, parent, NR_SAMA5D4_IRQS);
 }
 IRQCHIP_DECLARE(sama5d4_aic5, "atmel,sama5d4-aic", sama5d4_aic5_of_init);
+
+#define NR_SAM9X60_IRQS		50
+
+static int __init sam9x60_aic5_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAM9X60_IRQS);
+}
+IRQCHIP_DECLARE(sam9x60_aic5, "microchip,sam9x60-aic", sam9x60_aic5_of_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 62e54f1a248b..787e8eec9a7f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -175,6 +175,22 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static u16 get_its_list(struct its_vm *vm)
+{
+	struct its_node *its;
+	unsigned long its_list = 0;
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (!its->is_v4)
+			continue;
+
+		if (vm->vlpi_count[its->list_nr])
+			__set_bit(its->list_nr, &its_list);
+	}
+
+	return (u16)its_list;
+}
+
 static struct its_collection *dev_event_to_col(struct its_device *its_dev,
 					       u32 event)
 {
@@ -976,17 +992,15 @@ static void its_send_vmapp(struct its_node *its,
 
 static void its_send_vmovp(struct its_vpe *vpe)
 {
-	struct its_cmd_desc desc;
+	struct its_cmd_desc desc = {};
 	struct its_node *its;
 	unsigned long flags;
 	int col_id = vpe->col_idx;
 
 	desc.its_vmovp_cmd.vpe = vpe;
-	desc.its_vmovp_cmd.its_list = (u16)its_list_map;
 
 	if (!its_list_map) {
 		its = list_first_entry(&its_nodes, struct its_node, entry);
-		desc.its_vmovp_cmd.seq_num = 0;
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
 		its_send_single_vcommand(its, its_build_vmovp_cmd, &desc);
 		return;
@@ -1003,6 +1017,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
 
 	desc.its_vmovp_cmd.seq_num = vmovp_seq_num++;
+	desc.its_vmovp_cmd.its_list = get_its_list(vpe->its_vm);
 
 	/* Emit VMOVPs */
 	list_for_each_entry(its, &its_nodes, entry) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 422664ac5f53..6bb1f682f78b 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -59,7 +59,7 @@ static struct gic_chip_data gic_data __read_mostly;
 static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 
 #define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
-#define GIC_LINE_NR	max(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
+#define GIC_LINE_NR	min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
 /*
@@ -87,6 +87,15 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
  */
 static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
 
+/*
+ * Global static key controlling whether an update to PMR allowing more
+ * interrupts requires to be propagated to the redistributor (DSB SY).
+ * And this needs to be exported for modules to be able to enable
+ * interrupts...
+ */
+DEFINE_STATIC_KEY_FALSE(gic_pmr_sync);
+EXPORT_SYMBOL(gic_pmr_sync);
+
 /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
 static refcount_t *ppi_nmi_refs;
 
@@ -1502,6 +1511,17 @@ static void gic_enable_nmi_support(void)
 	for (i = 0; i < gic_data.ppi_nr; i++)
 		refcount_set(&ppi_nmi_refs[i], 0);
 
+	/*
+	 * Linux itself doesn't use 1:N distribution, so has no need to
+	 * set PMHE. The only reason to have it set is if EL3 requires it
+	 * (and we can't change it).
+	 */
+	if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK)
+		static_branch_enable(&gic_pmr_sync);
+
+	pr_info("%s ICC_PMR_EL1 synchronisation\n",
+		static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing");
+
 	static_branch_enable(&supports_pseudo_nmis);
 
 	if (static_branch_likely(&supports_deactivate_key))
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index c72c036aea76..7d0a12fe2714 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -97,7 +97,7 @@ static inline void plic_irq_toggle(const struct cpumask *mask,
 	}
 }
 
-static void plic_irq_enable(struct irq_data *d)
+static void plic_irq_unmask(struct irq_data *d)
 {
 	unsigned int cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
 					   cpu_online_mask);
@@ -106,7 +106,7 @@ static void plic_irq_enable(struct irq_data *d)
 	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
 }
 
-static void plic_irq_disable(struct irq_data *d)
+static void plic_irq_mask(struct irq_data *d)
 {
 	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
 }
@@ -125,10 +125,8 @@ static int plic_set_affinity(struct irq_data *d,
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	if (!irqd_irq_disabled(d)) {
-		plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
-		plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
-	}
+	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
+	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -136,14 +134,18 @@ static int plic_set_affinity(struct irq_data *d,
 }
 #endif
 
+static void plic_irq_eoi(struct irq_data *d)
+{
+	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+
+	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+}
+
 static struct irq_chip plic_chip = {
 	.name		= "SiFive PLIC",
-	/*
-	 * There is no need to mask/unmask PLIC interrupts.  They are "masked"
-	 * by reading claim and "unmasked" when writing it back.
-	 */
-	.irq_enable	= plic_irq_enable,
-	.irq_disable	= plic_irq_disable,
+	.irq_mask	= plic_irq_mask,
+	.irq_unmask	= plic_irq_unmask,
+	.irq_eoi	= plic_irq_eoi,
 #ifdef CONFIG_SMP
 	.irq_set_affinity = plic_set_affinity,
 #endif
@@ -152,7 +154,7 @@ static struct irq_chip plic_chip = {
 static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &plic_chip, handle_simple_irq);
+	irq_set_chip_and_handler(irq, &plic_chip, handle_fasteoi_irq);
 	irq_set_chip_data(irq, NULL);
 	irq_set_noprobe(irq);
 	return 0;
@@ -188,7 +190,6 @@ static void plic_handle_irq(struct pt_regs *regs)
 					hwirq);
 		else
 			generic_handle_irq(irq);
-		writel(hwirq, claim);
 	}
 	csr_set(sie, SIE_SEIE);
 }
@@ -251,8 +252,8 @@ static int __init plic_init(struct device_node *node,
 			continue;
 		}
 
-		/* skip context holes */
-		if (parent.args[0] == -1)
+		/* skip contexts other than supervisor external interrupt */
+		if (parent.args[0] != IRQ_S_EXT)
 			continue;
 
 		hartid = plic_find_hart_id(parent.np);
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index c92b405b7646..ba8619524231 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -744,7 +744,7 @@ capi_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &(cdev->recvwait), wait);
 	mask = EPOLLOUT | EPOLLWRNORM;
-	if (!skb_queue_empty(&cdev->recvqueue))
+	if (!skb_queue_empty_lockless(&cdev->recvqueue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	return mask;
 }
diff --git a/drivers/macintosh/windfarm_cpufreq_clamp.c b/drivers/macintosh/windfarm_cpufreq_clamp.c
index 705c6200814b..7b726f00f183 100644
--- a/drivers/macintosh/windfarm_cpufreq_clamp.c
+++ b/drivers/macintosh/windfarm_cpufreq_clamp.c
@@ -18,7 +18,7 @@
 
 static int clamped;
 static struct wf_control *clamp_control;
-static struct dev_pm_qos_request qos_req;
+static struct freq_qos_request qos_req;
 static unsigned int min_freq, max_freq;
 
 static int clamp_set(struct wf_control *ct, s32 value)
@@ -35,7 +35,7 @@ static int clamp_set(struct wf_control *ct, s32 value)
 	}
 	clamped = value;
 
-	return dev_pm_qos_update_request(&qos_req, freq);
+	return freq_qos_update_request(&qos_req, freq);
 }
 
 static int clamp_get(struct wf_control *ct, s32 *value)
@@ -77,38 +77,44 @@ static int __init wf_cpufreq_clamp_init(void)
 
 	min_freq = policy->cpuinfo.min_freq;
 	max_freq = policy->cpuinfo.max_freq;
+
+	ret = freq_qos_add_request(&policy->constraints, &qos_req, FREQ_QOS_MAX,
+				   max_freq);
+
 	cpufreq_cpu_put(policy);
 
+	if (ret < 0) {
+		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
+		       ret);
+		return ret;
+	}
+
 	dev = get_cpu_device(0);
 	if (unlikely(!dev)) {
 		pr_warn("%s: No cpu device for cpu0\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto fail;
 	}
 
 	clamp = kmalloc(sizeof(struct wf_control), GFP_KERNEL);
-	if (clamp == NULL)
-		return -ENOMEM;
-
-	ret = dev_pm_qos_add_request(dev, &qos_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     max_freq);
-	if (ret < 0) {
-		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
-		       ret);
-		goto free;
+	if (clamp == NULL) {
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	clamp->ops = &clamp_ops;
 	clamp->name = "cpufreq-clamp";
 	ret = wf_register_control(clamp);
 	if (ret)
-		goto fail;
+		goto free;
+
 	clamp_control = clamp;
 	return 0;
- fail:
-	dev_pm_qos_remove_request(&qos_req);
 
  free:
 	kfree(clamp);
+ fail:
+	freq_qos_remove_request(&qos_req);
 	return ret;
 }
 
@@ -116,7 +122,7 @@ static void __exit wf_cpufreq_clamp_exit(void)
 {
 	if (clamp_control) {
 		wf_unregister_control(clamp_control);
-		dev_pm_qos_remove_request(&qos_req);
+		freq_qos_remove_request(&qos_req);
 	}
 }
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index aa98953f4462..d6d5ab23c088 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -38,9 +38,9 @@ config MD_AUTODETECT
 	default y
 	---help---
 	  If you say Y here, then the kernel will try to autodetect raid
-	  arrays as part of its boot process. 
+	  arrays as part of its boot process.
 
-	  If you don't use raid and say Y, this autodetection can cause 
+	  If you don't use raid and say Y, this autodetection can cause
 	  a several-second delay in the boot time due to various
 	  synchronisation steps that are part of this step.
 
@@ -290,7 +290,7 @@ config DM_SNAPSHOT
        depends on BLK_DEV_DM
        select DM_BUFIO
        ---help---
-         Allow volume managers to take writable snapshots of a device.
+	 Allow volume managers to take writable snapshots of a device.
 
 config DM_THIN_PROVISIONING
        tristate "Thin provisioning target"
@@ -298,7 +298,7 @@ config DM_THIN_PROVISIONING
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         Provides thin provisioning and snapshots that share a data store.
+	 Provides thin provisioning and snapshots that share a data store.
 
 config DM_CACHE
        tristate "Cache target (EXPERIMENTAL)"
@@ -307,23 +307,23 @@ config DM_CACHE
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         dm-cache attempts to improve performance of a block device by
-         moving frequently used data to a smaller, higher performance
-         device.  Different 'policy' plugins can be used to change the
-         algorithms used to select which blocks are promoted, demoted,
-         cleaned etc.  It supports writeback and writethrough modes.
+	 dm-cache attempts to improve performance of a block device by
+	 moving frequently used data to a smaller, higher performance
+	 device.  Different 'policy' plugins can be used to change the
+	 algorithms used to select which blocks are promoted, demoted,
+	 cleaned etc.  It supports writeback and writethrough modes.
 
 config DM_CACHE_SMQ
        tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)"
        depends on DM_CACHE
        default y
        ---help---
-         A cache policy that uses a multiqueue ordered by recent hits
-         to select which blocks should be promoted and demoted.
-         This is meant to be a general purpose policy.  It prioritises
-         reads over writes.  This SMQ policy (vs MQ) offers the promise
-         of less memory utilization, improved performance and increased
-         adaptability in the face of changing workloads.
+	 A cache policy that uses a multiqueue ordered by recent hits
+	 to select which blocks should be promoted and demoted.
+	 This is meant to be a general purpose policy.  It prioritises
+	 reads over writes.  This SMQ policy (vs MQ) offers the promise
+	 of less memory utilization, improved performance and increased
+	 adaptability in the face of changing workloads.
 
 config DM_WRITECACHE
 	tristate "Writecache target"
@@ -343,9 +343,9 @@ config DM_ERA
        select DM_PERSISTENT_DATA
        select DM_BIO_PRISON
        ---help---
-         dm-era tracks which parts of a block device are written to
-         over time.  Useful for maintaining cache coherency when using
-         vendor snapshots.
+	 dm-era tracks which parts of a block device are written to
+	 over time.  Useful for maintaining cache coherency when using
+	 vendor snapshots.
 
 config DM_CLONE
        tristate "Clone target (EXPERIMENTAL)"
@@ -353,20 +353,20 @@ config DM_CLONE
        default n
        select DM_PERSISTENT_DATA
        ---help---
-         dm-clone produces a one-to-one copy of an existing, read-only source
-         device into a writable destination device. The cloned device is
-         visible/mountable immediately and the copy of the source device to the
-         destination device happens in the background, in parallel with user
-         I/O.
+	 dm-clone produces a one-to-one copy of an existing, read-only source
+	 device into a writable destination device. The cloned device is
+	 visible/mountable immediately and the copy of the source device to the
+	 destination device happens in the background, in parallel with user
+	 I/O.
 
-         If unsure, say N.
+	 If unsure, say N.
 
 config DM_MIRROR
        tristate "Mirror target"
        depends on BLK_DEV_DM
        ---help---
-         Allow volume managers to mirror logical volumes, also
-         needed for live data migration tools such as 'pvmove'.
+	 Allow volume managers to mirror logical volumes, also
+	 needed for live data migration tools such as 'pvmove'.
 
 config DM_LOG_USERSPACE
 	tristate "Mirror userspace logging"
@@ -483,7 +483,7 @@ config DM_FLAKEY
        tristate "Flakey target"
        depends on BLK_DEV_DM
        ---help---
-         A target that intermittently fails I/O for debugging purposes.
+	 A target that intermittently fails I/O for debugging purposes.
 
 config DM_VERITY
 	tristate "Verity target support"
diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile
index d26b35195825..fd714628da6a 100644
--- a/drivers/md/bcache/Makefile
+++ b/drivers/md/bcache/Makefile
@@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE)	+= bcache.o
 bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
 	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
 	util.o writeback.o
-
-CFLAGS_request.o	+= -Iblock
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 6f776823b9ba..a1df0d95151c 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -377,7 +377,10 @@ retry_invalidate:
 			if (!fifo_full(&ca->free_inc))
 				goto retry_invalidate;
 
-			bch_prio_write(ca);
+			if (bch_prio_write(ca, false) < 0) {
+				ca->invalidate_needs_gc = 1;
+				wake_up_gc(ca->set);
+			}
 		}
 	}
 out:
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 013e35a9e317..9198c1b480d9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -582,6 +582,7 @@ struct cache_set {
 	 */
 	wait_queue_head_t	btree_cache_wait;
 	struct task_struct	*btree_cache_alloc_lock;
+	spinlock_t		btree_cannibalize_lock;
 
 	/*
 	 * When we free a btree node, we increment the gen of the bucket the
@@ -723,6 +724,7 @@ struct cache_set {
 	unsigned int		gc_always_rewrite:1;
 	unsigned int		shrinker_disabled:1;
 	unsigned int		copy_gc_enabled:1;
+	unsigned int		idle_max_writeback_rate_enabled:1;
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
@@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc);
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...);
 
-void bch_prio_write(struct cache *ca);
+int bch_prio_write(struct cache *ca, bool wait);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 08768796b543..cffcdc9feefb 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s)
 	return 0;
 }
 
+/* Pop the top key of keylist by pointing l->top to its previous key */
 struct bkey *bch_keylist_pop(struct keylist *l)
 {
 	struct bkey *k = l->keys;
@@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l)
 	return l->top = k;
 }
 
+/* Pop the bottom key of keylist and update l->top_p */
 void bch_keylist_pop_front(struct keylist *l)
 {
 	l->top_p -= bkey_u64s(l->keys);
@@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b)
 	t->tree = NULL;
 	t->data = NULL;
 }
-EXPORT_SYMBOL(bch_btree_keys_free);
 
 int bch_btree_keys_alloc(struct btree_keys *b,
 			 unsigned int page_order,
@@ -342,7 +343,6 @@ err:
 	bch_btree_keys_free(b);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(bch_btree_keys_alloc);
 
 void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 			 bool *expensive_debug_checks)
@@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 	 * any more.
 	 */
 }
-EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
@@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 
 	bch_bset_build_unwritten_tree(b);
 }
-EXPORT_SYMBOL(bch_bset_init_next);
 
 /*
  * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
@@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b)
 	     j = inorder_next(j, t->size))
 		make_bfloat(t, j);
 }
-EXPORT_SYMBOL(bch_bset_build_written_tree);
 
 /* Insert */
 
@@ -780,7 +777,6 @@ fix_right:	do {
 			j = j * 2 + 1;
 		} while (j < t->size);
 }
-EXPORT_SYMBOL(bch_bset_fix_invalidated_key);
 
 static void bch_bset_fix_lookup_table(struct btree_keys *b,
 				      struct bset_tree *t,
@@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r)
 
 	return b->ops->key_merge(b, l, r);
 }
-EXPORT_SYMBOL(bch_bkey_try_merge);
 
 void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 		     struct bkey *insert)
@@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 	bkey_copy(where, insert);
 	bch_bset_fix_lookup_table(b, t, where);
 }
-EXPORT_SYMBOL(bch_bset_insert);
 
 unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 			      struct bkey *replace_key)
@@ -931,7 +925,6 @@ copy:	bkey_copy(m, k);
 merged:
 	return status;
 }
-EXPORT_SYMBOL(bch_btree_insert_key);
 
 /* Lookup */
 
@@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 	return i.l;
 }
-EXPORT_SYMBOL(__bch_bset_search);
 
 /* Btree iterator */
 
@@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b,
 {
 	return __bch_btree_iter_init(b, iter, search, b->set);
 }
-EXPORT_SYMBOL(bch_btree_iter_init);
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 						 btree_iter_cmp_fn *cmp)
@@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 	return __bch_btree_iter_next(iter, btree_iter_cmp);
 
 }
-EXPORT_SYMBOL(bch_btree_iter_next);
 
 struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 					struct btree_keys *b, ptr_filter_fn fn)
@@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state,
 
 	return mempool_init_page_pool(&state->pool, 1, page_order);
 }
-EXPORT_SYMBOL(bch_bset_sort_state_init);
 
 static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
@@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
-EXPORT_SYMBOL(bch_btree_sort_partial);
 
 void bch_btree_sort_and_fix_extents(struct btree_keys *b,
 				    struct btree_iter *iter,
@@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state)
 out:
 	bch_bset_build_written_tree(b);
 }
-EXPORT_SYMBOL(bch_btree_sort_lazy);
 
 void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats)
 {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ba434d9ac720..14d6c33b0957 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 
 	set_btree_node_dirty(b);
 
+	/*
+	 * w->journal is always the oldest journal pin of all bkeys
+	 * in the leaf node, to make sure the oldest jset seq won't
+	 * be increased before this btree node is flushed.
+	 */
 	if (journal_ref) {
 		if (w->journal &&
 		    journal_pin_cmp(b->c, w->journal, journal_ref)) {
@@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink,
 	 * IO can always make forward progress:
 	 */
 	nr /= c->btree_pages;
+	if (nr == 0)
+		nr = 1;
 	nr = min_t(unsigned long, nr, mca_can_free(c));
 
 	i = 0;
@@ -884,15 +891,17 @@ out:
 
 static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op)
 {
-	struct task_struct *old;
-
-	old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current);
-	if (old && old != current) {
+	spin_lock(&c->btree_cannibalize_lock);
+	if (likely(c->btree_cache_alloc_lock == NULL)) {
+		c->btree_cache_alloc_lock = current;
+	} else if (c->btree_cache_alloc_lock != current) {
 		if (op)
 			prepare_to_wait(&c->btree_cache_wait, &op->wait,
 					TASK_UNINTERRUPTIBLE);
+		spin_unlock(&c->btree_cannibalize_lock);
 		return -EINTR;
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 
 	return 0;
 }
@@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
  */
 static void bch_cannibalize_unlock(struct cache_set *c)
 {
+	spin_lock(&c->btree_cannibalize_lock);
 	if (c->btree_cache_alloc_lock == current) {
 		c->btree_cache_alloc_lock = NULL;
 		wake_up(&c->btree_cache_wait);
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 }
 
 static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index c12cd809ab19..0164a1fe94a9 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v)
 {
 	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
 }
-EXPORT_SYMBOL(closure_sub);
 
 /*
  * closure_put - decrement a closure's refcount
@@ -54,7 +53,6 @@ void closure_put(struct closure *cl)
 {
 	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
 }
-EXPORT_SYMBOL(closure_put);
 
 /*
  * closure_wake_up - wake up all closures on a wait list, without memory barrier
@@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list)
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
 }
-EXPORT_SYMBOL(__closure_wake_up);
 
 /**
  * closure_wait - add a closure to a waitlist
@@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
 
 	return true;
 }
-EXPORT_SYMBOL(closure_wait);
 
 struct closure_syncer {
 	struct task_struct	*task;
@@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl)
 
 	__set_current_state(TASK_RUNNING);
 }
-EXPORT_SYMBOL(__closure_sync);
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
@@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl)
 	list_add(&cl->all, &closure_list);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_create);
 
 void closure_debug_destroy(struct closure *cl)
 {
@@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl)
 	list_del(&cl->all);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_destroy);
 
 static struct dentry *closure_debug;
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 41adcd1546f1..73478a91a342 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl)
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
 
-	/*
-	 * If we're looping, might already be waiting on
-	 * another journal write - can't wait on more than one journal write at
-	 * a time
-	 *
-	 * XXX: this looks wrong
-	 */
-#if 0
-	while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING)
-		closure_sync(&s->cl);
-#endif
-
 	if (!op->replace)
 		journal_ref = bch_journal(op->c, &op->insert_keys,
 					  op->flush_journal ? cl : NULL);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 20ed838e9413..77e9869345e7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u",
 		 sb->version, sb->flags, sb->seq, sb->keys);
 
-	err = "Not a bcache superblock";
+	err = "Not a bcache superblock (bad offset)";
 	if (sb->offset != SB_SECTOR)
 		goto err;
 
+	err = "Not a bcache superblock (bad magic)";
 	if (memcmp(sb->magic, bcache_magic, 16))
 		goto err;
 
@@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op,
 	closure_sync(cl);
 }
 
-void bch_prio_write(struct cache *ca)
+int bch_prio_write(struct cache *ca, bool wait)
 {
 	int i;
 	struct bucket *b;
 	struct closure cl;
 
+	pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu",
+		 fifo_used(&ca->free[RESERVE_PRIO]),
+		 fifo_used(&ca->free[RESERVE_NONE]),
+		 fifo_used(&ca->free_inc));
+
+	/*
+	 * Pre-check if there are enough free buckets. In the non-blocking
+	 * scenario it's better to fail early rather than starting to allocate
+	 * buckets and do a cleanup later in case of failure.
+	 */
+	if (!wait) {
+		size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) +
+			       fifo_used(&ca->free[RESERVE_NONE]);
+		if (prio_buckets(ca) > avail)
+			return -ENOMEM;
+	}
+
 	closure_init_stack(&cl);
 
 	lockdep_assert_held(&ca->set->bucket_lock);
@@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca)
 	atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
 			&ca->meta_sectors_written);
 
-	//pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
-	//	 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
-
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
 		struct prio_set *p = ca->disk_buckets;
@@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca)
 		p->magic	= pset_magic(&ca->sb);
 		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
-		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true);
+		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait);
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
@@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca)
 
 		ca->prio_last_buckets[i] = ca->prio_buckets[i];
 	}
+	return 0;
 }
 
 static void prio_read(struct cache *ca, uint64_t bucket)
@@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx)
 
 static void bcache_device_free(struct bcache_device *d)
 {
+	struct gendisk *disk = d->disk;
+
 	lockdep_assert_held(&bch_register_lock);
 
-	pr_info("%s stopped", d->disk->disk_name);
+	if (disk)
+		pr_info("%s stopped", disk->disk_name);
+	else
+		pr_err("bcache device (NULL gendisk) stopped");
 
 	if (d->c)
 		bcache_device_detach(d);
-	if (d->disk && d->disk->flags & GENHD_FL_UP)
-		del_gendisk(d->disk);
-	if (d->disk && d->disk->queue)
-		blk_cleanup_queue(d->disk->queue);
-	if (d->disk) {
+
+	if (disk) {
+		if (disk->flags & GENHD_FL_UP)
+			del_gendisk(disk);
+
+		if (disk->queue)
+			blk_cleanup_queue(disk->queue);
+
 		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(d->disk->first_minor));
-		put_disk(d->disk);
+				  first_minor_to_idx(disk->first_minor));
+		put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	sema_init(&c->sb_write_mutex, 1);
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
+	spin_lock_init(&c->btree_cannibalize_lock);
 	init_waitqueue_head(&c->bucket_wait);
 	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
@@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
 	c->error_limit	= DEFAULT_IO_ERROR_LIMIT;
+	c->idle_max_writeback_rate_enabled = 1;
 	WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
 	return c;
@@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c)
 
 		mutex_lock(&c->bucket_lock);
 		for_each_cache(ca, c, i)
-			bch_prio_write(ca);
+			bch_prio_write(ca, true);
 		mutex_unlock(&c->bucket_lock);
 
 		err = "cannot allocate new UUID bucket";
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 627dcea0f5b6..733e2ddf3c78 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks);
 rw_attribute(cache_replacement_policy);
 rw_attribute(btree_shrinker_disabled);
 rw_attribute(copy_gc_enabled);
+rw_attribute(idle_max_writeback_rate);
 rw_attribute(gc_after_writeback);
 rw_attribute(size);
 
@@ -747,6 +748,8 @@ SHOW(__bch_cache_set)
 	sysfs_printf(gc_always_rewrite,		"%i", c->gc_always_rewrite);
 	sysfs_printf(btree_shrinker_disabled,	"%i", c->shrinker_disabled);
 	sysfs_printf(copy_gc_enabled,		"%i", c->copy_gc_enabled);
+	sysfs_printf(idle_max_writeback_rate,	"%i",
+		     c->idle_max_writeback_rate_enabled);
 	sysfs_printf(gc_after_writeback,	"%i", c->gc_after_writeback);
 	sysfs_printf(io_disable,		"%i",
 		     test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -864,6 +867,9 @@ STORE(__bch_cache_set)
 	sysfs_strtoul_bool(gc_always_rewrite,	c->gc_always_rewrite);
 	sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled);
 	sysfs_strtoul_bool(copy_gc_enabled,	c->copy_gc_enabled);
+	sysfs_strtoul_bool(idle_max_writeback_rate,
+			   c->idle_max_writeback_rate_enabled);
+
 	/*
 	 * write gc_after_writeback here may overwrite an already set
 	 * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
@@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = {
 	&sysfs_gc_always_rewrite,
 	&sysfs_btree_shrinker_disabled,
 	&sysfs_copy_gc_enabled,
+	&sysfs_idle_max_writeback_rate,
 	&sysfs_gc_after_writeback,
 	&sysfs_io_disable,
 	&sysfs_cutoff_writeback,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index d60268fe49e1..4a40f9eadeaf 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc)
 static bool set_at_max_writeback_rate(struct cache_set *c,
 				       struct cached_dev *dc)
 {
+	/* Don't sst max writeback rate if it is disabled */
+	if (!c->idle_max_writeback_rate_enabled)
+		return false;
+
 	/* Don't set max writeback rate if gc is running */
 	if (!c->gc_mark_valid)
 		return false;
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index b5389890bbc3..1f8f98efd97a 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -150,11 +150,10 @@ static int bio_detain(struct dm_bio_prison *prison,
 		      struct dm_bio_prison_cell **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -198,11 +197,9 @@ void dm_cell_release(struct dm_bio_prison *prison,
 		     struct dm_bio_prison_cell *cell,
 		     struct bio_list *bios)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	__cell_release(prison, cell, bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_release);
 
@@ -250,12 +247,10 @@ void dm_cell_visit_release(struct dm_bio_prison *prison,
 			   void *context,
 			   struct dm_bio_prison_cell *cell)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	visit_fn(context, cell);
 	rb_erase(&cell->node, &prison->cells);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_visit_release);
 
@@ -275,11 +270,10 @@ int dm_cell_promote_or_release(struct dm_bio_prison *prison,
 			       struct dm_bio_prison_cell *cell)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __promote_or_release(prison, cell);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -379,10 +373,9 @@ EXPORT_SYMBOL_GPL(dm_deferred_entry_dec);
 int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work)
 {
 	int r = 1;
-	unsigned long flags;
 	unsigned next_entry;
 
-	spin_lock_irqsave(&ds->lock, flags);
+	spin_lock_irq(&ds->lock);
 	if ((ds->sweeper == ds->current_entry) &&
 	    !ds->entries[ds->current_entry].count)
 		r = 0;
@@ -392,7 +385,7 @@ int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work)
 		if (!ds->entries[next_entry].count)
 			ds->current_entry = next_entry;
 	}
-	spin_unlock_irqrestore(&ds->lock, flags);
+	spin_unlock_irq(&ds->lock);
 
 	return r;
 }
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index b092cdc8e1ae..8ee019eda32d 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -177,11 +177,10 @@ bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison,
 		    struct dm_bio_prison_cell_v2 **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __get(prison, key, lock_level, inmate, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -261,11 +260,10 @@ int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison,
 		    struct dm_bio_prison_cell_v2 **cell_result)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __lock(prison, key, lock_level, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -285,11 +283,9 @@ void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison,
 			struct dm_bio_prison_cell_v2 *cell,
 			struct work_struct *continuation)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	__quiesce(prison, cell, continuation);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 }
 EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2);
 
@@ -309,11 +305,10 @@ int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison,
 			    unsigned new_lock_level)
 {
 	int r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __promote(prison, cell, new_lock_level);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
@@ -342,11 +337,10 @@ bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison,
 		       struct bio_list *bios)
 {
 	bool r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irq(&prison->lock);
 	r = __unlock(prison, cell, bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irq(&prison->lock);
 
 	return r;
 }
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index d249cf8ac277..2d32821b3a5b 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -74,22 +74,19 @@ static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs)
 static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs)
 {
 	bool r;
-	unsigned long flags;
 
-	spin_lock_irqsave(&iot->lock, flags);
+	spin_lock_irq(&iot->lock);
 	r = __iot_idle_for(iot, jifs);
-	spin_unlock_irqrestore(&iot->lock, flags);
+	spin_unlock_irq(&iot->lock);
 
 	return r;
 }
 
 static void iot_io_begin(struct io_tracker *iot, sector_t len)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&iot->lock, flags);
+	spin_lock_irq(&iot->lock);
 	iot->in_flight += len;
-	spin_unlock_irqrestore(&iot->lock, flags);
+	spin_unlock_irq(&iot->lock);
 }
 
 static void __iot_io_end(struct io_tracker *iot, sector_t len)
@@ -172,7 +169,6 @@ static void __commit(struct work_struct *_ws)
 {
 	struct batcher *b = container_of(_ws, struct batcher, commit_work);
 	blk_status_t r;
-	unsigned long flags;
 	struct list_head work_items;
 	struct work_struct *ws, *tmp;
 	struct continuation *k;
@@ -186,12 +182,12 @@ static void __commit(struct work_struct *_ws)
 	 * We have to grab these before the commit_op to avoid a race
 	 * condition.
 	 */
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	list_splice_init(&b->work_items, &work_items);
 	bio_list_merge(&bios, &b->bios);
 	bio_list_init(&b->bios);
 	b->commit_scheduled = false;
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	r = b->commit_op(b->commit_context);
 
@@ -238,13 +234,12 @@ static void async_commit(struct batcher *b)
 
 static void continue_after_commit(struct batcher *b, struct continuation *k)
 {
-	unsigned long flags;
 	bool commit_scheduled;
 
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	commit_scheduled = b->commit_scheduled;
 	list_add_tail(&k->ws.entry, &b->work_items);
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	if (commit_scheduled)
 		async_commit(b);
@@ -255,13 +250,12 @@ static void continue_after_commit(struct batcher *b, struct continuation *k)
  */
 static void issue_after_commit(struct batcher *b, struct bio *bio)
 {
-       unsigned long flags;
        bool commit_scheduled;
 
-       spin_lock_irqsave(&b->lock, flags);
+       spin_lock_irq(&b->lock);
        commit_scheduled = b->commit_scheduled;
        bio_list_add(&b->bios, bio);
-       spin_unlock_irqrestore(&b->lock, flags);
+       spin_unlock_irq(&b->lock);
 
        if (commit_scheduled)
 	       async_commit(b);
@@ -273,12 +267,11 @@ static void issue_after_commit(struct batcher *b, struct bio *bio)
 static void schedule_commit(struct batcher *b)
 {
 	bool immediate;
-	unsigned long flags;
 
-	spin_lock_irqsave(&b->lock, flags);
+	spin_lock_irq(&b->lock);
 	immediate = !list_empty(&b->work_items) || !bio_list_empty(&b->bios);
 	b->commit_scheduled = true;
-	spin_unlock_irqrestore(&b->lock, flags);
+	spin_unlock_irq(&b->lock);
 
 	if (immediate)
 		async_commit(b);
@@ -542,7 +535,7 @@ static void wake_migration_worker(struct cache *cache)
 
 static struct dm_bio_prison_cell_v2 *alloc_prison_cell(struct cache *cache)
 {
-	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOWAIT);
+	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOIO);
 }
 
 static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell_v2 *cell)
@@ -554,9 +547,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache)
 {
 	struct dm_cache_migration *mg;
 
-	mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
-	if (!mg)
-		return NULL;
+	mg = mempool_alloc(&cache->migration_pool, GFP_NOIO);
 
 	memset(mg, 0, sizeof(*mg));
 
@@ -632,23 +623,19 @@ static struct per_bio_data *init_per_bio_data(struct bio *bio)
 
 static void defer_bio(struct cache *cache, struct bio *bio)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_add(&cache->deferred_bios, bio);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
 }
 
 static void defer_bios(struct cache *cache, struct bio_list *bios)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_merge(&cache->deferred_bios, bios);
 	bio_list_init(bios);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	wake_deferred_bio_worker(cache);
 }
@@ -664,10 +651,6 @@ static bool bio_detain_shared(struct cache *cache, dm_oblock_t oblock, struct bi
 	struct dm_bio_prison_cell_v2 *cell_prealloc, *cell;
 
 	cell_prealloc = alloc_prison_cell(cache); /* FIXME: allow wait if calling from worker */
-	if (!cell_prealloc) {
-		defer_bio(cache, bio);
-		return false;
-	}
 
 	build_key(oblock, end, &key);
 	r = dm_cell_get_v2(cache->prison, &key, lock_level(bio), bio, cell_prealloc, &cell);
@@ -762,33 +745,27 @@ static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock)
 
 static void set_discard(struct cache *cache, dm_dblock_t b)
 {
-	unsigned long flags;
-
 	BUG_ON(from_dblock(b) >= from_dblock(cache->discard_nr_blocks));
 	atomic_inc(&cache->stats.discard_count);
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	set_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static void clear_discard(struct cache *cache, dm_dblock_t b)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	clear_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static bool is_discarded(struct cache *cache, dm_dblock_t b)
 {
 	int r;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	r = test_bit(from_dblock(b), cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	return r;
 }
@@ -796,12 +773,10 @@ static bool is_discarded(struct cache *cache, dm_dblock_t b)
 static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b)
 {
 	int r;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	r = test_bit(from_dblock(oblock_to_dblock(cache, b)),
 		     cache->discard_bitset);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	return r;
 }
@@ -833,17 +808,16 @@ static void remap_to_cache(struct cache *cache, struct bio *bio,
 
 static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 {
-	unsigned long flags;
 	struct per_bio_data *pb;
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) &&
 	    bio_op(bio) != REQ_OP_DISCARD) {
 		pb = get_per_bio_data(bio);
 		pb->tick = true;
 		cache->need_tick_bio = false;
 	}
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 }
 
 static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
@@ -1493,11 +1467,6 @@ static int mg_lock_writes(struct dm_cache_migration *mg)
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		DMERR_LIMIT("%s: alloc_prison_cell failed", cache_device_name(cache));
-		mg_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	/*
 	 * Prevent writes to the block, but allow reads to continue.
@@ -1535,11 +1504,6 @@ static int mg_start(struct cache *cache, struct policy_work *op, struct bio *bio
 	}
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		policy_complete_background_work(cache->policy, op, false);
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->op = op;
 	mg->overwrite_bio = bio;
@@ -1628,10 +1592,6 @@ static int invalidate_lock(struct dm_cache_migration *mg)
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		invalidate_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	build_key(mg->invalidate_oblock, oblock_succ(mg->invalidate_oblock), &key);
 	r = dm_cell_lock_v2(cache->prison, &key,
@@ -1669,10 +1629,6 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock,
 		return -EPERM;
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->overwrite_bio = bio;
 	mg->invalidate_cblock = cblock;
@@ -1913,17 +1869,16 @@ static void process_deferred_bios(struct work_struct *ws)
 {
 	struct cache *cache = container_of(ws, struct cache, deferred_bio_worker);
 
-	unsigned long flags;
 	bool commit_needed = false;
 	struct bio_list bios;
 	struct bio *bio;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&cache->lock, flags);
+	spin_lock_irq(&cache->lock);
 	bio_list_merge(&bios, &cache->deferred_bios);
 	bio_list_init(&cache->deferred_bios);
-	spin_unlock_irqrestore(&cache->lock, flags);
+	spin_unlock_irq(&cache->lock);
 
 	while ((bio = bio_list_pop(&bios))) {
 		if (bio->bi_opf & REQ_PREFLUSH)
diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c
index 6bc8c1d1c351..08c552e5e41b 100644
--- a/drivers/md/dm-clone-metadata.c
+++ b/drivers/md/dm-clone-metadata.c
@@ -712,7 +712,7 @@ static int __metadata_commit(struct dm_clone_metadata *cmd)
 static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 {
 	int r;
-	unsigned long word, flags;
+	unsigned long word;
 
 	word = 0;
 	do {
@@ -736,9 +736,9 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 		return r;
 
 	/* Update the changed flag */
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	dmap->changed = 0;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	return 0;
 }
@@ -746,7 +746,6 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap)
 int dm_clone_metadata_commit(struct dm_clone_metadata *cmd)
 {
 	int r = -EPERM;
-	unsigned long flags;
 	struct dirty_map *dmap, *next_dmap;
 
 	down_write(&cmd->lock);
@@ -770,9 +769,9 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd)
 	}
 
 	/* Swap dirty bitmaps */
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->current_dmap = next_dmap;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	/*
 	 * No one is accessing the old dirty bitmap anymore, so we can flush
@@ -817,9 +816,9 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 {
 	int r = 0;
 	struct dirty_map *dmap;
-	unsigned long word, region_nr, flags;
+	unsigned long word, region_nr;
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 
 	if (cmd->read_only) {
 		r = -EPERM;
@@ -836,7 +835,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 		}
 	}
 out:
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	return r;
 }
@@ -903,13 +902,11 @@ out:
 
 void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd)
 {
-	unsigned long flags;
-
 	down_write(&cmd->lock);
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->read_only = 1;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	if (!cmd->fail_io)
 		dm_bm_set_read_only(cmd->bm);
@@ -919,13 +916,11 @@ void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd)
 
 void dm_clone_metadata_set_read_write(struct dm_clone_metadata *cmd)
 {
-	unsigned long flags;
-
 	down_write(&cmd->lock);
 
-	spin_lock_irqsave(&cmd->bitmap_lock, flags);
+	spin_lock_irq(&cmd->bitmap_lock);
 	cmd->read_only = 0;
-	spin_unlock_irqrestore(&cmd->bitmap_lock, flags);
+	spin_unlock_irq(&cmd->bitmap_lock);
 
 	if (!cmd->fail_io)
 		dm_bm_set_read_write(cmd->bm);
diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h
index 434bff08508b..3fe50a781c11 100644
--- a/drivers/md/dm-clone-metadata.h
+++ b/drivers/md/dm-clone-metadata.h
@@ -44,7 +44,9 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re
  * @start: Starting region number
  * @nr_regions: Number of regions in the range
  *
- * This function doesn't block, so it's safe to call it from interrupt context.
+ * This function doesn't block, but since it uses spin_lock_irq()/spin_unlock_irq()
+ * it's NOT safe to call it from any context where interrupts are disabled, e.g.,
+ * from interrupt context.
  */
 int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
 			    unsigned long nr_regions);
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index cd6f9e9fc98e..b3d89072d21c 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -332,8 +332,6 @@ static void submit_bios(struct bio_list *bios)
  */
 static void issue_bio(struct clone *clone, struct bio *bio)
 {
-	unsigned long flags;
-
 	if (!bio_triggers_commit(clone, bio)) {
 		generic_make_request(bio);
 		return;
@@ -352,9 +350,9 @@ static void issue_bio(struct clone *clone, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a single
 	 * commit for them in process_deferred_flush_bios().
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_add(&clone->deferred_flush_bios, bio);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	wake_worker(clone);
 }
@@ -469,7 +467,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ
 
 static void process_discard_bio(struct clone *clone, struct bio *bio)
 {
-	unsigned long rs, re, flags;
+	unsigned long rs, re;
 
 	bio_region_range(clone, bio, &rs, &re);
 	BUG_ON(re > clone->nr_regions);
@@ -501,9 +499,9 @@ static void process_discard_bio(struct clone *clone, struct bio *bio)
 	/*
 	 * Defer discard processing.
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_add(&clone->deferred_discard_bios, bio);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	wake_worker(clone);
 }
@@ -554,6 +552,12 @@ struct hash_table_bucket {
 #define bucket_unlock_irqrestore(bucket, flags) \
 	spin_unlock_irqrestore(&(bucket)->lock, flags)
 
+#define bucket_lock_irq(bucket) \
+	spin_lock_irq(&(bucket)->lock)
+
+#define bucket_unlock_irq(bucket) \
+	spin_unlock_irq(&(bucket)->lock)
+
 static int hash_table_init(struct clone *clone)
 {
 	unsigned int i, sz;
@@ -591,8 +595,8 @@ static struct hash_table_bucket *get_hash_table_bucket(struct clone *clone,
  *
  * NOTE: Must be called with the bucket lock held
  */
-struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket,
-					      unsigned long region_nr)
+static struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket,
+						     unsigned long region_nr)
 {
 	struct dm_clone_region_hydration *hd;
 
@@ -851,7 +855,6 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio
  */
 static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 {
-	unsigned long flags;
 	unsigned long region_nr;
 	struct hash_table_bucket *bucket;
 	struct dm_clone_region_hydration *hd, *hd2;
@@ -859,19 +862,19 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	region_nr = bio_to_region(clone, bio);
 	bucket = get_hash_table_bucket(clone, region_nr);
 
-	bucket_lock_irqsave(bucket, flags);
+	bucket_lock_irq(bucket);
 
 	hd = __hash_find(bucket, region_nr);
 	if (hd) {
 		/* Someone else is hydrating the region */
 		bio_list_add(&hd->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		return;
 	}
 
 	if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) {
 		/* The region has been hydrated */
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		issue_bio(clone, bio);
 		return;
 	}
@@ -880,16 +883,16 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 * We must allocate a hydration descriptor and start the hydration of
 	 * the corresponding region.
 	 */
-	bucket_unlock_irqrestore(bucket, flags);
+	bucket_unlock_irq(bucket);
 
 	hd = alloc_hydration(clone);
 	hydration_init(hd, region_nr);
 
-	bucket_lock_irqsave(bucket, flags);
+	bucket_lock_irq(bucket);
 
 	/* Check if the region has been hydrated in the meantime. */
 	if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) {
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		issue_bio(clone, bio);
 		return;
@@ -899,7 +902,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	if (hd2 != hd) {
 		/* Someone else started the region's hydration. */
 		bio_list_add(&hd2->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		return;
 	}
@@ -911,7 +914,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 */
 	if (unlikely(get_clone_mode(clone) >= CM_READ_ONLY)) {
 		hlist_del(&hd->h);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		free_hydration(hd);
 		bio_io_error(bio);
 		return;
@@ -925,11 +928,11 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio)
 	 * to the destination device.
 	 */
 	if (is_overwrite_bio(clone, bio)) {
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		hydration_overwrite(hd, bio);
 	} else {
 		bio_list_add(&hd->deferred_bios, bio);
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 		hydration_copy(hd, 1);
 	}
 }
@@ -996,7 +999,6 @@ static unsigned long __start_next_hydration(struct clone *clone,
 					    unsigned long offset,
 					    struct batch_info *batch)
 {
-	unsigned long flags;
 	struct hash_table_bucket *bucket;
 	struct dm_clone_region_hydration *hd;
 	unsigned long nr_regions = clone->nr_regions;
@@ -1010,13 +1012,13 @@ static unsigned long __start_next_hydration(struct clone *clone,
 			break;
 
 		bucket = get_hash_table_bucket(clone, offset);
-		bucket_lock_irqsave(bucket, flags);
+		bucket_lock_irq(bucket);
 
 		if (!dm_clone_is_region_hydrated(clone->cmd, offset) &&
 		    !__hash_find(bucket, offset)) {
 			hydration_init(hd, offset);
 			__insert_region_hydration(bucket, hd);
-			bucket_unlock_irqrestore(bucket, flags);
+			bucket_unlock_irq(bucket);
 
 			/* Batch hydration */
 			__batch_hydration(batch, hd);
@@ -1024,7 +1026,7 @@ static unsigned long __start_next_hydration(struct clone *clone,
 			return (offset + 1);
 		}
 
-		bucket_unlock_irqrestore(bucket, flags);
+		bucket_unlock_irq(bucket);
 
 	} while (++offset < nr_regions);
 
@@ -1140,13 +1142,13 @@ static void process_deferred_discards(struct clone *clone)
 	int r = -EPERM;
 	struct bio *bio;
 	struct blk_plug plug;
-	unsigned long rs, re, flags;
+	unsigned long rs, re;
 	struct bio_list discards = BIO_EMPTY_LIST;
 
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&discards, &clone->deferred_discard_bios);
 	bio_list_init(&clone->deferred_discard_bios);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&discards))
 		return;
@@ -1176,13 +1178,12 @@ out:
 
 static void process_deferred_bios(struct clone *clone)
 {
-	unsigned long flags;
 	struct bio_list bios = BIO_EMPTY_LIST;
 
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&bios, &clone->deferred_bios);
 	bio_list_init(&clone->deferred_bios);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios))
 		return;
@@ -1193,7 +1194,6 @@ static void process_deferred_bios(struct clone *clone)
 static void process_deferred_flush_bios(struct clone *clone)
 {
 	struct bio *bio;
-	unsigned long flags;
 	struct bio_list bios = BIO_EMPTY_LIST;
 	struct bio_list bio_completions = BIO_EMPTY_LIST;
 
@@ -1201,13 +1201,13 @@ static void process_deferred_flush_bios(struct clone *clone)
 	 * If there are any deferred flush bios, we must commit the metadata
 	 * before issuing them or signaling their completion.
 	 */
-	spin_lock_irqsave(&clone->lock, flags);
+	spin_lock_irq(&clone->lock);
 	bio_list_merge(&bios, &clone->deferred_flush_bios);
 	bio_list_init(&clone->deferred_flush_bios);
 
 	bio_list_merge(&bio_completions, &clone->deferred_flush_completions);
 	bio_list_init(&clone->deferred_flush_completions);
-	spin_unlock_irqrestore(&clone->lock, flags);
+	spin_unlock_irq(&clone->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&
 	    !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone)))
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index f87f6495652f..eb9782fc93fe 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -2700,21 +2700,18 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ret = -ENOMEM;
-	cc->io_queue = alloc_workqueue("kcryptd_io/%s",
-				       WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
-				       1, devname);
+	cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname);
 	if (!cc->io_queue) {
 		ti->error = "Couldn't create kcryptd io queue";
 		goto bad;
 	}
 
 	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
+		cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
 						  1, devname);
 	else
 		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
+						  WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
 						  num_online_cpus(), devname);
 	if (!cc->crypt_queue) {
 		ti->error = "Couldn't create kcryptd queue";
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index 8288887b7f94..eb37584427a4 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -17,6 +17,7 @@
 struct badblock {
 	struct rb_node node;
 	sector_t bb;
+	unsigned char wr_fail_cnt;
 };
 
 struct dust_device {
@@ -101,7 +102,8 @@ static int dust_remove_block(struct dust_device *dd, unsigned long long block)
 	return 0;
 }
 
-static int dust_add_block(struct dust_device *dd, unsigned long long block)
+static int dust_add_block(struct dust_device *dd, unsigned long long block,
+			  unsigned char wr_fail_cnt)
 {
 	struct badblock *bblock;
 	unsigned long flags;
@@ -115,6 +117,7 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block)
 
 	spin_lock_irqsave(&dd->dust_lock, flags);
 	bblock->bb = block;
+	bblock->wr_fail_cnt = wr_fail_cnt;
 	if (!dust_rb_insert(&dd->badblocklist, bblock)) {
 		if (!dd->quiet_mode) {
 			DMERR("%s: block %llu already in badblocklist",
@@ -126,8 +129,10 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block)
 	}
 
 	dd->badblock_count++;
-	if (!dd->quiet_mode)
-		DMINFO("%s: badblock added at block %llu", __func__, block);
+	if (!dd->quiet_mode) {
+		DMINFO("%s: badblock added at block %llu with write fail count %hhu",
+		       __func__, block, wr_fail_cnt);
+	}
 	spin_unlock_irqrestore(&dd->dust_lock, flags);
 
 	return 0;
@@ -163,22 +168,27 @@ static int dust_map_read(struct dust_device *dd, sector_t thisblock,
 			 bool fail_read_on_bb)
 {
 	unsigned long flags;
-	int ret = DM_MAPIO_REMAPPED;
+	int r = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		ret = __dust_map_read(dd, thisblock);
+		r = __dust_map_read(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return ret;
+	return r;
 }
 
-static void __dust_map_write(struct dust_device *dd, sector_t thisblock)
+static int __dust_map_write(struct dust_device *dd, sector_t thisblock)
 {
 	struct badblock *bblk = dust_rb_search(&dd->badblocklist, thisblock);
 
+	if (bblk && bblk->wr_fail_cnt > 0) {
+		bblk->wr_fail_cnt--;
+		return DM_MAPIO_KILL;
+	}
+
 	if (bblk) {
 		rb_erase(&bblk->node, &dd->badblocklist);
 		dd->badblock_count--;
@@ -189,37 +199,40 @@ static void __dust_map_write(struct dust_device *dd, sector_t thisblock)
 			       (unsigned long long)thisblock);
 		}
 	}
+
+	return DM_MAPIO_REMAPPED;
 }
 
 static int dust_map_write(struct dust_device *dd, sector_t thisblock,
 			  bool fail_read_on_bb)
 {
 	unsigned long flags;
+	int ret = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		__dust_map_write(dd, thisblock);
+		ret = __dust_map_write(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return DM_MAPIO_REMAPPED;
+	return ret;
 }
 
 static int dust_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dust_device *dd = ti->private;
-	int ret;
+	int r;
 
 	bio_set_dev(bio, dd->dev->bdev);
 	bio->bi_iter.bi_sector = dd->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	if (bio_data_dir(bio) == READ)
-		ret = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
+		r = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
 	else
-		ret = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
+		r = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb);
 
-	return ret;
+	return r;
 }
 
 static bool __dust_clear_badblocks(struct rb_root *tree,
@@ -375,8 +388,10 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 	struct dust_device *dd = ti->private;
 	sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT;
 	bool invalid_msg = false;
-	int result = -EINVAL;
+	int r = -EINVAL;
 	unsigned long long tmp, block;
+	unsigned char wr_fail_cnt;
+	unsigned int tmp_ui;
 	unsigned long flags;
 	char dummy;
 
@@ -388,45 +403,69 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 		} else if (!strcasecmp(argv[0], "disable")) {
 			DMINFO("disabling read failures on bad sectors");
 			dd->fail_read_on_bb = false;
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "enable")) {
 			DMINFO("enabling read failures on bad sectors");
 			dd->fail_read_on_bb = true;
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "countbadblocks")) {
 			spin_lock_irqsave(&dd->dust_lock, flags);
 			DMINFO("countbadblocks: %llu badblock(s) found",
 			       dd->badblock_count);
 			spin_unlock_irqrestore(&dd->dust_lock, flags);
-			result = 0;
+			r = 0;
 		} else if (!strcasecmp(argv[0], "clearbadblocks")) {
-			result = dust_clear_badblocks(dd);
+			r = dust_clear_badblocks(dd);
 		} else if (!strcasecmp(argv[0], "quiet")) {
 			if (!dd->quiet_mode)
 				dd->quiet_mode = true;
 			else
 				dd->quiet_mode = false;
-			result = 0;
+			r = 0;
 		} else {
 			invalid_msg = true;
 		}
 	} else if (argc == 2) {
 		if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1)
-			return result;
+			return r;
 
 		block = tmp;
 		sector_div(size, dd->sect_per_block);
 		if (block > size) {
 			DMERR("selected block value out of range");
-			return result;
+			return r;
 		}
 
 		if (!strcasecmp(argv[0], "addbadblock"))
-			result = dust_add_block(dd, block);
+			r = dust_add_block(dd, block, 0);
 		else if (!strcasecmp(argv[0], "removebadblock"))
-			result = dust_remove_block(dd, block);
+			r = dust_remove_block(dd, block);
 		else if (!strcasecmp(argv[0], "queryblock"))
-			result = dust_query_block(dd, block);
+			r = dust_query_block(dd, block);
+		else
+			invalid_msg = true;
+
+	} else if (argc == 3) {
+		if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1)
+			return r;
+
+		if (sscanf(argv[2], "%u%c", &tmp_ui, &dummy) != 1)
+			return r;
+
+		block = tmp;
+		if (tmp_ui > 255) {
+			DMERR("selected write fail count out of range");
+			return r;
+		}
+		wr_fail_cnt = tmp_ui;
+		sector_div(size, dd->sect_per_block);
+		if (block > size) {
+			DMERR("selected block value out of range");
+			return r;
+		}
+
+		if (!strcasecmp(argv[0], "addbadblock"))
+			r = dust_add_block(dd, block, wr_fail_cnt);
 		else
 			invalid_msg = true;
 
@@ -436,7 +475,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (invalid_msg)
 		DMERR("unrecognized message '%s' received", argv[0]);
 
-	return result;
+	return r;
 }
 
 static void dust_status(struct dm_target *ti, status_type_t type,
@@ -499,12 +538,12 @@ static struct target_type dust_target = {
 
 static int __init dm_dust_init(void)
 {
-	int result = dm_register_target(&dust_target);
+	int r = dm_register_target(&dust_target);
 
-	if (result < 0)
-		DMERR("dm_register_target failed %d", result);
+	if (r < 0)
+		DMERR("dm_register_target failed %d", r);
 
-	return result;
+	return r;
 }
 
 static void __exit dm_dust_exit(void)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 2900fbde89b3..a2cc9e45cbba 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	struct flakey_c *fc = ti->private;
 
 	bio_set_dev(bio, fc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 	pb->bio_submitted = false;
 
-	/* Do not fail reset zone */
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		goto map_bio;
 
 	/* Are we alive ? */
@@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		return DM_ENDIO_DONE;
 
 	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
@@ -460,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static int flakey_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+static int flakey_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
 {
 	struct flakey_c *fc = ti->private;
-	int ret;
+	sector_t sector = flakey_map_sector(ti, args->next_sector);
 
-	/* Do report and remap it */
-	ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
-				  zones, nr_zones);
-	if (ret != 0)
-		return ret;
-
-	if (*nr_zones)
-		dm_remap_zone_report(ti, fc->start, zones, nr_zones);
-	return 0;
+	args->start = fc->start;
+	return blkdev_report_zones(fc->dev->bdev, sector, nr_zones,
+				   dm_report_zones_cb, args);
 }
 #endif
 
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index dab4446fe7d8..b225b3e445fa 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -53,6 +53,7 @@
 #define SB_VERSION_1			1
 #define SB_VERSION_2			2
 #define SB_VERSION_3			3
+#define SB_VERSION_4			4
 #define SB_SECTORS			8
 #define MAX_SECTORS_PER_BLOCK		8
 
@@ -73,6 +74,7 @@ struct superblock {
 #define SB_FLAG_HAVE_JOURNAL_MAC	0x1
 #define SB_FLAG_RECALCULATING		0x2
 #define SB_FLAG_DIRTY_BITMAP		0x4
+#define SB_FLAG_FIXED_PADDING		0x8
 
 #define	JOURNAL_ENTRY_ROUNDUP		8
 
@@ -250,6 +252,7 @@ struct dm_integrity_c {
 	bool journal_uptodate;
 	bool just_formatted;
 	bool recalculate_flag;
+	bool fix_padding;
 
 	struct alg_spec internal_hash_alg;
 	struct alg_spec journal_crypt_alg;
@@ -463,7 +466,9 @@ static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr)
 
 static void sb_set_version(struct dm_integrity_c *ic)
 {
-	if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
+	if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING))
+		ic->sb->version = SB_VERSION_4;
+	else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP))
 		ic->sb->version = SB_VERSION_3;
 	else if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
 		ic->sb->version = SB_VERSION_2;
@@ -2955,6 +2960,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		arg_count += !!ic->internal_hash_alg.alg_string;
 		arg_count += !!ic->journal_crypt_alg.alg_string;
 		arg_count += !!ic->journal_mac_alg.alg_string;
+		arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0;
 		DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start,
 		       ic->tag_size, ic->mode, arg_count);
 		if (ic->meta_dev)
@@ -2974,6 +2980,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit);
 			DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval));
 		}
+		if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0)
+			DMEMIT(" fix_padding");
 
 #define EMIT_ALG(a, n)							\
 		do {							\
@@ -3042,8 +3050,14 @@ static int calculate_device_limits(struct dm_integrity_c *ic)
 	if (!ic->meta_dev) {
 		sector_t last_sector, last_area, last_offset;
 
-		ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
-					   (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT;
+		/* we have to maintain excessive padding for compatibility with existing volumes */
+		__u64 metadata_run_padding =
+			ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING) ?
+			(__u64)(METADATA_PADDING_SECTORS << SECTOR_SHIFT) :
+			(__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS);
+
+		ic->metadata_run = round_up((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block),
+					    metadata_run_padding) >> SECTOR_SHIFT;
 		if (!(ic->metadata_run & (ic->metadata_run - 1)))
 			ic->log2_metadata_run = __ffs(ic->metadata_run);
 		else
@@ -3086,6 +3100,8 @@ static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sec
 		journal_sections = 1;
 
 	if (!ic->meta_dev) {
+		if (ic->fix_padding)
+			ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_PADDING);
 		ic->sb->journal_sections = cpu_to_le32(journal_sections);
 		if (!interleave_sectors)
 			interleave_sectors = DEFAULT_INTERLEAVE_SECTORS;
@@ -3725,6 +3741,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto bad;
 		} else if (!strcmp(opt_string, "recalculate")) {
 			ic->recalculate_flag = true;
+		} else if (!strcmp(opt_string, "fix_padding")) {
+			ic->fix_padding = true;
 		} else {
 			r = -EINVAL;
 			ti->error = "Invalid argument";
@@ -3867,7 +3885,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			should_write_sb = true;
 	}
 
-	if (!ic->sb->version || ic->sb->version > SB_VERSION_3) {
+	if (!ic->sb->version || ic->sb->version > SB_VERSION_4) {
 		r = -EINVAL;
 		ti->error = "Unknown version";
 		goto bad;
@@ -4182,7 +4200,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 3, 0},
+	.version		= {1, 4, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index ecefe6703736..8d07fdf63a47 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 	struct linear_c *lc = ti->private;
 
 	bio_set_dev(bio, lc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			linear_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static int linear_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+static int linear_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
 {
-	struct linear_c *lc = (struct linear_c *) ti->private;
-	int ret;
-
-	/* Do report and remap it */
-	ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector),
-				  zones, nr_zones);
-	if (ret != 0)
-		return ret;
+	struct linear_c *lc = ti->private;
+	sector_t sector = linear_map_sector(ti, args->next_sector);
 
-	if (*nr_zones)
-		dm_remap_zone_report(ti, lc->start, zones, nr_zones);
-	return 0;
+	args->start = lc->start;
+	return blkdev_report_zones(lc->dev->bdev, sector, nr_zones,
+				   dm_report_zones_cb, args);
 }
 #endif
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index b0aa595e4375..c412eaa975fc 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -209,6 +209,7 @@ struct raid_dev {
 #define RT_FLAG_RS_SUSPENDED		5
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
+#define RT_FLAG_RS_GROW			8
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -241,6 +242,9 @@ struct raid_set {
 	struct raid_type *raid_type;
 	struct dm_target_callbacks callbacks;
 
+	sector_t array_sectors;
+	sector_t dev_sectors;
+
 	/* Optional raid4/5/6 journal device */
 	struct journal_dev {
 		struct dm_dev *dev;
@@ -616,7 +620,6 @@ static int raid10_format_to_md_layout(struct raid_set *rs,
 
 	} else if (algorithm == ALGORITHM_RAID10_FAR) {
 		f = copies;
-		r = !RAID10_OFFSET;
 		if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
 			r |= RAID10_USE_FAR_SETS;
 
@@ -1615,13 +1618,12 @@ static int _check_data_dev_sectors(struct raid_set *rs)
 }
 
 /* Calculate the sectors per device and per array used for @rs */
-static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
+static int rs_set_dev_and_array_sectors(struct raid_set *rs, sector_t sectors, bool use_mddev)
 {
 	int delta_disks;
 	unsigned int data_stripes;
+	sector_t array_sectors = sectors, dev_sectors = sectors;
 	struct mddev *mddev = &rs->md;
-	struct md_rdev *rdev;
-	sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len;
 
 	if (use_mddev) {
 		delta_disks = mddev->delta_disks;
@@ -1656,12 +1658,9 @@ static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
 		/* Striped layouts */
 		array_sectors = (data_stripes + delta_disks) * dev_sectors;
 
-	rdev_for_each(rdev, mddev)
-		if (!test_bit(Journal, &rdev->flags))
-			rdev->sectors = dev_sectors;
-
 	mddev->array_sectors = array_sectors;
 	mddev->dev_sectors = dev_sectors;
+	rs_set_rdev_sectors(rs);
 
 	return _check_data_dev_sectors(rs);
 bad:
@@ -1670,7 +1669,7 @@ bad:
 }
 
 /* Setup recovery on @rs */
-static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
 {
 	/* raid0 does not recover */
 	if (rs_is_raid0(rs))
@@ -1691,22 +1690,6 @@ static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
 				     ? MaxSector : dev_sectors;
 }
 
-/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */
-static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
-{
-	if (!dev_sectors)
-		/* New raid set or 'sync' flag provided */
-		__rs_setup_recovery(rs, 0);
-	else if (dev_sectors == MaxSector)
-		/* Prevent recovery */
-		__rs_setup_recovery(rs, MaxSector);
-	else if (__rdev_sectors(rs) < dev_sectors)
-		/* Grown raid set */
-		__rs_setup_recovery(rs, __rdev_sectors(rs));
-	else
-		__rs_setup_recovery(rs, MaxSector);
-}
-
 static void do_table_event(struct work_struct *ws)
 {
 	struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
@@ -2474,7 +2457,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 		return -EINVAL;
 	}
 
-	/* Enable bitmap creation for RAID levels != 0 */
+	/* Enable bitmap creation on @rs unless no metadevs or raid0 or journaled raid4/5/6 set. */
 	mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096);
 	mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
 
@@ -2911,7 +2894,7 @@ static int rs_setup_reshape(struct raid_set *rs)
 
 	/* Remove disk(s) */
 	} else if (rs->delta_disks < 0) {
-		r = rs_set_dev_and_array_sectors(rs, true);
+		r = rs_set_dev_and_array_sectors(rs, rs->ti->len, true);
 		mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */
 
 	/* Change layout and/or chunk size */
@@ -3008,7 +2991,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	bool resize = false;
 	struct raid_type *rt;
 	unsigned int num_raid_params, num_raid_devs;
-	sector_t calculated_dev_sectors, rdev_sectors, reshape_sectors;
+	sector_t sb_array_sectors, rdev_sectors, reshape_sectors;
 	struct raid_set *rs = NULL;
 	const char *arg;
 	struct rs_layout rs_layout;
@@ -3067,11 +3050,13 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	 *
 	 * Any existing superblock will overwrite the array and device sizes
 	 */
-	r = rs_set_dev_and_array_sectors(rs, false);
+	r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false);
 	if (r)
 		goto bad;
 
-	calculated_dev_sectors = rs->md.dev_sectors;
+	/* Memorize just calculated, potentially larger sizes to grow the raid set in preresume */
+	rs->array_sectors = rs->md.array_sectors;
+	rs->dev_sectors = rs->md.dev_sectors;
 
 	/*
 	 * Backup any new raid set level, layout, ...
@@ -3084,6 +3069,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
+	/* All in-core metadata now as of current superblocks after calling analyse_superblocks() */
+	sb_array_sectors = rs->md.array_sectors;
 	rdev_sectors = __rdev_sectors(rs);
 	if (!rdev_sectors) {
 		ti->error = "Invalid rdev size";
@@ -3093,8 +3080,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 
 	reshape_sectors = _get_reshape_sectors(rs);
-	if (calculated_dev_sectors != rdev_sectors)
-		resize = calculated_dev_sectors != (reshape_sectors ? rdev_sectors - reshape_sectors : rdev_sectors);
+	if (rs->dev_sectors != rdev_sectors) {
+		resize = (rs->dev_sectors != rdev_sectors - reshape_sectors);
+		if (rs->dev_sectors > rdev_sectors - reshape_sectors)
+			set_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
+	}
 
 	INIT_WORK(&rs->md.event_work, do_table_event);
 	ti->private = rs;
@@ -3121,13 +3111,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
 		rs_set_new(rs);
 	} else if (rs_is_recovering(rs)) {
-		/* Rebuild particular devices */
-		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
-			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
-			rs_setup_recovery(rs, MaxSector);
-		}
 		/* A recovering raid set may be resized */
-		; /* skip setup rs */
+		goto size_check;
 	} else if (rs_is_reshaping(rs)) {
 		/* Have to reject size change request during reshape */
 		if (resize) {
@@ -3171,6 +3156,9 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		rs_setup_recovery(rs, MaxSector);
 		rs_set_new(rs);
 	} else if (rs_reshape_requested(rs)) {
+		/* Only request grow on raid set size extensions, not on reshapes. */
+		clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
+
 		/*
 		 * No need to check for 'ongoing' takeover here, because takeover
 		 * is an instant operation as oposed to an ongoing reshape.
@@ -3201,13 +3189,31 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		}
 		rs_set_cur(rs);
 	} else {
+size_check:
 		/* May not set recovery when a device rebuild is requested */
 		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
-			rs_setup_recovery(rs, MaxSector);
+			clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags);
 			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
-		} else
-			rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ?
-					      0 : (resize ? calculated_dev_sectors : MaxSector));
+			rs_setup_recovery(rs, MaxSector);
+		} else if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) {
+			/*
+			 * Set raid set to current size, i.e. size as of
+			 * superblocks to grow to larger size in preresume.
+			 */
+			r = rs_set_dev_and_array_sectors(rs, sb_array_sectors, false);
+			if (r)
+				goto bad;
+
+			rs_setup_recovery(rs, rs->md.recovery_cp < rs->md.dev_sectors ? rs->md.recovery_cp : rs->md.dev_sectors);
+		} else {
+			/* This is no size change or it is shrinking, update size and record in superblocks */
+			r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false);
+			if (r)
+				goto bad;
+
+			if (sb_array_sectors > rs->array_sectors)
+				set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		}
 		rs_set_cur(rs);
 	}
 
@@ -3406,10 +3412,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev)
 
 /* Helper to return resync/reshape progress for @rs and runtime flags for raid set in sync / resynching */
 static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
-				sector_t resync_max_sectors)
+				enum sync_state state, sector_t resync_max_sectors)
 {
 	sector_t r;
-	enum sync_state state;
 	struct mddev *mddev = &rs->md;
 
 	clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
@@ -3420,8 +3425,6 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 		set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
 	} else {
-		state = decipher_sync_action(mddev, recovery);
-
 		if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery))
 			r = mddev->recovery_cp;
 		else
@@ -3439,18 +3442,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			/*
 			 * In case we are recovering, the array is not in sync
 			 * and health chars should show the recovering legs.
+			 *
+			 * Already retrieved recovery offset from curr_resync_completed above.
 			 */
 			;
-		else if (state == st_resync)
-			/*
-			 * If "resync" is occurring, the raid set
-			 * is or may be out of sync hence the health
-			 * characters shall be 'a'.
-			 */
-			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
-		else if (state == st_reshape)
+
+		else if (state == st_resync || state == st_reshape)
 			/*
-			 * If "reshape" is occurring, the raid set
+			 * If "resync/reshape" is occurring, the raid set
 			 * is or may be out of sync hence the health
 			 * characters shall be 'a'.
 			 */
@@ -3464,22 +3463,22 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			 */
 			set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
-		else {
-			struct md_rdev *rdev;
-
+		else if (test_bit(MD_RECOVERY_NEEDED, &recovery))
 			/*
 			 * We are idle and recovery is needed, prevent 'A' chars race
 			 * caused by components still set to in-sync by constructor.
 			 */
-			if (test_bit(MD_RECOVERY_NEEDED, &recovery))
-				set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
+			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
 
+		else {
 			/*
-			 * The raid set may be doing an initial sync, or it may
-			 * be rebuilding individual components.	 If all the
-			 * devices are In_sync, then it is the raid set that is
-			 * being initialized.
+			 * We are idle and the raid set may be doing an initial
+			 * sync, or it may be rebuilding individual components.
+			 * If all the devices are In_sync, then it is the raid set
+			 * that is being initialized.
 			 */
+			struct md_rdev *rdev;
+
 			set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 			rdev_for_each(rdev, mddev)
 				if (!test_bit(Journal, &rdev->flags) &&
@@ -3512,7 +3511,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	unsigned int rebuild_disks;
 	unsigned int write_mostly_params = 0;
 	sector_t progress, resync_max_sectors, resync_mismatches;
-	const char *sync_action;
+	enum sync_state state;
 	struct raid_type *rt;
 
 	switch (type) {
@@ -3526,14 +3525,14 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 
 		/* Access most recent mddev properties for status output */
 		smp_rmb();
-		recovery = rs->md.recovery;
 		/* Get sensible max sectors even if raid set not yet started */
 		resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ?
 				      mddev->resync_max_sectors : mddev->dev_sectors;
-		progress = rs_get_progress(rs, recovery, resync_max_sectors);
+		recovery = rs->md.recovery;
+		state = decipher_sync_action(mddev, recovery);
+		progress = rs_get_progress(rs, recovery, state, resync_max_sectors);
 		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
-		sync_action = sync_str(decipher_sync_action(&rs->md, recovery));
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */
 		for (i = 0; i < rs->raid_disks; i++)
@@ -3561,7 +3560,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		 *   See Documentation/admin-guide/device-mapper/dm-raid.rst for
 		 *   information on each of these states.
 		 */
-		DMEMIT(" %s", sync_action);
+		DMEMIT(" %s", sync_str(state));
 
 		/*
 		 * v1.5.0+:
@@ -3955,11 +3954,22 @@ static int raid_preresume(struct dm_target *ti)
 	if (r)
 		return r;
 
-	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
-	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
-	    mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
-		r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors,
-				     to_bytes(rs->requested_bitmap_chunk_sectors), 0);
+	/* We are extending the raid set size, adjust mddev/md_rdev sizes and set capacity. */
+	if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) {
+		mddev->array_sectors = rs->array_sectors;
+		mddev->dev_sectors = rs->dev_sectors;
+		rs_set_rdev_sectors(rs);
+		rs_set_capacity(rs);
+	}
+
+	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */
+        if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
+	    (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) ||
+	     (rs->requested_bitmap_chunk_sectors &&
+	       mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) {
+		int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize;
+
+		r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, chunksize, 0);
 		if (r)
 			DMERR("Failed to resize bitmap");
 	}
@@ -3968,8 +3978,10 @@ static int raid_preresume(struct dm_target *ti)
 	/* Be prepared for mddev_resume() in raid_resume() */
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
-		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
+		if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags))
+			mddev->resync_max_sectors = mddev->dev_sectors;
 	}
 
 	/* Check for any reshape request unless new raid set */
@@ -4017,7 +4029,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index f150f5c5492b..4fb1a40e68a0 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -18,7 +18,6 @@
 #include <linux/vmalloc.h>
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
-#include <linux/semaphore.h>
 
 #include "dm.h"
 
@@ -107,8 +106,8 @@ struct dm_snapshot {
 	/* The on disk metadata handler */
 	struct dm_exception_store *store;
 
-	/* Maximum number of in-flight COW jobs. */
-	struct semaphore cow_count;
+	unsigned in_progress;
+	struct wait_queue_head in_progress_wait;
 
 	struct dm_kcopyd_client *kcopyd_client;
 
@@ -162,8 +161,8 @@ struct dm_snapshot {
  */
 #define DEFAULT_COW_THRESHOLD 2048
 
-static int cow_threshold = DEFAULT_COW_THRESHOLD;
-module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644);
+static unsigned cow_threshold = DEFAULT_COW_THRESHOLD;
+module_param_named(snapshot_cow_threshold, cow_threshold, uint, 0644);
 MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write");
 
 DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
@@ -1327,7 +1326,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_hash_tables;
 	}
 
-	sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX);
+	init_waitqueue_head(&s->in_progress_wait);
 
 	s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle);
 	if (IS_ERR(s->kcopyd_client)) {
@@ -1509,9 +1508,56 @@ static void snapshot_dtr(struct dm_target *ti)
 
 	dm_put_device(ti, s->origin);
 
+	WARN_ON(s->in_progress);
+
 	kfree(s);
 }
 
+static void account_start_copy(struct dm_snapshot *s)
+{
+	spin_lock(&s->in_progress_wait.lock);
+	s->in_progress++;
+	spin_unlock(&s->in_progress_wait.lock);
+}
+
+static void account_end_copy(struct dm_snapshot *s)
+{
+	spin_lock(&s->in_progress_wait.lock);
+	BUG_ON(!s->in_progress);
+	s->in_progress--;
+	if (likely(s->in_progress <= cow_threshold) &&
+	    unlikely(waitqueue_active(&s->in_progress_wait)))
+		wake_up_locked(&s->in_progress_wait);
+	spin_unlock(&s->in_progress_wait.lock);
+}
+
+static bool wait_for_in_progress(struct dm_snapshot *s, bool unlock_origins)
+{
+	if (unlikely(s->in_progress > cow_threshold)) {
+		spin_lock(&s->in_progress_wait.lock);
+		if (likely(s->in_progress > cow_threshold)) {
+			/*
+			 * NOTE: this throttle doesn't account for whether
+			 * the caller is servicing an IO that will trigger a COW
+			 * so excess throttling may result for chunks not required
+			 * to be COW'd.  But if cow_threshold was reached, extra
+			 * throttling is unlikely to negatively impact performance.
+			 */
+			DECLARE_WAITQUEUE(wait, current);
+			__add_wait_queue(&s->in_progress_wait, &wait);
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			spin_unlock(&s->in_progress_wait.lock);
+			if (unlock_origins)
+				up_read(&_origins_lock);
+			io_schedule();
+			remove_wait_queue(&s->in_progress_wait, &wait);
+			return false;
+		}
+		spin_unlock(&s->in_progress_wait.lock);
+	}
+	return true;
+}
+
 /*
  * Flush a list of buffers.
  */
@@ -1527,7 +1573,7 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static int do_origin(struct dm_dev *origin, struct bio *bio);
+static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit);
 
 /*
  * Flush a list of buffers.
@@ -1540,7 +1586,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio)
 	while (bio) {
 		n = bio->bi_next;
 		bio->bi_next = NULL;
-		r = do_origin(s->origin, bio);
+		r = do_origin(s->origin, bio, false);
 		if (r == DM_MAPIO_REMAPPED)
 			generic_make_request(bio);
 		bio = n;
@@ -1732,7 +1778,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
 		rb_link_node(&pe->out_of_order_node, parent, p);
 		rb_insert_color(&pe->out_of_order_node, &s->out_of_order_tree);
 	}
-	up(&s->cow_count);
+	account_end_copy(s);
 }
 
 /*
@@ -1756,7 +1802,7 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 	dest.count = src.count;
 
 	/* Hand over to kcopyd */
-	down(&s->cow_count);
+	account_start_copy(s);
 	dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe);
 }
 
@@ -1776,7 +1822,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
 	pe->full_bio = bio;
 	pe->full_bio_end_io = bio->bi_end_io;
 
-	down(&s->cow_count);
+	account_start_copy(s);
 	callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client,
 						   copy_callback, pe);
 
@@ -1866,7 +1912,7 @@ static void zero_callback(int read_err, unsigned long write_err, void *context)
 	struct bio *bio = context;
 	struct dm_snapshot *s = bio->bi_private;
 
-	up(&s->cow_count);
+	account_end_copy(s);
 	bio->bi_status = write_err ? BLK_STS_IOERR : 0;
 	bio_endio(bio);
 }
@@ -1880,7 +1926,7 @@ static void zero_exception(struct dm_snapshot *s, struct dm_exception *e,
 	dest.sector = bio->bi_iter.bi_sector;
 	dest.count = s->store->chunk_size;
 
-	down(&s->cow_count);
+	account_start_copy(s);
 	WARN_ON_ONCE(bio->bi_private);
 	bio->bi_private = s;
 	dm_kcopyd_zero(s->kcopyd_client, 1, &dest, 0, zero_callback, bio);
@@ -1916,6 +1962,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 	if (!s->valid)
 		return DM_MAPIO_KILL;
 
+	if (bio_data_dir(bio) == WRITE) {
+		while (unlikely(!wait_for_in_progress(s, false)))
+			; /* wait_for_in_progress() has slept */
+	}
+
 	down_read(&s->lock);
 	dm_exception_table_lock(&lock);
 
@@ -2112,7 +2163,7 @@ redirect_to_origin:
 
 	if (bio_data_dir(bio) == WRITE) {
 		up_write(&s->lock);
-		return do_origin(s->origin, bio);
+		return do_origin(s->origin, bio, false);
 	}
 
 out_unlock:
@@ -2487,15 +2538,24 @@ next_snapshot:
 /*
  * Called on a write from the origin driver.
  */
-static int do_origin(struct dm_dev *origin, struct bio *bio)
+static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit)
 {
 	struct origin *o;
 	int r = DM_MAPIO_REMAPPED;
 
+again:
 	down_read(&_origins_lock);
 	o = __lookup_origin(origin->bdev);
-	if (o)
+	if (o) {
+		if (limit) {
+			struct dm_snapshot *s;
+			list_for_each_entry(s, &o->snapshots, list)
+				if (unlikely(!wait_for_in_progress(s, true)))
+					goto again;
+		}
+
 		r = __origin_write(&o->snapshots, bio->bi_iter.bi_sector, bio);
+	}
 	up_read(&_origins_lock);
 
 	return r;
@@ -2608,7 +2668,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
 		dm_accept_partial_bio(bio, available_sectors);
 
 	/* Only tell snapshots if this is a write */
-	return do_origin(o->dev, bio);
+	return do_origin(o->dev, bio, true);
 }
 
 /*
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 8547d7594338..63bbcc20f49a 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -55,19 +55,6 @@ static void trigger_event(struct work_struct *work)
 	dm_table_event(sc->ti->table);
 }
 
-static inline struct stripe_c *alloc_context(unsigned int stripes)
-{
-	size_t len;
-
-	if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe),
-			     stripes))
-		return NULL;
-
-	len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes);
-
-	return kmalloc(len, GFP_KERNEL);
-}
-
 /*
  * Parse a single <dev> <sector> pair
  */
@@ -142,7 +129,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -EINVAL;
 	}
 
-	sc = alloc_context(stripes);
+	sc = kmalloc(struct_size(sc, stripe, stripes), GFP_KERNEL);
 	if (!sc) {
 		ti->error = "Memory allocation for striped context "
 		    "failed";
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 52e049554f5c..2ae0c1913766 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -918,21 +918,15 @@ bool dm_table_supports_dax(struct dm_table *t,
 
 static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
 
-struct verify_rq_based_data {
-	unsigned sq_count;
-	unsigned mq_count;
-};
-
-static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev,
-			      sector_t start, sector_t len, void *data)
+static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
+				  sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	struct verify_rq_based_data *v = data;
+	struct block_device *bdev = dev->bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (queue_is_mq(q))
-		v->mq_count++;
-	else
-		v->sq_count++;
+	/* request-based cannot stack on partitions! */
+	if (bdev != bdev->bd_contains)
+		return false;
 
 	return queue_is_mq(q);
 }
@@ -941,7 +935,6 @@ static int dm_table_determine_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
-	struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0};
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
@@ -1045,14 +1038,10 @@ verify_rq_based:
 
 	/* Non-request-stackable devices can't be used for request-based dm */
 	if (!tgt->type->iterate_devices ||
-	    !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) {
+	    !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) {
 		DMERR("table load rejected: including non-request-stackable devices");
 		return -EINVAL;
 	}
-	if (v.sq_count > 0) {
-		DMERR("table load rejected: not all devices are blk-mq request-stackable");
-		return -EINVAL;
-	}
 
 	return 0;
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fcd887703f95..5a2c494cb552 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -609,13 +609,12 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 		blk_status_t error)
 {
 	struct bio_list bios;
-	unsigned long flags;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	__merge_bio_list(&bios, master);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, error);
 }
@@ -623,15 +622,14 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
 static void requeue_deferred_cells(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct list_head cells;
 	struct dm_bio_prison_cell *cell, *tmp;
 
 	INIT_LIST_HEAD(&cells);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_splice_init(&tc->deferred_cells, &cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	list_for_each_entry_safe(cell, tmp, &cells, user_list)
 		cell_requeue(pool, cell);
@@ -640,14 +638,13 @@ static void requeue_deferred_cells(struct thin_c *tc)
 static void requeue_io(struct thin_c *tc)
 {
 	struct bio_list bios;
-	unsigned long flags;
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	__merge_bio_list(&bios, &tc->deferred_bio_list);
 	__merge_bio_list(&bios, &tc->retry_on_resume_list);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	error_bio_list(&bios, BLK_STS_DM_REQUEUE);
 	requeue_deferred_cells(tc);
@@ -756,7 +753,6 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio)
 static void issue(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 
 	if (!bio_triggers_commit(tc, bio)) {
 		generic_make_request(bio);
@@ -777,9 +773,9 @@ static void issue(struct thin_c *tc, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a
 	 * single commit for them in process_deferred_bios().
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_add(&pool->deferred_flush_bios, bio);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio)
@@ -886,12 +882,15 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c
 {
 	struct pool *pool = tc->pool;
 	unsigned long flags;
+	int has_work;
 
 	spin_lock_irqsave(&tc->lock, flags);
 	cell_release_no_holder(pool, cell, &tc->deferred_bio_list);
+	has_work = !bio_list_empty(&tc->deferred_bio_list);
 	spin_unlock_irqrestore(&tc->lock, flags);
 
-	wake_worker(pool);
+	if (has_work)
+		wake_worker(pool);
 }
 
 static void thin_defer_bio(struct thin_c *tc, struct bio *bio);
@@ -960,7 +959,6 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 
 	/*
 	 * If the bio has the REQ_FUA flag set we must commit the metadata
@@ -985,9 +983,9 @@ static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio)
 	 * Batch together any bios that trigger commits and then issue a
 	 * single commit for them in process_deferred_bios().
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_add(&pool->deferred_flush_completions, bio);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void process_prepared_mapping(struct dm_thin_new_mapping *m)
@@ -1226,14 +1224,13 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
 static void process_prepared(struct pool *pool, struct list_head *head,
 			     process_mapping_fn *fn)
 {
-	unsigned long flags;
 	struct list_head maps;
 	struct dm_thin_new_mapping *m, *tmp;
 
 	INIT_LIST_HEAD(&maps);
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	list_splice_init(head, &maps);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	list_for_each_entry_safe(m, tmp, &maps, list)
 		(*fn)(m);
@@ -1510,14 +1507,12 @@ static int commit(struct pool *pool)
 
 static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks)
 {
-	unsigned long flags;
-
 	if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) {
 		DMWARN("%s: reached low water mark for data device: sending event.",
 		       dm_device_name(pool->pool_md));
-		spin_lock_irqsave(&pool->lock, flags);
+		spin_lock_irq(&pool->lock);
 		pool->low_water_triggered = true;
-		spin_unlock_irqrestore(&pool->lock, flags);
+		spin_unlock_irq(&pool->lock);
 		dm_table_event(pool->ti->table);
 	}
 }
@@ -1593,11 +1588,10 @@ static void retry_on_resume(struct bio *bio)
 {
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct thin_c *tc = h->tc;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	bio_list_add(&tc->retry_on_resume_list, bio);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 }
 
 static blk_status_t should_error_unserviceable_bio(struct pool *pool)
@@ -2170,7 +2164,6 @@ static void __sort_thin_deferred_bios(struct thin_c *tc)
 static void process_thin_deferred_bios(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct bio *bio;
 	struct bio_list bios;
 	struct blk_plug plug;
@@ -2184,10 +2177,10 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 
 	if (bio_list_empty(&tc->deferred_bio_list)) {
-		spin_unlock_irqrestore(&tc->lock, flags);
+		spin_unlock_irq(&tc->lock);
 		return;
 	}
 
@@ -2196,7 +2189,7 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 	bio_list_merge(&bios, &tc->deferred_bio_list);
 	bio_list_init(&tc->deferred_bio_list);
 
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(&bios))) {
@@ -2206,10 +2199,10 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 		 * prepared mappings to process.
 		 */
 		if (ensure_next_mapping(pool)) {
-			spin_lock_irqsave(&tc->lock, flags);
+			spin_lock_irq(&tc->lock);
 			bio_list_add(&tc->deferred_bio_list, bio);
 			bio_list_merge(&tc->deferred_bio_list, &bios);
-			spin_unlock_irqrestore(&tc->lock, flags);
+			spin_unlock_irq(&tc->lock);
 			break;
 		}
 
@@ -2264,16 +2257,15 @@ static unsigned sort_cells(struct pool *pool, struct list_head *cells)
 static void process_thin_deferred_cells(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
-	unsigned long flags;
 	struct list_head cells;
 	struct dm_bio_prison_cell *cell;
 	unsigned i, j, count;
 
 	INIT_LIST_HEAD(&cells);
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_splice_init(&tc->deferred_cells, &cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	if (list_empty(&cells))
 		return;
@@ -2294,9 +2286,9 @@ static void process_thin_deferred_cells(struct thin_c *tc)
 				for (j = i; j < count; j++)
 					list_add(&pool->cell_sort_array[j]->user_list, &cells);
 
-				spin_lock_irqsave(&tc->lock, flags);
+				spin_lock_irq(&tc->lock);
 				list_splice(&cells, &tc->deferred_cells);
-				spin_unlock_irqrestore(&tc->lock, flags);
+				spin_unlock_irq(&tc->lock);
 				return;
 			}
 
@@ -2349,7 +2341,6 @@ static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc)
 
 static void process_deferred_bios(struct pool *pool)
 {
-	unsigned long flags;
 	struct bio *bio;
 	struct bio_list bios, bio_completions;
 	struct thin_c *tc;
@@ -2368,13 +2359,13 @@ static void process_deferred_bios(struct pool *pool)
 	bio_list_init(&bios);
 	bio_list_init(&bio_completions);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_list_merge(&bios, &pool->deferred_flush_bios);
 	bio_list_init(&pool->deferred_flush_bios);
 
 	bio_list_merge(&bio_completions, &pool->deferred_flush_completions);
 	bio_list_init(&pool->deferred_flush_completions);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) &&
 	    !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
@@ -2657,12 +2648,11 @@ static void metadata_operation_failed(struct pool *pool, const char *op, int r)
  */
 static void thin_defer_bio(struct thin_c *tc, struct bio *bio)
 {
-	unsigned long flags;
 	struct pool *pool = tc->pool;
 
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	bio_list_add(&tc->deferred_bio_list, bio);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 
 	wake_worker(pool);
 }
@@ -2678,13 +2668,12 @@ static void thin_defer_bio_with_throttle(struct thin_c *tc, struct bio *bio)
 
 static void thin_defer_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 {
-	unsigned long flags;
 	struct pool *pool = tc->pool;
 
 	throttle_lock(&pool->throttle);
-	spin_lock_irqsave(&tc->lock, flags);
+	spin_lock_irq(&tc->lock);
 	list_add_tail(&cell->user_list, &tc->deferred_cells);
-	spin_unlock_irqrestore(&tc->lock, flags);
+	spin_unlock_irq(&tc->lock);
 	throttle_unlock(&pool->throttle);
 
 	wake_worker(pool);
@@ -2810,15 +2799,14 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
 
 static void requeue_bios(struct pool *pool)
 {
-	unsigned long flags;
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list) {
-		spin_lock_irqsave(&tc->lock, flags);
+		spin_lock_irq(&tc->lock);
 		bio_list_merge(&tc->deferred_bio_list, &tc->retry_on_resume_list);
 		bio_list_init(&tc->retry_on_resume_list);
-		spin_unlock_irqrestore(&tc->lock, flags);
+		spin_unlock_irq(&tc->lock);
 	}
 	rcu_read_unlock();
 }
@@ -3412,15 +3400,14 @@ static int pool_map(struct dm_target *ti, struct bio *bio)
 	int r;
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	/*
 	 * As this is a singleton target, ti->begin is always zero.
 	 */
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	bio_set_dev(bio, pt->data_dev->bdev);
 	r = DM_MAPIO_REMAPPED;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	return r;
 }
@@ -3591,7 +3578,6 @@ static void pool_resume(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	/*
 	 * Must requeue active_thins' bios and then resume
@@ -3600,10 +3586,10 @@ static void pool_resume(struct dm_target *ti)
 	requeue_bios(pool);
 	pool_resume_active_thins(pool);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->low_water_triggered = false;
 	pool->suspended = false;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	do_waker(&pool->waker.work);
 }
@@ -3612,11 +3598,10 @@ static void pool_presuspend(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->suspended = true;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 
 	pool_suspend_active_thins(pool);
 }
@@ -3625,13 +3610,12 @@ static void pool_presuspend_undo(struct dm_target *ti)
 {
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
-	unsigned long flags;
 
 	pool_resume_active_thins(pool);
 
-	spin_lock_irqsave(&pool->lock, flags);
+	spin_lock_irq(&pool->lock);
 	pool->suspended = false;
-	spin_unlock_irqrestore(&pool->lock, flags);
+	spin_unlock_irq(&pool->lock);
 }
 
 static void pool_postsuspend(struct dm_target *ti)
@@ -4110,11 +4094,10 @@ static void thin_put(struct thin_c *tc)
 static void thin_dtr(struct dm_target *ti)
 {
 	struct thin_c *tc = ti->private;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tc->pool->lock, flags);
+	spin_lock_irq(&tc->pool->lock);
 	list_del_rcu(&tc->list);
-	spin_unlock_irqrestore(&tc->pool->lock, flags);
+	spin_unlock_irq(&tc->pool->lock);
 	synchronize_rcu();
 
 	thin_put(tc);
@@ -4150,7 +4133,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	struct thin_c *tc;
 	struct dm_dev *pool_dev, *origin_dev;
 	struct mapped_device *pool_md;
-	unsigned long flags;
 
 	mutex_lock(&dm_thin_pool_table.mutex);
 
@@ -4244,9 +4226,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
-	spin_lock_irqsave(&tc->pool->lock, flags);
+	spin_lock_irq(&tc->pool->lock);
 	if (tc->pool->suspended) {
-		spin_unlock_irqrestore(&tc->pool->lock, flags);
+		spin_unlock_irq(&tc->pool->lock);
 		mutex_lock(&dm_thin_pool_table.mutex); /* reacquire for __pool_dec */
 		ti->error = "Unable to activate thin device while pool is suspended";
 		r = -EINVAL;
@@ -4255,7 +4237,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	refcount_set(&tc->refcount, 1);
 	init_completion(&tc->can_destroy);
 	list_add_tail_rcu(&tc->list, &tc->pool->active_thins);
-	spin_unlock_irqrestore(&tc->pool->lock, flags);
+	spin_unlock_irq(&tc->pool->lock);
 	/*
 	 * This synchronize_rcu() call is needed here otherwise we risk a
 	 * wake_worker() call finding no bios to process (because the newly
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index d06b8aa41e26..7d727a72aa13 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1218,7 +1218,8 @@ bio_copy:
 			}
 		} while (bio->bi_iter.bi_size);
 
-		if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks))
+		if (unlikely(bio->bi_opf & REQ_FUA ||
+			     wc->uncommitted_blocks >= wc->autocommit_blocks))
 			writecache_flush(wc);
 		else
 			writecache_schedule_autocommit(wc);
@@ -1561,7 +1562,7 @@ static void writecache_writeback(struct work_struct *work)
 {
 	struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work);
 	struct blk_plug plug;
-	struct wc_entry *f, *g, *e = NULL;
+	struct wc_entry *f, *uninitialized_var(g), *e = NULL;
 	struct rb_node *node, *next_node;
 	struct list_head skipped;
 	struct writeback_list wbl;
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 595a73110e17..22b3cb0050a7 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -554,6 +554,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 		       TASK_UNINTERRUPTIBLE);
 	if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 		dmz_release_mblock(zmd, mblk);
+		dmz_check_bdev(zmd->dev);
 		return ERR_PTR(-EIO);
 	}
 
@@ -625,6 +626,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
+	if (ret)
+		dmz_check_bdev(zmd->dev);
 	return ret;
 }
 
@@ -691,6 +694,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 			       TASK_UNINTERRUPTIBLE);
 		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 			clear_bit(DMZ_META_ERROR, &mblk->state);
+			dmz_check_bdev(zmd->dev);
 			ret = -EIO;
 		}
 		nr_mblks_submitted--;
@@ -768,7 +772,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	/* If there are no dirty metadata blocks, just flush the device cache */
 	if (list_empty(&write_list)) {
 		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL);
-		goto out;
+		goto err;
 	}
 
 	/*
@@ -778,7 +782,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_log_dirty_mblocks(zmd, &write_list);
 	if (ret)
-		goto out;
+		goto err;
 
 	/*
 	 * The log is on disk. It is now safe to update in place
@@ -786,11 +790,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	ret = dmz_write_sb(zmd, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	while (!list_empty(&write_list)) {
 		mblk = list_first_entry(&write_list, struct dmz_mblock, link);
@@ -805,16 +809,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 
 	zmd->sb_gen++;
 out:
-	if (ret && !list_empty(&write_list)) {
-		spin_lock(&zmd->mblk_lock);
-		list_splice(&write_list, &zmd->mblk_dirty_list);
-		spin_unlock(&zmd->mblk_lock);
-	}
-
 	dmz_unlock_flush(zmd);
 	up_write(&zmd->mblk_sem);
 
 	return ret;
+
+err:
+	if (!list_empty(&write_list)) {
+		spin_lock(&zmd->mblk_lock);
+		list_splice(&write_list, &zmd->mblk_dirty_list);
+		spin_unlock(&zmd->mblk_lock);
+	}
+	if (!dmz_check_bdev(zmd->dev))
+		ret = -EIO;
+	goto out;
 }
 
 /*
@@ -1080,9 +1088,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
 /*
  * Initialize a zone descriptor.
  */
-static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
-			 struct blk_zone *blkz)
+static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
 {
+	struct dmz_metadata *zmd = data;
+	struct dm_zone *zone = &zmd->zones[idx];
 	struct dmz_dev *dev = zmd->dev;
 
 	/* Ignore the eventual last runt (smaller) zone */
@@ -1096,26 +1105,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
 	atomic_set(&zone->refcount, 0);
 	zone->chunk = DMZ_MAP_UNMAPPED;
 
-	if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
+	switch (blkz->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
 		set_bit(DMZ_RND, &zone->flags);
 		zmd->nr_rnd_zones++;
-	} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
-		   blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
+		break;
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 		set_bit(DMZ_SEQ, &zone->flags);
-	} else
+		break;
+	default:
 		return -ENXIO;
-
-	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz->cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
+	}
 
 	if (dmz_is_rnd(zone))
 		zone->wp_block = 0;
 	else
 		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
 
-	if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) {
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
+	else {
 		zmd->nr_useable_zones++;
 		if (dmz_is_rnd(zone)) {
 			zmd->nr_rnd_zones++;
@@ -1139,23 +1151,13 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
 }
 
 /*
- * The size of a zone report in number of zones.
- * This results in 4096*64B=256KB report zones commands.
- */
-#define DMZ_REPORT_NR_ZONES	4096
-
-/*
  * Allocate and initialize zone descriptors using the zone
  * information from disk.
  */
 static int dmz_init_zones(struct dmz_metadata *zmd)
 {
 	struct dmz_dev *dev = zmd->dev;
-	struct dm_zone *zone;
-	struct blk_zone *blkz;
-	unsigned int nr_blkz;
-	sector_t sector = 0;
-	int i, ret = 0;
+	int ret;
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
@@ -1169,54 +1171,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 	dmz_dev_info(dev, "Using %zu B for zone information",
 		     sizeof(struct dm_zone) * dev->nr_zones);
 
-	/* Get zone information */
-	nr_blkz = DMZ_REPORT_NR_ZONES;
-	blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!blkz) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	/*
-	 * Get zone information and initialize zone descriptors.
-	 * At the same time, determine where the super block
-	 * should be: first block of the first randomly writable
-	 * zone.
+	 * Get zone information and initialize zone descriptors.  At the same
+	 * time, determine where the super block should be: first block of the
+	 * first randomly writable zone.
 	 */
-	zone = zmd->zones;
-	while (sector < dev->capacity) {
-		/* Get zone information */
-		nr_blkz = DMZ_REPORT_NR_ZONES;
-		ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz);
-		if (ret) {
-			dmz_dev_err(dev, "Report zones failed %d", ret);
-			goto out;
-		}
+	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone,
+				  zmd);
+	if (ret < 0) {
+		dmz_drop_zones(zmd);
+		return ret;
+	}
 
-		if (!nr_blkz)
-			break;
+	return 0;
+}
 
-		/* Process report */
-		for (i = 0; i < nr_blkz; i++) {
-			ret = dmz_init_zone(zmd, zone, &blkz[i]);
-			if (ret)
-				goto out;
-			sector += dev->zone_nr_sectors;
-			zone++;
-		}
-	}
+static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx,
+			      void *data)
+{
+	struct dm_zone *zone = data;
 
-	/* The entire zone configuration of the disk should now be known */
-	if (sector < dev->capacity) {
-		dmz_dev_err(dev, "Failed to get correct zone information");
-		ret = -ENXIO;
-	}
-out:
-	kfree(blkz);
-	if (ret)
-		dmz_drop_zones(zmd);
+	clear_bit(DMZ_OFFLINE, &zone->flags);
+	clear_bit(DMZ_READ_ONLY, &zone->flags);
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
 
-	return ret;
+	if (dmz_is_seq(zone))
+		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
+	else
+		zone->wp_block = 0;
+	return 0;
 }
 
 /*
@@ -1224,9 +1210,7 @@ out:
  */
 static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	unsigned int nr_blkz = 1;
 	unsigned int noio_flag;
-	struct blk_zone blkz;
 	int ret;
 
 	/*
@@ -1236,29 +1220,19 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	 * GFP_NOIO was specified.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
-				  &blkz, &nr_blkz);
+	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1,
+				  dmz_update_zone_cb, zone);
 	memalloc_noio_restore(noio_flag);
-	if (!nr_blkz)
+
+	if (ret == 0)
 		ret = -EIO;
-	if (ret) {
+	if (ret < 0) {
 		dmz_dev_err(zmd->dev, "Get zone %u report failed",
 			    dmz_id(zmd, zone));
+		dmz_check_bdev(zmd->dev);
 		return ret;
 	}
 
-	clear_bit(DMZ_OFFLINE, &zone->flags);
-	clear_bit(DMZ_READ_ONLY, &zone->flags);
-	if (blkz.cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz.cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
-
-	if (dmz_is_seq(zone))
-		zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start);
-	else
-		zone->wp_block = 0;
-
 	return 0;
 }
 
@@ -1312,9 +1286,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index d240d7ca8a8a..e7ace908a9b7 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -82,6 +82,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
 			    "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
 			    dmz_id(zmd, zone), (unsigned long long)wp_block,
 			    (unsigned long long)block, nr_blocks, ret);
+		dmz_check_bdev(zrc->dev);
 		return ret;
 	}
 
@@ -489,12 +490,7 @@ static void dmz_reclaim_work(struct work_struct *work)
 	ret = dmz_do_reclaim(zrc);
 	if (ret) {
 		dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret);
-		if (ret == -EIO)
-			/*
-			 * LLD might be performing some error handling sequence
-			 * at the underlying device. To not interfere, do not
-			 * attempt to schedule the next reclaim run immediately.
-			 */
+		if (!dmz_check_bdev(zrc->dev))
 			return;
 	}
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index d3bcc4197f5d..4574e0dedbd6 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
 
 	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
 		bio->bi_status = status;
+	if (bio->bi_status != BLK_STS_OK)
+		bioctx->target->dev->flags |= DMZ_CHECK_BDEV;
 
 	if (refcount_dec_and_test(&bioctx->ref)) {
 		struct dm_zone *zone = bioctx->zone;
@@ -565,32 +567,52 @@ out:
 }
 
 /*
- * Check the backing device availability. If it's on the way out,
+ * Check if the backing device is being removed. If it's on the way out,
  * start failing I/O. Reclaim and metadata components also call this
  * function to cleanly abort operation in the event of such failure.
  */
 bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev)
 {
-	struct gendisk *disk;
+	if (dmz_dev->flags & DMZ_BDEV_DYING)
+		return true;
 
-	if (!(dmz_dev->flags & DMZ_BDEV_DYING)) {
-		disk = dmz_dev->bdev->bd_disk;
-		if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
-			dmz_dev_warn(dmz_dev, "Backing device queue dying");
-			dmz_dev->flags |= DMZ_BDEV_DYING;
-		} else if (disk->fops->check_events) {
-			if (disk->fops->check_events(disk, 0) &
-					DISK_EVENT_MEDIA_CHANGE) {
-				dmz_dev_warn(dmz_dev, "Backing device offline");
-				dmz_dev->flags |= DMZ_BDEV_DYING;
-			}
-		}
+	if (dmz_dev->flags & DMZ_CHECK_BDEV)
+		return !dmz_check_bdev(dmz_dev);
+
+	if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
+		dmz_dev_warn(dmz_dev, "Backing device queue dying");
+		dmz_dev->flags |= DMZ_BDEV_DYING;
 	}
 
 	return dmz_dev->flags & DMZ_BDEV_DYING;
 }
 
 /*
+ * Check the backing device availability. This detects such events as
+ * backing device going offline due to errors, media removals, etc.
+ * This check is less efficient than dmz_bdev_is_dying() and should
+ * only be performed as a part of error handling.
+ */
+bool dmz_check_bdev(struct dmz_dev *dmz_dev)
+{
+	struct gendisk *disk;
+
+	dmz_dev->flags &= ~DMZ_CHECK_BDEV;
+
+	if (dmz_bdev_is_dying(dmz_dev))
+		return false;
+
+	disk = dmz_dev->bdev->bd_disk;
+	if (disk->fops->check_events &&
+	    disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) {
+		dmz_dev_warn(dmz_dev, "Backing device offline");
+		dmz_dev->flags |= DMZ_BDEV_DYING;
+	}
+
+	return !(dmz_dev->flags & DMZ_BDEV_DYING);
+}
+
+/*
  * Process a new BIO.
  */
 static int dmz_map(struct dm_target *ti, struct bio *bio)
@@ -902,8 +924,8 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct dmz_target *dmz = ti->private;
 
-	if (dmz_bdev_is_dying(dmz->dev))
-		return -ENODEV;
+	if (!dmz_check_bdev(dmz->dev))
+		return -EIO;
 
 	*bdev = dmz->dev->bdev;
 
diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h
index d8e70b0ade35..5b5e493d479c 100644
--- a/drivers/md/dm-zoned.h
+++ b/drivers/md/dm-zoned.h
@@ -72,6 +72,7 @@ struct dmz_dev {
 
 /* Device flags. */
 #define DMZ_BDEV_DYING		(1 << 0)
+#define DMZ_CHECK_BDEV		(2 << 0)
 
 /*
  * Zone descriptor.
@@ -255,5 +256,6 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc);
  * Functions defined in dm-zoned-target.c
  */
 bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev);
+bool dmz_check_bdev(struct dmz_dev *dmz_dev);
 
 #endif /* DM_ZONED_H */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1a5e328c443a..e8f9661a10a1 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data)
+{
+	struct dm_report_zones_args *args = data;
+	sector_t sector_diff = args->tgt->begin - args->start;
+
+	/*
+	 * Ignore zones beyond the target range.
+	 */
+	if (zone->start >= args->start + args->tgt->len)
+		return 0;
+
+	/*
+	 * Remap the start sector and write pointer position of the zone
+	 * to match its position in the target range.
+	 */
+	zone->start += sector_diff;
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			zone->wp = zone->start + zone->len;
+		else if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->wp = zone->start;
+		else
+			zone->wp += sector_diff;
+	}
+
+	args->next_sector = zone->start + zone->len;
+	return args->orig_cb(zone, args->zone_idx++, args->orig_data);
+}
+EXPORT_SYMBOL_GPL(dm_report_zones_cb);
+
 static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones)
+		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
-#ifdef CONFIG_BLK_DEV_ZONED
 	struct mapped_device *md = disk->private_data;
-	struct dm_target *tgt;
 	struct dm_table *map;
 	int srcu_idx, ret;
+	struct dm_report_zones_args args = {
+		.next_sector = sector,
+		.orig_data = data,
+		.orig_cb = cb,
+	};
 
 	if (dm_suspended_md(md))
 		return -EAGAIN;
@@ -456,38 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 	if (!map)
 		return -EIO;
 
-	tgt = dm_table_find_target(map, sector);
-	if (!tgt) {
-		ret = -EIO;
-		goto out;
-	}
+	do {
+		struct dm_target *tgt;
 
-	/*
-	 * If we are executing this, we already know that the block device
-	 * is a zoned device and so each target should have support for that
-	 * type of drive. A missing report_zones method means that the target
-	 * driver has a problem.
-	 */
-	if (WARN_ON(!tgt->type->report_zones)) {
-		ret = -EIO;
-		goto out;
-	}
+		tgt = dm_table_find_target(map, args.next_sector);
+		if (WARN_ON_ONCE(!tgt->type->report_zones)) {
+			ret = -EIO;
+			goto out;
+		}
 
-	/*
-	 * blkdev_report_zones() will loop and call this again to cover all the
-	 * zones of the target, eventually moving on to the next target.
-	 * So there is no need to loop here trying to fill the entire array
-	 * of zones.
-	 */
-	ret = tgt->type->report_zones(tgt, sector, zones, nr_zones);
+		args.tgt = tgt;
+		ret = tgt->type->report_zones(tgt, &args, nr_zones);
+		if (ret < 0)
+			goto out;
+	} while (args.zone_idx < nr_zones &&
+		 args.next_sector < get_capacity(disk));
 
+	ret = args.zone_idx;
 out:
 	dm_put_live_table(md, srcu_idx);
 	return ret;
-#else
-	return -ENOTSUPP;
-#endif
 }
+#else
+#define dm_blk_report_zones		NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
 			    struct block_device **bdev)
@@ -1174,7 +1200,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
- * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
+ * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
+ * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH.
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1212,54 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
-/*
- * The zone descriptors obtained with a zone report indicate
- * zone positions within the underlying device of the target. The zone
- * descriptors must be remapped to match their position within the dm device.
- * The caller target should obtain the zones information using
- * blkdev_report_zones() to ensure that remapping for partition offset is
- * already handled.
- */
-void dm_remap_zone_report(struct dm_target *ti, sector_t start,
-			  struct blk_zone *zones, unsigned int *nr_zones)
-{
-#ifdef CONFIG_BLK_DEV_ZONED
-	struct blk_zone *zone;
-	unsigned int nrz = *nr_zones;
-	int i;
-
-	/*
-	 * Remap the start sector and write pointer position of the zones in
-	 * the array. Since we may have obtained from the target underlying
-	 * device more zones that the target size, also adjust the number
-	 * of zones.
-	 */
-	for (i = 0; i < nrz; i++) {
-		zone = zones + i;
-		if (zone->start >= start + ti->len) {
-			memset(zone, 0, sizeof(struct blk_zone) * (nrz - i));
-			break;
-		}
-
-		zone->start = zone->start + ti->begin - start;
-		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-			continue;
-
-		if (zone->cond == BLK_ZONE_COND_FULL)
-			zone->wp = zone->start + zone->len;
-		else if (zone->cond == BLK_ZONE_COND_EMPTY)
-			zone->wp = zone->start;
-		else
-			zone->wp = zone->wp + ti->begin - start;
-	}
-
-	*nr_zones = i;
-#else /* !CONFIG_BLK_DEV_ZONED */
-	*nr_zones = 0;
-#endif
-}
-EXPORT_SYMBOL_GPL(dm_remap_zone_report);
-
 static blk_qc_t __map_bio(struct dm_target_io *tio)
 {
 	int r;
@@ -1627,7 +1606,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
-	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
+	} else if (op_is_zone_mgmt(bio_op(bio))) {
 		ci.bio = bio;
 		ci.sector_count = 0;
 		error = __split_and_process_non_flush(&ci);
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index b092c7b5282f..3ad18246fcb3 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
 		       sizeof(bitmap_super_t));
+	spin_lock_irq(&bitmap->counts.lock);
 	md_bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 
@@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	blocks = min(old_counts.chunks << old_counts.chunkshift,
 		     chunks << chunkshift);
 
-	spin_lock_irq(&bitmap->counts.lock);
 	/* For cluster raid, need to pre-allocate bitmap */
 	if (mddev_is_clustered(bitmap->mddev)) {
 		unsigned long page;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c766c559d36d..26c75c0199fa 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	sector_t start_sector, end_sector, data_offset;
 	sector_t bio_sector = bio->bi_iter.bi_sector;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	tmp_dev = which_dev(mddev, bio_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 6780938d2991..152f9e65a226 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1be7abeb24fd..805b33e27496 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws)
 	}
 }
 
-void md_flush_request(struct mddev *mddev, struct bio *bio)
+/*
+ * Manages consolidation of flushes and submitting any flushes needed for
+ * a bio with REQ_PREFLUSH.  Returns true if the bio is finished or is
+ * being finished in another context.  Returns false if the flushing is
+ * complete but still needs the I/O portion of the bio to be processed.
+ */
+bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
 	ktime_t start = ktime_get_boottime();
 	spin_lock_irq(&mddev->lock);
@@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 			bio_endio(bio);
 		else {
 			bio->bi_opf &= ~REQ_PREFLUSH;
-			mddev->pers->make_request(mddev, bio);
+			return false;
 		}
 	}
+	return true;
 }
 EXPORT_SYMBOL(md_flush_request);
 
@@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	mdp_super_t *sb;
 	int ret;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock (512byte sectors),
@@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	else
 		rdev->desc_nr = sb->this_disk.number;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == LEVEL_MULTIPATH ||
+		(rdev->desc_nr >= 0 &&
+		 sb->disks[rdev->desc_nr].state &
+		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = page_address(refdev->sb_page);
@@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		}
 		ev1 = md_event(sb);
 		ev2 = md_event(refsb);
-		if (ev1 > ev2)
+
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	sector_t sectors;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	int bmask;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock in 512byte sectors.
@@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
+		(rdev->desc_nr >= 0 &&
+		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);
@@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		ev1 = le64_to_cpu(sb->events);
 		ev2 = le64_to_cpu(refsb->events);
 
-		if (ev1 > ev2)
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -3597,7 +3628,7 @@ abort_free:
  * Check a full RAID array for plausibility
  */
 
-static void analyze_sbs(struct mddev *mddev)
+static int analyze_sbs(struct mddev *mddev)
 {
 	int i;
 	struct md_rdev *rdev, *freshest, *tmp;
@@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev)
 			md_kick_rdev_from_array(rdev);
 		}
 
+	/* Cannot find a valid fresh disk */
+	if (!freshest) {
+		pr_warn("md: cannot find a valid disk\n");
+		return -EINVAL;
+	}
+
 	super_types[mddev->major_version].
 		validate_super(mddev, freshest);
 
@@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev)
 			clear_bit(In_sync, &rdev->flags);
 		}
 	}
+
+	return 0;
 }
 
 /* Read a fixed-point number.
@@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev)
 	if (!mddev->raid_disks) {
 		if (!mddev->persistent)
 			return -EINVAL;
-		analyze_sbs(mddev);
+		err = analyze_sbs(mddev);
+		if (err)
+			return -EINVAL;
 	}
 
 	if (mddev->level != LEVEL_NONE)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index c5e3ff398b59..5f86f8adb0a4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -550,7 +550,7 @@ struct md_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	bool (*make_request)(struct mddev *mddev, struct bio *bio);
+	bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio);
 	/*
 	 * start up works that do NOT require md_thread. tasks that
 	 * requires md_thread should go into start()
@@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
 extern int mddev_congested(struct mddev *mddev, int bits);
-extern void md_flush_request(struct mddev *mddev, struct bio *bio);
+extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern int md_super_wait(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f61693e59684..b7c20979bd19 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -154,7 +154,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	} else {
 		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
 		       mdname(mddev));
-		pr_err("md/raid0: please set raid.default_layout to 1 or 2\n");
+		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
 		err = -ENOTSUPP;
 		goto abort;
 	}
@@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 	unsigned chunk_sects;
 	unsigned sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
 		raid0_handle_discard(mddev, bio);
@@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		tmp_dev = map_sector(mddev, zone, sector, &sector);
 		break;
 	default:
-		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
 		bio_io_error(bio);
 		return true;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0466ee2453b4..a409ab6f30bc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 		else
 			generic_make_request(bio);
 		bio = next;
+		cond_resched();
 	}
 }
 
@@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	/*
 	 * There is a limit to the maximum size, but
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 299c7b1c9718..ec136e44aef7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 out_free_pages:
 	while (--j >= 0)
-		resync_free_pages(&rps[j * 2]);
+		resync_free_pages(&rps[j]);
 
 	j = 0;
 out_free_bio:
@@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	int chunk_sects = chunk_mask + 1;
 	int sectors = bio_sectors(bio);
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (!md_write_start(mddev, bio))
 		return false;
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 18a4064a61a8..cab5b1352892 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf)
 	atomic64_set(&ppl_conf->seq, 0);
 	INIT_LIST_HEAD(&ppl_conf->no_mem_stripes);
 	spin_lock_init(&ppl_conf->no_mem_stripes_lock);
-	ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET;
+	ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET;
 
 	if (!mddev->external) {
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 223e97ab27e6..f0fc538bfe59 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1134,7 +1134,7 @@ again:
 			bi->bi_iter.bi_size = STRIPE_SIZE;
 			bi->bi_write_hint = sh->dev[i].write_hint;
 			if (!rrdev)
-				sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+				sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -1187,7 +1187,7 @@ again:
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_iter.bi_size = STRIPE_SIZE;
 			rbi->bi_write_hint = sh->dev[i].write_hint;
-			sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+			sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		if (ret == 0)
 			return true;
 		if (ret == -ENODEV) {
-			md_flush_request(mddev, bi);
-			return true;
+			if (md_flush_request(mddev, bi))
+				return true;
 		}
 		/* ret == -EAGAIN, fallback */
 		/*
diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index 32747425297d..64fff6abe60e 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -941,7 +941,7 @@ static int jmb38x_ms_probe(struct pci_dev *pdev,
 	if (!cnt) {
 		rc = -ENODEV;
 		pci_dev_busy = 1;
-		goto err_out;
+		goto err_out_int;
 	}
 
 	jm = kzalloc(sizeof(struct jmb38x_ms)
diff --git a/drivers/mfd/mt6397-core.c b/drivers/mfd/mt6397-core.c
index 310dae26ddff..b2c325ead1c8 100644
--- a/drivers/mfd/mt6397-core.c
+++ b/drivers/mfd/mt6397-core.c
@@ -129,11 +129,27 @@ static int mt6397_irq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(mt6397_pm_ops, mt6397_irq_suspend,
 			mt6397_irq_resume);
 
+struct chip_data {
+	u32 cid_addr;
+	u32 cid_shift;
+};
+
+static const struct chip_data mt6323_core = {
+	.cid_addr = MT6323_CID,
+	.cid_shift = 0,
+};
+
+static const struct chip_data mt6397_core = {
+	.cid_addr = MT6397_CID,
+	.cid_shift = 0,
+};
+
 static int mt6397_probe(struct platform_device *pdev)
 {
 	int ret;
 	unsigned int id;
 	struct mt6397_chip *pmic;
+	const struct chip_data *pmic_core;
 
 	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
@@ -149,28 +165,30 @@ static int mt6397_probe(struct platform_device *pdev)
 	if (!pmic->regmap)
 		return -ENODEV;
 
-	platform_set_drvdata(pdev, pmic);
+	pmic_core = of_device_get_match_data(&pdev->dev);
+	if (!pmic_core)
+		return -ENODEV;
 
-	ret = regmap_read(pmic->regmap, MT6397_CID, &id);
+	ret = regmap_read(pmic->regmap, pmic_core->cid_addr, &id);
 	if (ret) {
-		dev_err(pmic->dev, "Failed to read chip id: %d\n", ret);
+		dev_err(&pdev->dev, "Failed to read chip id: %d\n", ret);
 		return ret;
 	}
 
+	pmic->chip_id = (id >> pmic_core->cid_shift) & 0xff;
+
+	platform_set_drvdata(pdev, pmic);
+
 	pmic->irq = platform_get_irq(pdev, 0);
 	if (pmic->irq <= 0)
 		return pmic->irq;
 
-	switch (id & 0xff) {
-	case MT6323_CHIP_ID:
-		pmic->int_con[0] = MT6323_INT_CON0;
-		pmic->int_con[1] = MT6323_INT_CON1;
-		pmic->int_status[0] = MT6323_INT_STATUS0;
-		pmic->int_status[1] = MT6323_INT_STATUS1;
-		ret = mt6397_irq_init(pmic);
-		if (ret)
-			return ret;
+	ret = mt6397_irq_init(pmic);
+	if (ret)
+		return ret;
 
+	switch (pmic->chip_id) {
+	case MT6323_CHIP_ID:
 		ret = devm_mfd_add_devices(&pdev->dev, -1, mt6323_devs,
 					   ARRAY_SIZE(mt6323_devs), NULL,
 					   0, pmic->irq_domain);
@@ -178,21 +196,13 @@ static int mt6397_probe(struct platform_device *pdev)
 
 	case MT6391_CHIP_ID:
 	case MT6397_CHIP_ID:
-		pmic->int_con[0] = MT6397_INT_CON0;
-		pmic->int_con[1] = MT6397_INT_CON1;
-		pmic->int_status[0] = MT6397_INT_STATUS0;
-		pmic->int_status[1] = MT6397_INT_STATUS1;
-		ret = mt6397_irq_init(pmic);
-		if (ret)
-			return ret;
-
 		ret = devm_mfd_add_devices(&pdev->dev, -1, mt6397_devs,
 					   ARRAY_SIZE(mt6397_devs), NULL,
 					   0, pmic->irq_domain);
 		break;
 
 	default:
-		dev_err(&pdev->dev, "unsupported chip: %d\n", id);
+		dev_err(&pdev->dev, "unsupported chip: %d\n", pmic->chip_id);
 		return -ENODEV;
 	}
 
@@ -205,9 +215,15 @@ static int mt6397_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id mt6397_of_match[] = {
-	{ .compatible = "mediatek,mt6397" },
-	{ .compatible = "mediatek,mt6323" },
-	{ }
+	{
+		.compatible = "mediatek,mt6323",
+		.data = &mt6323_core,
+	}, {
+		.compatible = "mediatek,mt6397",
+		.data = &mt6397_core,
+	}, {
+		/* sentinel */
+	}
 };
 MODULE_DEVICE_TABLE(of, mt6397_of_match);
 
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index f7bdae5354c3..5047f7343ffc 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -611,7 +611,8 @@ static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	cq_host->slot[tag].flags = 0;
 
 	cq_host->qcnt += 1;
-
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
 	cqhci_writel(cq_host, 1 << tag, CQHCI_TDBR);
 	if (!(cqhci_readl(cq_host, CQHCI_TDBR) & (1 << tag)))
 		pr_debug("%s: cqhci: doorbell not set for tag %d\n",
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 78e7e350655c..4031217d21c3 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
+#include <linux/dma/mxs-dma.h>
 #include <linux/highmem.h>
 #include <linux/clk.h>
 #include <linux/err.h>
@@ -266,7 +267,7 @@ static void mxs_mmc_bc(struct mxs_mmc_host *host)
 	ssp->ssp_pio_words[2] = cmd1;
 	ssp->dma_dir = DMA_NONE;
 	ssp->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
@@ -311,7 +312,7 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	ssp->ssp_pio_words[2] = cmd1;
 	ssp->dma_dir = DMA_NONE;
 	ssp->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
@@ -441,7 +442,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 	host->data = data;
 	ssp->dma_dir = dma_data_dir;
 	ssp->slave_dirn = slave_dirn;
-	desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index d4ada5cca2d1..234551a68739 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -646,8 +646,8 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	struct tmio_mmc_dma *dma_priv;
 	struct tmio_mmc_host *host;
 	struct renesas_sdhi *priv;
+	int num_irqs, irq, ret, i;
 	struct resource *res;
-	int irq, ret, i;
 	u16 ver;
 
 	of_data = of_device_get_match_data(&pdev->dev);
@@ -825,24 +825,31 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		host->hs400_complete = renesas_sdhi_hs400_complete;
 	}
 
-	i = 0;
-	while (1) {
+	num_irqs = platform_irq_count(pdev);
+	if (num_irqs < 0) {
+		ret = num_irqs;
+		goto eirq;
+	}
+
+	/* There must be at least one IRQ source */
+	if (!num_irqs) {
+		ret = -ENXIO;
+		goto eirq;
+	}
+
+	for (i = 0; i < num_irqs; i++) {
 		irq = platform_get_irq(pdev, i);
-		if (irq < 0)
-			break;
-		i++;
+		if (irq < 0) {
+			ret = irq;
+			goto eirq;
+		}
+
 		ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
 				       dev_name(&pdev->dev), host);
 		if (ret)
 			goto eirq;
 	}
 
-	/* There must be at least one IRQ source */
-	if (!i) {
-		ret = irq;
-		goto eirq;
-	}
-
 	dev_info(&pdev->dev, "%s base at 0x%08lx max clock rate %u MHz\n",
 		 mmc_hostname(host->mmc), (unsigned long)
 		 (platform_get_resource(pdev, IORESOURCE_MEM, 0)->start),
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 2b9cdcd1dd9d..f4f5f0a70cda 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -262,6 +262,7 @@ static const struct sdhci_iproc_data bcm2835_data = {
 };
 
 static const struct sdhci_pltfm_data sdhci_bcm2711_pltfm_data = {
+	.quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
 	.ops = &sdhci_iproc_32only_ops,
 };
 
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index e7d1920729fb..0ae986c42bc8 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -358,7 +358,7 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 
 	/* HS200 is broken at this moment */
-	host->quirks2 = SDHCI_QUIRK2_BROKEN_HS200;
+	host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
 
 	ret = sdhci_add_host(host);
 	if (ret)
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 41c2677c587f..083e7e053c95 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -372,7 +372,7 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * on temperature
 	 */
 	if (temperature < -20000)
-		phase_delay = min(max_window + 4 * max_len - 24,
+		phase_delay = min(max_window + 4 * (max_len - 1) - 24,
 				  max_window +
 				  DIV_ROUND_UP(13 * max_len, 16) * 4);
 	else if (temperature < 20000)
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 81bd9afb0980..98c575de43c7 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1393,11 +1393,9 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	const char *name;
 
 	irq[0] = platform_get_irq(pdev, 0);
-	irq[1] = platform_get_irq(pdev, 1);
-	if (irq[0] < 0) {
-		dev_err(dev, "Get irq error\n");
+	irq[1] = platform_get_irq_optional(pdev, 1);
+	if (irq[0] < 0)
 		return -ENXIO;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(dev, res);
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index 79a53cb8507b..00a79489067c 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -1353,7 +1353,7 @@ static int do_point_onechip (struct map_info *map, struct flchip *chip, loff_t a
 {
 	unsigned long cmd_addr;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1383,7 +1383,7 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len,
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long ofs, last_end = 0;
 	int chipnum;
-	int ret = 0;
+	int ret;
 
 	if (!map->virt)
 		return -EINVAL;
@@ -1550,7 +1550,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	map_word status, write_cmd;
-	int ret=0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1624,7 +1624,7 @@ static int cfi_intelext_write_words (struct mtd_info *mtd, loff_t to , size_t le
 {
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -1871,7 +1871,7 @@ static int cfi_intelext_writev (struct mtd_info *mtd, const struct kvec *vecs,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs, vec_seek, i;
 	size_t len = 0;
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index cf8c8be40a9c..04b383bc3947 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -123,19 +123,23 @@ static int cfi_use_status_reg(struct cfi_private *cfi)
 		(extp->SoftwareFeatures & poll_mask) == CFI_POLL_STATUS_REG;
 }
 
-static void cfi_check_err_status(struct map_info *map, struct flchip *chip,
-				 unsigned long adr)
+static int cfi_check_err_status(struct map_info *map, struct flchip *chip,
+				unsigned long adr)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	map_word status;
 
 	if (!cfi_use_status_reg(cfi))
-		return;
+		return 0;
 
 	cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
 			 cfi->device_type, NULL);
 	status = map_read(map, adr);
 
+	/* The error bits are invalid while the chip's busy */
+	if (!map_word_bitsset(map, status, CMD(CFI_SR_DRB)))
+		return 0;
+
 	if (map_word_bitsset(map, status, CMD(0x3a))) {
 		unsigned long chipstatus = MERGESTATUS(status);
 
@@ -151,7 +155,12 @@ static void cfi_check_err_status(struct map_info *map, struct flchip *chip,
 		if (chipstatus & CFI_SR_SLSB)
 			pr_err("%s sector write protected, status %lx\n",
 			       map->name, chipstatus);
+
+		/* Erase/Program status bits are set on the operation failure */
+		if (chipstatus & (CFI_SR_ESB | CFI_SR_PSB))
+			return 1;
 	}
+	return 0;
 }
 
 /* #define DEBUG_CFI_FEATURES */
@@ -785,7 +794,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd)
 	kfree(mtd->eraseregions);
 	kfree(mtd);
 	kfree(cfi->cmdset_priv);
-	kfree(cfi->cfiq);
 	return NULL;
 }
 
@@ -848,20 +856,16 @@ static int __xipram chip_good(struct map_info *map, struct flchip *chip,
 
 	if (cfi_use_status_reg(cfi)) {
 		map_word ready = CMD(CFI_SR_DRB);
-		map_word err = CMD(CFI_SR_PSB | CFI_SR_ESB);
+
 		/*
 		 * For chips that support status register, check device
-		 * ready bit and Erase/Program status bit to know if
-		 * operation succeeded.
+		 * ready bit
 		 */
 		cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi,
 				 cfi->device_type, NULL);
 		curd = map_read(map, addr);
 
-		if (map_word_andequal(map, curd, ready, ready))
-			return !map_word_bitsset(map, curd, err);
-
-		return 0;
+		return map_word_andequal(map, curd, ready, ready);
 	}
 
 	oldd = map_read(map, addr);
@@ -1699,8 +1703,11 @@ static int __xipram do_write_oneword_once(struct map_info *map,
 			break;
 		}
 
-		if (chip_good(map, chip, adr, datum))
+		if (chip_good(map, chip, adr, datum)) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		/* Latency issues. Drop the lock, wait a while and retry */
 		UDELAY(map, chip, adr, 1);
@@ -1713,7 +1720,7 @@ static int __xipram do_write_oneword_start(struct map_info *map,
 					   struct flchip *chip,
 					   unsigned long adr, int mode)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&chip->mutex);
 
@@ -1773,7 +1780,6 @@ static int __xipram do_write_oneword_retry(struct map_info *map,
 	ret = do_write_oneword_once(map, chip, adr, datum, mode, cfi);
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -1791,7 +1797,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 				     unsigned long adr, map_word datum,
 				     int mode)
 {
-	int ret = 0;
+	int ret;
 
 	adr += chip->start;
 
@@ -1815,7 +1821,7 @@ static int cfi_amdstd_write_words(struct mtd_info *mtd, loff_t to, size_t len,
 {
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs, chipstart;
 	DECLARE_WAITQUEUE(wait, current);
@@ -1970,12 +1976,17 @@ static int __xipram do_write_buffer_wait(struct map_info *map,
 		 */
 		if (time_after(jiffies, timeo) &&
 		    !chip_good(map, chip, adr, datum)) {
+			pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
+			       __func__, adr);
 			ret = -EIO;
 			break;
 		}
 
-		if (chip_good(map, chip, adr, datum))
+		if (chip_good(map, chip, adr, datum)) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		/* Latency issues. Drop the lock, wait a while and retry */
 		UDELAY(map, chip, adr, 1);
@@ -2014,7 +2025,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 				    int len)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
-	int ret = -EIO;
+	int ret;
 	unsigned long cmd_adr;
 	int z, words;
 	map_word datum;
@@ -2071,12 +2082,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 				chip->word_write_time);
 
 	ret = do_write_buffer_wait(map, chip, adr, datum);
-	if (ret) {
-		cfi_check_err_status(map, chip, adr);
+	if (ret)
 		do_write_buffer_reset(map, chip, cfi);
-		pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
-		       __func__, adr);
-	}
 
 	xip_enable(map, chip, adr);
 
@@ -2095,7 +2102,7 @@ static int cfi_amdstd_write_buffers(struct mtd_info *mtd, loff_t to, size_t len,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -2232,7 +2239,7 @@ static int do_panic_write_oneword(struct map_info *map, struct flchip *chip,
 	struct cfi_private *cfi = map->fldrv_priv;
 	int retry_cnt = 0;
 	map_word oldd;
-	int ret = 0;
+	int ret;
 	int i;
 
 	adr += chip->start;
@@ -2271,9 +2278,9 @@ retry:
 		udelay(1);
 	}
 
-	if (!chip_good(map, chip, adr, datum)) {
+	if (!chip_good(map, chip, adr, datum) ||
+	    cfi_check_err_status(map, chip, adr)) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -2307,7 +2314,7 @@ static int cfi_amdstd_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long ofs, chipstart;
-	int ret = 0;
+	int ret;
 	int chipnum;
 
 	chipnum = to >> cfi->chipshift;
@@ -2411,7 +2418,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 	unsigned long timeo = jiffies + HZ;
 	unsigned long int adr;
 	DECLARE_WAITQUEUE(wait, current);
-	int ret = 0;
+	int ret;
 	int retry_cnt = 0;
 
 	adr = cfi->addr_unlock1;
@@ -2467,8 +2474,11 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 			chip->erase_suspended = 0;
 		}
 
-		if (chip_good(map, chip, adr, map_word_ff(map)))
+		if (chip_good(map, chip, adr, map_word_ff(map))) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		if (time_after(jiffies, timeo)) {
 			printk(KERN_WARNING "MTD %s(): software timeout\n",
@@ -2483,7 +2493,6 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
 	/* Did we succeed? */
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
@@ -2508,7 +2517,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long timeo = jiffies + HZ;
 	DECLARE_WAITQUEUE(wait, current);
-	int ret = 0;
+	int ret;
 	int retry_cnt = 0;
 
 	adr += chip->start;
@@ -2564,8 +2573,11 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 			chip->erase_suspended = 0;
 		}
 
-		if (chip_good(map, chip, adr, map_word_ff(map)))
+		if (chip_good(map, chip, adr, map_word_ff(map))) {
+			if (cfi_check_err_status(map, chip, adr))
+				ret = -EIO;
 			break;
+		}
 
 		if (time_after(jiffies, timeo)) {
 			printk(KERN_WARNING "MTD %s(): software timeout\n",
@@ -2580,7 +2592,6 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 	/* Did we succeed? */
 	if (ret) {
 		/* reset on all failures. */
-		cfi_check_err_status(map, chip, adr);
 		map_write(map, CMD(0xF0), chip->start);
 		/* FIXME - should have reset delay before continuing */
 
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index e752067526a5..54edae63b92d 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -611,7 +611,7 @@ static int cfi_staa_write_buffers (struct mtd_info *mtd, loff_t to,
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize;
-	int ret = 0;
+	int ret;
 	int chipnum;
 	unsigned long ofs;
 
@@ -895,7 +895,7 @@ static int cfi_staa_erase_varsize(struct mtd_info *mtd,
 {	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr, len;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 	int i, first;
 	struct mtd_erase_region_info *regions = mtd->eraseregions;
 
@@ -1132,7 +1132,7 @@ static int cfi_staa_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 #ifdef DEBUG_LOCK_BITS
 	int ofs_factor = cfi->interleave * cfi->device_type;
 #endif
@@ -1279,7 +1279,7 @@ static int cfi_staa_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct map_info *map = mtd->priv;
 	struct cfi_private *cfi = map->fldrv_priv;
 	unsigned long adr;
-	int chipnum, ret = 0;
+	int chipnum, ret;
 #ifdef DEBUG_LOCK_BITS
 	int ofs_factor = cfi->interleave * cfi->device_type;
 #endif
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index e3b266ee06af..e2d4db05aeb3 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -26,7 +26,7 @@
 void cfi_udelay(int us)
 {
 	if (us >= 1000) {
-		msleep((us+999)/1000);
+		msleep(DIV_ROUND_UP(us, 1000));
 	} else {
 		udelay(us);
 		cond_resched();
diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c
index b20d02b4f830..77c872fd3d83 100644
--- a/drivers/mtd/devices/mchp23k256.c
+++ b/drivers/mtd/devices/mchp23k256.c
@@ -64,15 +64,17 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	command[0] = MCHP23K256_CMD_WRITE;
 	mchp23k256_addr2cmd(flash, to, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].tx_buf = buf;
@@ -88,8 +90,8 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
@@ -101,16 +103,18 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	memset(&transfer, 0, sizeof(transfer));
 	command[0] = MCHP23K256_CMD_READ;
 	mchp23k256_addr2cmd(flash, from, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].rx_buf = buf;
@@ -126,8 +130,8 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c
index 986f81d2f93e..79dcca16481d 100644
--- a/drivers/mtd/devices/spear_smi.c
+++ b/drivers/mtd/devices/spear_smi.c
@@ -592,6 +592,26 @@ static int spear_mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 	return 0;
 }
 
+/*
+ * The purpose of this function is to ensure a memcpy_toio() with byte writes
+ * only. Its structure is inspired from the ARM implementation of _memcpy_toio()
+ * which also does single byte writes but cannot be used here as this is just an
+ * implementation detail and not part of the API. Not mentioning the comment
+ * stating that _memcpy_toio() should be optimized.
+ */
+static void spear_smi_memcpy_toio_b(volatile void __iomem *dest,
+				    const void *src, size_t len)
+{
+	const unsigned char *from = src;
+
+	while (len) {
+		len--;
+		writeb(*from, dest);
+		from++;
+		dest++;
+	}
+}
+
 static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank,
 		void __iomem *dest, const void *src, size_t len)
 {
@@ -614,7 +634,23 @@ static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank,
 	ctrlreg1 = readl(dev->io_base + SMI_CR1);
 	writel((ctrlreg1 | WB_MODE) & ~SW_MODE, dev->io_base + SMI_CR1);
 
-	memcpy_toio(dest, src, len);
+	/*
+	 * In Write Burst mode (WB_MODE), the specs states that writes must be:
+	 * - incremental
+	 * - of the same size
+	 * The ARM implementation of memcpy_toio() will optimize the number of
+	 * I/O by using as much 4-byte writes as possible, surrounded by
+	 * 2-byte/1-byte access if:
+	 * - the destination is not 4-byte aligned
+	 * - the length is not a multiple of 4-byte.
+	 * Avoid this alternance of write access size by using our own 'byte
+	 * access' helper if at least one of the two conditions above is true.
+	 */
+	if (IS_ALIGNED(len, sizeof(u32)) &&
+	    IS_ALIGNED((uintptr_t)dest, sizeof(u32)))
+		memcpy_toio(dest, src, len);
+	else
+		spear_smi_memcpy_toio_b(dest, src, len);
 
 	writel(ctrlreg1, dev->io_base + SMI_CR1);
 
@@ -777,9 +813,6 @@ static int spear_smi_probe_config_dt(struct platform_device *pdev,
 
 	/* Fill structs for each subnode (flash device) */
 	while ((pp = of_get_next_child(np, pp))) {
-		struct spear_smi_flash_info *flash_info;
-
-		flash_info = &pdata->board_flash_info[i];
 		pdata->np[i] = pp;
 
 		/* Read base-addr and size from DT */
@@ -933,7 +966,6 @@ static int spear_smi_probe(struct platform_device *pdev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = -ENODEV;
-		dev_err(&pdev->dev, "invalid smi irq\n");
 		goto err;
 	}
 
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index f4d1667daaf9..1888523d9745 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -255,7 +255,6 @@ struct stfsm_seq {
 struct stfsm {
 	struct device		*dev;
 	void __iomem		*base;
-	struct resource		*region;
 	struct mtd_info		mtd;
 	struct mutex		lock;
 	struct flash_info       *info;
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bc82305ebb4c..b28225a7c4f3 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -96,6 +96,17 @@ config MTD_PHYSMAP_GEMINI
 	  platforms, some detection and setting up parallel mode on the
 	  external interface.
 
+config MTD_PHYSMAP_IXP4XX
+	bool "Intel IXP4xx OF-based physical memory map handling"
+	depends on MTD_PHYSMAP_OF
+	depends on ARM
+	select MTD_COMPLEX_MAPPINGS
+	select MTD_CFI_BE_BYTE_SWAP if CPU_BIG_ENDIAN
+	default ARCH_IXP4XX
+	help
+	  This provides some extra DT physmap parsing for the Intel IXP4xx
+	  platforms, some elaborate endianness handling in particular.
+
 config MTD_PHYSMAP_GPIO_ADDR
 	bool "GPIO-assisted Flash Chip Support"
 	depends on MTD_PHYSMAP
diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile
index 1146009f41df..c0da86a5d26f 100644
--- a/drivers/mtd/maps/Makefile
+++ b/drivers/mtd/maps/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_MTD_PXA2XX)	+= pxa2xx-flash.o
 physmap-objs-y			+= physmap-core.o
 physmap-objs-$(CONFIG_MTD_PHYSMAP_VERSATILE) += physmap-versatile.o
 physmap-objs-$(CONFIG_MTD_PHYSMAP_GEMINI) += physmap-gemini.o
+physmap-objs-$(CONFIG_MTD_PHYSMAP_IXP4XX) += physmap-ixp4xx.o
 physmap-objs			:= $(physmap-objs-y)
 obj-$(CONFIG_MTD_PHYSMAP)	+= physmap.o
 obj-$(CONFIG_MTD_PISMO)		+= pismo.o
diff --git a/drivers/mtd/maps/l440gx.c b/drivers/mtd/maps/l440gx.c
index 876f12f40018..0eeadfeb620d 100644
--- a/drivers/mtd/maps/l440gx.c
+++ b/drivers/mtd/maps/l440gx.c
@@ -86,7 +86,7 @@ static int __init init_l440gx(void)
 		return -ENOMEM;
 	}
 	simple_map_init(&l440gx_map);
-	printk(KERN_NOTICE "window_addr = 0x%08lx\n", (unsigned long)l440gx_map.virt);
+	pr_debug("window_addr = %p\n", l440gx_map.virt);
 
 	/* Setup the pm iobase resource
 	 * This code should move into some kind of generic bridge
diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c
index 21b556afc305..a9f7964e2edb 100644
--- a/drivers/mtd/maps/physmap-core.c
+++ b/drivers/mtd/maps/physmap-core.c
@@ -41,6 +41,7 @@
 #include <linux/gpio/consumer.h>
 
 #include "physmap-gemini.h"
+#include "physmap-ixp4xx.h"
 #include "physmap-versatile.h"
 
 struct physmap_flash_info {
@@ -370,6 +371,10 @@ static int physmap_flash_of_init(struct platform_device *dev)
 		if (err)
 			return err;
 
+		err = of_flash_probe_ixp4xx(dev, dp, &info->maps[i]);
+		if (err)
+			return err;
+
 		err = of_flash_probe_versatile(dev, dp, &info->maps[i]);
 		if (err)
 			return err;
diff --git a/drivers/mtd/maps/physmap-ixp4xx.c b/drivers/mtd/maps/physmap-ixp4xx.c
new file mode 100644
index 000000000000..6a054229a8a0
--- /dev/null
+++ b/drivers/mtd/maps/physmap-ixp4xx.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel IXP4xx OF physmap add-on
+ * Copyright (C) 2019 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on the ixp4xx.c map driver, originally written by:
+ * Intel Corporation
+ * Deepak Saxena <dsaxena@mvista.com>
+ * Copyright (C) 2002 Intel Corporation
+ * Copyright (C) 2003-2004 MontaVista Software, Inc.
+ */
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/mtd/map.h>
+#include <linux/mtd/xip.h>
+#include "physmap-ixp4xx.h"
+
+/*
+ * Read/write a 16 bit word from flash address 'addr'.
+ *
+ * When the cpu is in little-endian mode it swizzles the address lines
+ * ('address coherency') so we need to undo the swizzling to ensure commands
+ * and the like end up on the correct flash address.
+ *
+ * To further complicate matters, due to the way the expansion bus controller
+ * handles 32 bit reads, the byte stream ABCD is stored on the flash as:
+ *     D15    D0
+ *     +---+---+
+ *     | A | B | 0
+ *     +---+---+
+ *     | C | D | 2
+ *     +---+---+
+ * This means that on LE systems each 16 bit word must be swapped. Note that
+ * this requires CONFIG_MTD_CFI_BE_BYTE_SWAP to be enabled to 'unswap' the CFI
+ * data and other flash commands which are always in D7-D0.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+
+static inline u16 flash_read16(void __iomem *addr)
+{
+	return be16_to_cpu(__raw_readw((void __iomem *)((unsigned long)addr ^ 0x2)));
+}
+
+static inline void flash_write16(u16 d, void __iomem *addr)
+{
+	__raw_writew(cpu_to_be16(d), (void __iomem *)((unsigned long)addr ^ 0x2));
+}
+
+#define	BYTE0(h)	((h) & 0xFF)
+#define	BYTE1(h)	(((h) >> 8) & 0xFF)
+
+#else
+
+static inline u16 flash_read16(const void __iomem *addr)
+{
+	return __raw_readw(addr);
+}
+
+static inline void flash_write16(u16 d, void __iomem *addr)
+{
+	__raw_writew(d, addr);
+}
+
+#define	BYTE0(h)	(((h) >> 8) & 0xFF)
+#define	BYTE1(h)	((h) & 0xFF)
+#endif
+
+static map_word ixp4xx_read16(struct map_info *map, unsigned long ofs)
+{
+	map_word val;
+
+	val.x[0] = flash_read16(map->virt + ofs);
+	return val;
+}
+
+/*
+ * The IXP4xx expansion bus only allows 16-bit wide acceses
+ * when attached to a 16-bit wide device (such as the 28F128J3A),
+ * so we can't just memcpy_fromio().
+ */
+static void ixp4xx_copy_from(struct map_info *map, void *to,
+			     unsigned long from, ssize_t len)
+{
+	u8 *dest = (u8 *) to;
+	void __iomem *src = map->virt + from;
+
+	if (len <= 0)
+		return;
+
+	if (from & 1) {
+		*dest++ = BYTE1(flash_read16(src-1));
+		src++;
+		--len;
+	}
+
+	while (len >= 2) {
+		u16 data = flash_read16(src);
+		*dest++ = BYTE0(data);
+		*dest++ = BYTE1(data);
+		src += 2;
+		len -= 2;
+	}
+
+	if (len > 0)
+		*dest++ = BYTE0(flash_read16(src));
+}
+
+static void ixp4xx_write16(struct map_info *map, map_word d, unsigned long adr)
+{
+	flash_write16(d.x[0], map->virt + adr);
+}
+
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	struct device *dev = &pdev->dev;
+
+	/* Multiplatform guard */
+	if (!of_device_is_compatible(np, "intel,ixp4xx-flash"))
+		return 0;
+
+	map->read = ixp4xx_read16;
+	map->write = ixp4xx_write16;
+	map->copy_from = ixp4xx_copy_from;
+	map->copy_to = NULL;
+
+	dev_info(dev, "initialized Intel IXP4xx-specific physmap control\n");
+
+	return 0;
+}
diff --git a/drivers/mtd/maps/physmap-ixp4xx.h b/drivers/mtd/maps/physmap-ixp4xx.h
new file mode 100644
index 000000000000..b0fc49b7f3ed
--- /dev/null
+++ b/drivers/mtd/maps/physmap-ixp4xx.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/of.h>
+#include <linux/mtd/map.h>
+
+#ifdef CONFIG_MTD_PHYSMAP_IXP4XX
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map);
+#else
+static inline
+int of_flash_probe_ixp4xx(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	return 0;
+}
+#endif
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 975aed94f06c..b841008a9eb7 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -174,7 +174,7 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 			break;
 		case MTD_FILE_MODE_RAW:
 		{
-			struct mtd_oob_ops ops;
+			struct mtd_oob_ops ops = {};
 
 			ops.mode = MTD_OPS_RAW;
 			ops.datbuf = kbuf;
@@ -268,7 +268,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 		case MTD_FILE_MODE_RAW:
 		{
-			struct mtd_oob_ops ops;
+			struct mtd_oob_ops ops = {};
 
 			ops.mode = MTD_OPS_RAW;
 			ops.datbuf = kbuf;
@@ -350,7 +350,7 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd,
 	uint32_t __user *retp)
 {
 	struct mtd_file_info *mfi = file->private_data;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	uint32_t retlen;
 	int ret = 0;
 
@@ -394,7 +394,7 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd,
 	uint32_t __user *retp)
 {
 	struct mtd_file_info *mfi = file->private_data;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	int ret = 0;
 
 	if (length > 4096)
@@ -587,7 +587,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 		struct mtd_write_req __user *argp)
 {
 	struct mtd_write_req req;
-	struct mtd_oob_ops ops;
+	struct mtd_oob_ops ops = {};
 	const void __user *usr_data, *usr_oob;
 	int ret;
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 6cc7ecb0c788..5fac4355b9c2 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -382,33 +382,21 @@ static struct dentry *dfs_dir_mtd;
 static void mtd_debugfs_populate(struct mtd_info *mtd)
 {
 	struct device *dev = &mtd->dev;
-	struct dentry *root, *dent;
+	struct dentry *root;
 
 	if (IS_ERR_OR_NULL(dfs_dir_mtd))
 		return;
 
 	root = debugfs_create_dir(dev_name(dev), dfs_dir_mtd);
-	if (IS_ERR_OR_NULL(root)) {
-		dev_dbg(dev, "won't show data in debugfs\n");
-		return;
-	}
-
 	mtd->dbg.dfs_dir = root;
 
-	if (mtd->dbg.partid) {
-		dent = debugfs_create_file("partid", 0400, root, mtd,
-					   &mtd_partid_debug_fops);
-		if (IS_ERR_OR_NULL(dent))
-			dev_err(dev, "can't create debugfs entry for partid\n");
-	}
+	if (mtd->dbg.partid)
+		debugfs_create_file("partid", 0400, root, mtd,
+				    &mtd_partid_debug_fops);
 
-	if (mtd->dbg.partname) {
-		dent = debugfs_create_file("partname", 0400, root, mtd,
-					   &mtd_partname_debug_fops);
-		if (IS_ERR_OR_NULL(dent))
-			dev_err(dev,
-				"can't create debugfs entry for partname\n");
-	}
+	if (mtd->dbg.partname)
+		debugfs_create_file("partname", 0400, root, mtd,
+				    &mtd_partname_debug_fops);
 }
 
 #ifndef CONFIG_MMU
diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c
index f92414eb4c86..58eefa43af14 100644
--- a/drivers/mtd/mtdswap.c
+++ b/drivers/mtd/mtdswap.c
@@ -1257,7 +1257,6 @@ DEFINE_SHOW_ATTRIBUTE(mtdswap);
 static int mtdswap_add_debugfs(struct mtdswap_dev *d)
 {
 	struct dentry *root = d->mtd->dbg.dfs_dir;
-	struct dentry *dent;
 
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
@@ -1265,12 +1264,7 @@ static int mtdswap_add_debugfs(struct mtdswap_dev *d)
 	if (IS_ERR_OR_NULL(root))
 		return -1;
 
-	dent = debugfs_create_file("mtdswap_stats", S_IRUSR, root, d,
-				&mtdswap_fops);
-	if (!dent) {
-		dev_err(d->dev, "debugfs_create_file failed\n");
-		return -1;
-	}
+	debugfs_create_file("mtdswap_stats", S_IRUSR, root, d, &mtdswap_fops);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index e59de3f60cf6..74fb91adeb46 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -450,6 +450,13 @@ config MTD_NAND_PLATFORM
 	  devices. You will need to provide platform-specific functions
 	  via platform_data.
 
+config MTD_NAND_CADENCE
+	tristate "Support Cadence NAND (HPNFC) controller"
+	depends on OF || COMPILE_TEST
+	help
+	  Enable the driver for NAND flash on platforms using a Cadence NAND
+	  controller.
+
 comment "Misc"
 
 config MTD_SM_COMMON
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index a98721988e61..2d136b158fb7 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -57,6 +57,7 @@ obj-$(CONFIG_MTD_NAND_MXIC)		+= mxic_nand.o
 obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 obj-$(CONFIG_MTD_NAND_STM32_FMC2)	+= stm32_fmc2_nand.o
 obj-$(CONFIG_MTD_NAND_MESON)		+= meson_nand.o
+obj-$(CONFIG_MTD_NAND_CADENCE)		+= cadence-nand-controller.o
 
 nand-objs := nand_base.o nand_legacy.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_onfi.o
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 15ef30b368a5..1a66b1cd51c0 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -117,6 +117,18 @@ enum flash_dma_reg {
 	FLASH_DMA_CURRENT_DESC_EXT,
 };
 
+/* flash_dma registers v0*/
+static const u16 flash_dma_regs_v0[] = {
+	[FLASH_DMA_REVISION]		= 0x00,
+	[FLASH_DMA_FIRST_DESC]		= 0x04,
+	[FLASH_DMA_CTRL]		= 0x08,
+	[FLASH_DMA_MODE]		= 0x0c,
+	[FLASH_DMA_STATUS]		= 0x10,
+	[FLASH_DMA_INTERRUPT_DESC]	= 0x14,
+	[FLASH_DMA_ERROR_STATUS]	= 0x18,
+	[FLASH_DMA_CURRENT_DESC]	= 0x1c,
+};
+
 /* flash_dma registers v1*/
 static const u16 flash_dma_regs_v1[] = {
 	[FLASH_DMA_REVISION]		= 0x00,
@@ -597,6 +609,8 @@ static void brcmnand_flash_dma_revision_init(struct brcmnand_controller *ctrl)
 	/* flash_dma register offsets */
 	if (ctrl->nand_version >= 0x0703)
 		ctrl->flash_dma_offsets = flash_dma_regs_v4;
+	else if (ctrl->nand_version == 0x0602)
+		ctrl->flash_dma_offsets = flash_dma_regs_v0;
 	else
 		ctrl->flash_dma_offsets = flash_dma_regs_v1;
 }
@@ -918,7 +932,7 @@ static inline void disable_ctrl_irqs(struct brcmnand_controller *ctrl)
 		return;
 
 	if (has_flash_dma(ctrl)) {
-		ctrl->flash_dma_base = 0;
+		ctrl->flash_dma_base = NULL;
 		disable_irq(ctrl->dma_irq);
 	}
 
@@ -1673,8 +1687,11 @@ static void brcmnand_dma_run(struct brcmnand_host *host, dma_addr_t desc)
 
 	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC, lower_32_bits(desc));
 	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC);
-	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT, upper_32_bits(desc));
-	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT);
+	if (ctrl->nand_version > 0x0602) {
+		flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT,
+				 upper_32_bits(desc));
+		(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT);
+	}
 
 	/* Start FLASH_DMA engine */
 	ctrl->dma_pending = true;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
new file mode 100644
index 000000000000..3a36285a8d8a
--- /dev/null
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -0,0 +1,3030 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Cadence NAND flash controller driver
+ *
+ * Copyright (C) 2019 Cadence
+ *
+ * Author: Piotr Sroka <piotrs@cadence.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of_device.h>
+#include <linux/iopoll.h>
+
+/*
+ * HPNFC can work in 3 modes:
+ * -  PIO - can work in master or slave DMA
+ * -  CDMA - needs Master DMA for accessing command descriptors.
+ * -  Generic mode - can use only slave DMA.
+ * CDMA and PIO modes can be used to execute only base commands.
+ * Generic mode can be used to execute any command
+ * on NAND flash memory. Driver uses CDMA mode for
+ * block erasing, page reading, page programing.
+ * Generic mode is used for executing rest of commands.
+ */
+
+#define MAX_OOB_SIZE_PER_SECTOR	32
+#define MAX_ADDRESS_CYC		6
+#define MAX_ERASE_ADDRESS_CYC	3
+#define MAX_DATA_SIZE		0xFFFC
+#define DMA_DATA_SIZE_ALIGN	8
+
+/* Register definition. */
+/*
+ * Command register 0.
+ * Writing data to this register will initiate a new transaction
+ * of the NF controller.
+ */
+#define CMD_REG0			0x0000
+/* Command type field mask. */
+#define		CMD_REG0_CT		GENMASK(31, 30)
+/* Command type CDMA. */
+#define		CMD_REG0_CT_CDMA	0uL
+/* Command type generic. */
+#define		CMD_REG0_CT_GEN		3uL
+/* Command thread number field mask. */
+#define		CMD_REG0_TN		GENMASK(27, 24)
+
+/* Command register 2. */
+#define CMD_REG2			0x0008
+/* Command register 3. */
+#define CMD_REG3			0x000C
+/* Pointer register to select which thread status will be selected. */
+#define CMD_STATUS_PTR			0x0010
+/* Command status register for selected thread. */
+#define CMD_STATUS			0x0014
+
+/* Interrupt status register. */
+#define INTR_STATUS			0x0110
+#define		INTR_STATUS_SDMA_ERR	BIT(22)
+#define		INTR_STATUS_SDMA_TRIGG	BIT(21)
+#define		INTR_STATUS_UNSUPP_CMD	BIT(19)
+#define		INTR_STATUS_DDMA_TERR	BIT(18)
+#define		INTR_STATUS_CDMA_TERR	BIT(17)
+#define		INTR_STATUS_CDMA_IDL	BIT(16)
+
+/* Interrupt enable register. */
+#define INTR_ENABLE				0x0114
+#define		INTR_ENABLE_INTR_EN		BIT(31)
+#define		INTR_ENABLE_SDMA_ERR_EN		BIT(22)
+#define		INTR_ENABLE_SDMA_TRIGG_EN	BIT(21)
+#define		INTR_ENABLE_UNSUPP_CMD_EN	BIT(19)
+#define		INTR_ENABLE_DDMA_TERR_EN	BIT(18)
+#define		INTR_ENABLE_CDMA_TERR_EN	BIT(17)
+#define		INTR_ENABLE_CDMA_IDLE_EN	BIT(16)
+
+/* Controller internal state. */
+#define CTRL_STATUS				0x0118
+#define		CTRL_STATUS_INIT_COMP		BIT(9)
+#define		CTRL_STATUS_CTRL_BUSY		BIT(8)
+
+/* Command Engine threads state. */
+#define TRD_STATUS				0x0120
+
+/* Command Engine interrupt thread error status. */
+#define TRD_ERR_INT_STATUS			0x0128
+/* Command Engine interrupt thread error enable. */
+#define TRD_ERR_INT_STATUS_EN			0x0130
+/* Command Engine interrupt thread complete status. */
+#define TRD_COMP_INT_STATUS			0x0138
+
+/*
+ * Transfer config 0 register.
+ * Configures data transfer parameters.
+ */
+#define TRAN_CFG_0				0x0400
+/* Offset value from the beginning of the page. */
+#define		TRAN_CFG_0_OFFSET		GENMASK(31, 16)
+/* Numbers of sectors to transfer within singlNF device's page. */
+#define		TRAN_CFG_0_SEC_CNT		GENMASK(7, 0)
+
+/*
+ * Transfer config 1 register.
+ * Configures data transfer parameters.
+ */
+#define TRAN_CFG_1				0x0404
+/* Size of last data sector. */
+#define		TRAN_CFG_1_LAST_SEC_SIZE	GENMASK(31, 16)
+/* Size of not-last data sector. */
+#define		TRAN_CFG_1_SECTOR_SIZE		GENMASK(15, 0)
+
+/* ECC engine configuration register 0. */
+#define ECC_CONFIG_0				0x0428
+/* Correction strength. */
+#define		ECC_CONFIG_0_CORR_STR		GENMASK(10, 8)
+/* Enable erased pages detection mechanism. */
+#define		ECC_CONFIG_0_ERASE_DET_EN	BIT(1)
+/* Enable controller ECC check bits generation and correction. */
+#define		ECC_CONFIG_0_ECC_EN		BIT(0)
+
+/* ECC engine configuration register 1. */
+#define ECC_CONFIG_1				0x042C
+
+/* Multiplane settings register. */
+#define MULTIPLANE_CFG				0x0434
+/* Cache operation settings. */
+#define CACHE_CFG				0x0438
+
+/* DMA settings register. */
+#define DMA_SETINGS				0x043C
+/* Enable SDMA error report on access unprepared slave DMA interface. */
+#define		DMA_SETINGS_SDMA_ERR_RSP	BIT(17)
+
+/* Transferred data block size for the slave DMA module. */
+#define SDMA_SIZE				0x0440
+
+/* Thread number associated with transferred data block
+ * for the slave DMA module.
+ */
+#define SDMA_TRD_NUM				0x0444
+/* Thread number mask. */
+#define		SDMA_TRD_NUM_SDMA_TRD		GENMASK(2, 0)
+
+#define CONTROL_DATA_CTRL			0x0494
+/* Thread number mask. */
+#define		CONTROL_DATA_CTRL_SIZE		GENMASK(15, 0)
+
+#define CTRL_VERSION				0x800
+#define		CTRL_VERSION_REV		GENMASK(7, 0)
+
+/* Available hardware features of the controller. */
+#define CTRL_FEATURES				0x804
+/* Support for NV-DDR2/3 work mode. */
+#define		CTRL_FEATURES_NVDDR_2_3		BIT(28)
+/* Support for NV-DDR work mode. */
+#define		CTRL_FEATURES_NVDDR		BIT(27)
+/* Support for asynchronous work mode. */
+#define		CTRL_FEATURES_ASYNC		BIT(26)
+/* Support for asynchronous work mode. */
+#define		CTRL_FEATURES_N_BANKS		GENMASK(25, 24)
+/* Slave and Master DMA data width. */
+#define		CTRL_FEATURES_DMA_DWITH64	BIT(21)
+/* Availability of Control Data feature.*/
+#define		CTRL_FEATURES_CONTROL_DATA	BIT(10)
+
+/* BCH Engine identification register 0 - correction strengths. */
+#define BCH_CFG_0				0x838
+#define		BCH_CFG_0_CORR_CAP_0		GENMASK(7, 0)
+#define		BCH_CFG_0_CORR_CAP_1		GENMASK(15, 8)
+#define		BCH_CFG_0_CORR_CAP_2		GENMASK(23, 16)
+#define		BCH_CFG_0_CORR_CAP_3		GENMASK(31, 24)
+
+/* BCH Engine identification register 1 - correction strengths. */
+#define BCH_CFG_1				0x83C
+#define		BCH_CFG_1_CORR_CAP_4		GENMASK(7, 0)
+#define		BCH_CFG_1_CORR_CAP_5		GENMASK(15, 8)
+#define		BCH_CFG_1_CORR_CAP_6		GENMASK(23, 16)
+#define		BCH_CFG_1_CORR_CAP_7		GENMASK(31, 24)
+
+/* BCH Engine identification register 2 - sector sizes. */
+#define BCH_CFG_2				0x840
+#define		BCH_CFG_2_SECT_0		GENMASK(15, 0)
+#define		BCH_CFG_2_SECT_1		GENMASK(31, 16)
+
+/* BCH Engine identification register 3. */
+#define BCH_CFG_3				0x844
+
+/* Ready/Busy# line status. */
+#define RBN_SETINGS				0x1004
+
+/* Common settings. */
+#define COMMON_SET				0x1008
+/* 16 bit device connected to the NAND Flash interface. */
+#define		COMMON_SET_DEVICE_16BIT		BIT(8)
+
+/* Skip_bytes registers. */
+#define SKIP_BYTES_CONF				0x100C
+#define		SKIP_BYTES_MARKER_VALUE		GENMASK(31, 16)
+#define		SKIP_BYTES_NUM_OF_BYTES		GENMASK(7, 0)
+
+#define SKIP_BYTES_OFFSET			0x1010
+#define		 SKIP_BYTES_OFFSET_VALUE	GENMASK(23, 0)
+
+/* Timings configuration. */
+#define ASYNC_TOGGLE_TIMINGS			0x101c
+#define		ASYNC_TOGGLE_TIMINGS_TRH	GENMASK(28, 24)
+#define		ASYNC_TOGGLE_TIMINGS_TRP	GENMASK(20, 16)
+#define		ASYNC_TOGGLE_TIMINGS_TWH	GENMASK(12, 8)
+#define		ASYNC_TOGGLE_TIMINGS_TWP	GENMASK(4, 0)
+
+#define	TIMINGS0				0x1024
+#define		TIMINGS0_TADL			GENMASK(31, 24)
+#define		TIMINGS0_TCCS			GENMASK(23, 16)
+#define		TIMINGS0_TWHR			GENMASK(15, 8)
+#define		TIMINGS0_TRHW			GENMASK(7, 0)
+
+#define	TIMINGS1				0x1028
+#define		TIMINGS1_TRHZ			GENMASK(31, 24)
+#define		TIMINGS1_TWB			GENMASK(23, 16)
+#define		TIMINGS1_TVDLY			GENMASK(7, 0)
+
+#define	TIMINGS2				0x102c
+#define		TIMINGS2_TFEAT			GENMASK(25, 16)
+#define		TIMINGS2_CS_HOLD_TIME		GENMASK(13, 8)
+#define		TIMINGS2_CS_SETUP_TIME		GENMASK(5, 0)
+
+/* Configuration of the resynchronization of slave DLL of PHY. */
+#define DLL_PHY_CTRL				0x1034
+#define		DLL_PHY_CTRL_DLL_RST_N		BIT(24)
+#define		DLL_PHY_CTRL_EXTENDED_WR_MODE	BIT(17)
+#define		DLL_PHY_CTRL_EXTENDED_RD_MODE	BIT(16)
+#define		DLL_PHY_CTRL_RS_HIGH_WAIT_CNT	GENMASK(11, 8)
+#define		DLL_PHY_CTRL_RS_IDLE_CNT	GENMASK(7, 0)
+
+/* Register controlling DQ related timing. */
+#define PHY_DQ_TIMING				0x2000
+/* Register controlling DSQ related timing.  */
+#define PHY_DQS_TIMING				0x2004
+#define		PHY_DQS_TIMING_DQS_SEL_OE_END	GENMASK(3, 0)
+#define		PHY_DQS_TIMING_PHONY_DQS_SEL	BIT(16)
+#define		PHY_DQS_TIMING_USE_PHONY_DQS	BIT(20)
+
+/* Register controlling the gate and loopback control related timing. */
+#define PHY_GATE_LPBK_CTRL			0x2008
+#define		PHY_GATE_LPBK_CTRL_RDS		GENMASK(24, 19)
+
+/* Register holds the control for the master DLL logic. */
+#define PHY_DLL_MASTER_CTRL			0x200C
+#define		PHY_DLL_MASTER_CTRL_BYPASS_MODE	BIT(23)
+
+/* Register holds the control for the slave DLL logic. */
+#define PHY_DLL_SLAVE_CTRL			0x2010
+
+/* This register handles the global control settings for the PHY. */
+#define PHY_CTRL				0x2080
+#define		PHY_CTRL_SDR_DQS		BIT(14)
+#define		PHY_CTRL_PHONY_DQS		GENMASK(9, 4)
+
+/*
+ * This register handles the global control settings
+ * for the termination selects for reads.
+ */
+#define PHY_TSEL				0x2084
+
+/* Generic command layout. */
+#define GCMD_LAY_CS			GENMASK_ULL(11, 8)
+/*
+ * This bit informs the minicotroller if it has to wait for tWB
+ * after sending the last CMD/ADDR/DATA in the sequence.
+ */
+#define GCMD_LAY_TWB			BIT_ULL(6)
+/* Type of generic instruction. */
+#define GCMD_LAY_INSTR			GENMASK_ULL(5, 0)
+
+/* Generic CMD sequence type. */
+#define		GCMD_LAY_INSTR_CMD	0
+/* Generic ADDR sequence type. */
+#define		GCMD_LAY_INSTR_ADDR	1
+/* Generic data transfer sequence type. */
+#define		GCMD_LAY_INSTR_DATA	2
+
+/* Input part of generic command type of input is command. */
+#define GCMD_LAY_INPUT_CMD		GENMASK_ULL(23, 16)
+
+/* Generic command address sequence - address fields. */
+#define GCMD_LAY_INPUT_ADDR		GENMASK_ULL(63, 16)
+/* Generic command address sequence - address size. */
+#define GCMD_LAY_INPUT_ADDR_SIZE	GENMASK_ULL(13, 11)
+
+/* Transfer direction field of generic command data sequence. */
+#define GCMD_DIR			BIT_ULL(11)
+/* Read transfer direction of generic command data sequence. */
+#define		GCMD_DIR_READ		0
+/* Write transfer direction of generic command data sequence. */
+#define		GCMD_DIR_WRITE		1
+
+/* ECC enabled flag of generic command data sequence - ECC enabled. */
+#define GCMD_ECC_EN			BIT_ULL(12)
+/* Generic command data sequence - sector size. */
+#define GCMD_SECT_SIZE			GENMASK_ULL(31, 16)
+/* Generic command data sequence - sector count. */
+#define GCMD_SECT_CNT			GENMASK_ULL(39, 32)
+/* Generic command data sequence - last sector size. */
+#define GCMD_LAST_SIZE			GENMASK_ULL(55, 40)
+
+/* CDMA descriptor fields. */
+/* Erase command type of CDMA descriptor. */
+#define CDMA_CT_ERASE		0x1000
+/* Program page command type of CDMA descriptor. */
+#define CDMA_CT_WR		0x2100
+/* Read page command type of CDMA descriptor. */
+#define CDMA_CT_RD		0x2200
+
+/* Flash pointer memory shift. */
+#define CDMA_CFPTR_MEM_SHIFT	24
+/* Flash pointer memory mask. */
+#define CDMA_CFPTR_MEM		GENMASK(26, 24)
+
+/*
+ * Command DMA descriptor flags. If set causes issue interrupt after
+ * the completion of descriptor processing.
+ */
+#define CDMA_CF_INT		BIT(8)
+/*
+ * Command DMA descriptor flags - the next descriptor
+ * address field is valid and descriptor processing should continue.
+ */
+#define CDMA_CF_CONT		BIT(9)
+/* DMA master flag of command DMA descriptor. */
+#define CDMA_CF_DMA_MASTER	BIT(10)
+
+/* Operation complete status of command descriptor. */
+#define CDMA_CS_COMP		BIT(15)
+/* Operation complete status of command descriptor. */
+/* Command descriptor status - operation fail. */
+#define CDMA_CS_FAIL		BIT(14)
+/* Command descriptor status - page erased. */
+#define CDMA_CS_ERP		BIT(11)
+/* Command descriptor status - timeout occurred. */
+#define CDMA_CS_TOUT		BIT(10)
+/*
+ * Maximum amount of correction applied to one ECC sector.
+ * It is part of command descriptor status.
+ */
+#define CDMA_CS_MAXERR		GENMASK(9, 2)
+/* Command descriptor status - uncorrectable ECC error. */
+#define CDMA_CS_UNCE		BIT(1)
+/* Command descriptor status - descriptor error. */
+#define CDMA_CS_ERR		BIT(0)
+
+/* Status of operation - OK. */
+#define STAT_OK			0
+/* Status of operation - FAIL. */
+#define STAT_FAIL		2
+/* Status of operation - uncorrectable ECC error. */
+#define STAT_ECC_UNCORR		3
+/* Status of operation - page erased. */
+#define STAT_ERASED		5
+/* Status of operation - correctable ECC error. */
+#define STAT_ECC_CORR		6
+/* Status of operation - unsuspected state. */
+#define STAT_UNKNOWN		7
+/* Status of operation - operation is not completed yet. */
+#define STAT_BUSY		0xFF
+
+#define BCH_MAX_NUM_CORR_CAPS		8
+#define BCH_MAX_NUM_SECTOR_SIZES	2
+
+struct cadence_nand_timings {
+	u32 async_toggle_timings;
+	u32 timings0;
+	u32 timings1;
+	u32 timings2;
+	u32 dll_phy_ctrl;
+	u32 phy_ctrl;
+	u32 phy_dqs_timing;
+	u32 phy_gate_lpbk_ctrl;
+};
+
+/* Command DMA descriptor. */
+struct cadence_nand_cdma_desc {
+	/* Next descriptor address. */
+	u64 next_pointer;
+
+	/* Flash address is a 32-bit address comprising of BANK and ROW ADDR. */
+	u32 flash_pointer;
+	/*field appears in HPNFC version 13*/
+	u16 bank;
+	u16 rsvd0;
+
+	/* Operation the controller needs to perform. */
+	u16 command_type;
+	u16 rsvd1;
+	/* Flags for operation of this command. */
+	u16 command_flags;
+	u16 rsvd2;
+
+	/* System/host memory address required for data DMA commands. */
+	u64 memory_pointer;
+
+	/* Status of operation. */
+	u32 status;
+	u32 rsvd3;
+
+	/* Address pointer to sync buffer location. */
+	u64 sync_flag_pointer;
+
+	/* Controls the buffer sync mechanism. */
+	u32 sync_arguments;
+	u32 rsvd4;
+
+	/* Control data pointer. */
+	u64 ctrl_data_ptr;
+};
+
+/* Interrupt status. */
+struct cadence_nand_irq_status {
+	/* Thread operation complete status. */
+	u32 trd_status;
+	/* Thread operation error. */
+	u32 trd_error;
+	/* Controller status. */
+	u32 status;
+};
+
+/* Cadence NAND flash controller capabilities get from driver data. */
+struct cadence_nand_dt_devdata {
+	/* Skew value of the output signals of the NAND Flash interface. */
+	u32 if_skew;
+	/* It informs if slave DMA interface is connected to DMA engine. */
+	unsigned int has_dma:1;
+};
+
+/* Cadence NAND flash controller capabilities read from registers. */
+struct cdns_nand_caps {
+	/* Maximum number of banks supported by hardware. */
+	u8 max_banks;
+	/* Slave and Master DMA data width in bytes (4 or 8). */
+	u8 data_dma_width;
+	/* Control Data feature supported. */
+	bool data_control_supp;
+	/* Is PHY type DLL. */
+	bool is_phy_type_dll;
+};
+
+struct cdns_nand_ctrl {
+	struct device *dev;
+	struct nand_controller controller;
+	struct cadence_nand_cdma_desc *cdma_desc;
+	/* IP capability. */
+	const struct cadence_nand_dt_devdata *caps1;
+	struct cdns_nand_caps caps2;
+	u8 ctrl_rev;
+	dma_addr_t dma_cdma_desc;
+	u8 *buf;
+	u32 buf_size;
+	u8 curr_corr_str_idx;
+
+	/* Register interface. */
+	void __iomem *reg;
+
+	struct {
+		void __iomem *virt;
+		dma_addr_t dma;
+	} io;
+
+	int irq;
+	/* Interrupts that have happened. */
+	struct cadence_nand_irq_status irq_status;
+	/* Interrupts we are waiting for. */
+	struct cadence_nand_irq_status irq_mask;
+	struct completion complete;
+	/* Protect irq_mask and irq_status. */
+	spinlock_t irq_lock;
+
+	int ecc_strengths[BCH_MAX_NUM_CORR_CAPS];
+	struct nand_ecc_step_info ecc_stepinfos[BCH_MAX_NUM_SECTOR_SIZES];
+	struct nand_ecc_caps ecc_caps;
+
+	int curr_trans_type;
+
+	struct dma_chan *dmac;
+
+	u32 nf_clk_rate;
+	/*
+	 * Estimated Board delay. The value includes the total
+	 * round trip delay for the signals and is used for deciding on values
+	 * associated with data read capture.
+	 */
+	u32 board_delay;
+
+	struct nand_chip *selected_chip;
+
+	unsigned long assigned_cs;
+	struct list_head chips;
+};
+
+struct cdns_nand_chip {
+	struct cadence_nand_timings timings;
+	struct nand_chip chip;
+	u8 nsels;
+	struct list_head node;
+
+	/*
+	 * part of oob area of NAND flash memory page.
+	 * This part is available for user to read or write.
+	 */
+	u32 avail_oob_size;
+
+	/* Sector size. There are few sectors per mtd->writesize */
+	u32 sector_size;
+	u32 sector_count;
+
+	/* Offset of BBM. */
+	u8 bbm_offs;
+	/* Number of bytes reserved for BBM. */
+	u8 bbm_len;
+	/* ECC strength index. */
+	u8 corr_str_idx;
+
+	u8 cs[];
+};
+
+struct ecc_info {
+	int (*calc_ecc_bytes)(int step_size, int strength);
+	int max_step_size;
+};
+
+static inline struct
+cdns_nand_chip *to_cdns_nand_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct cdns_nand_chip, chip);
+}
+
+static inline struct
+cdns_nand_ctrl *to_cdns_nand_ctrl(struct nand_controller *controller)
+{
+	return container_of(controller, struct cdns_nand_ctrl, controller);
+}
+
+static bool
+cadence_nand_dma_buf_ok(struct cdns_nand_ctrl *cdns_ctrl, const void *buf,
+			u32 buf_len)
+{
+	u8 data_dma_width = cdns_ctrl->caps2.data_dma_width;
+
+	return buf && virt_addr_valid(buf) &&
+		likely(IS_ALIGNED((uintptr_t)buf, data_dma_width)) &&
+		likely(IS_ALIGNED(buf_len, DMA_DATA_SIZE_ALIGN));
+}
+
+static int cadence_nand_wait_for_value(struct cdns_nand_ctrl *cdns_ctrl,
+				       u32 reg_offset, u32 timeout_us,
+				       u32 mask, bool is_clear)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_relaxed_poll_timeout(cdns_ctrl->reg + reg_offset,
+					 val, !(val & mask) == is_clear,
+					 10, timeout_us);
+
+	if (ret < 0) {
+		dev_err(cdns_ctrl->dev,
+			"Timeout while waiting for reg %x with mask %x is clear %d\n",
+			reg_offset, mask, is_clear);
+	}
+
+	return ret;
+}
+
+static int cadence_nand_set_ecc_enable(struct cdns_nand_ctrl *cdns_ctrl,
+				       bool enable)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+
+	if (enable)
+		reg |= ECC_CONFIG_0_ECC_EN;
+	else
+		reg &= ~ECC_CONFIG_0_ECC_EN;
+
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+
+	return 0;
+}
+
+static void cadence_nand_set_ecc_strength(struct cdns_nand_ctrl *cdns_ctrl,
+					  u8 corr_str_idx)
+{
+	u32 reg;
+
+	if (cdns_ctrl->curr_corr_str_idx == corr_str_idx)
+		return;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+	reg &= ~ECC_CONFIG_0_CORR_STR;
+	reg |= FIELD_PREP(ECC_CONFIG_0_CORR_STR, corr_str_idx);
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+
+	cdns_ctrl->curr_corr_str_idx = corr_str_idx;
+}
+
+static int cadence_nand_get_ecc_strength_idx(struct cdns_nand_ctrl *cdns_ctrl,
+					     u8 strength)
+{
+	int i, corr_str_idx = -1;
+
+	for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) {
+		if (cdns_ctrl->ecc_strengths[i] == strength) {
+			corr_str_idx = i;
+			break;
+		}
+	}
+
+	return corr_str_idx;
+}
+
+static int cadence_nand_set_skip_marker_val(struct cdns_nand_ctrl *cdns_ctrl,
+					    u16 marker_value)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF);
+	reg &= ~SKIP_BYTES_MARKER_VALUE;
+	reg |= FIELD_PREP(SKIP_BYTES_MARKER_VALUE,
+			  marker_value);
+
+	writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF);
+
+	return 0;
+}
+
+static int cadence_nand_set_skip_bytes_conf(struct cdns_nand_ctrl *cdns_ctrl,
+					    u8 num_of_bytes,
+					    u32 offset_value,
+					    int enable)
+{
+	u32 reg, skip_bytes_offset;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	if (!enable) {
+		num_of_bytes = 0;
+		offset_value = 0;
+	}
+
+	reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF);
+	reg &= ~SKIP_BYTES_NUM_OF_BYTES;
+	reg |= FIELD_PREP(SKIP_BYTES_NUM_OF_BYTES,
+			  num_of_bytes);
+	skip_bytes_offset = FIELD_PREP(SKIP_BYTES_OFFSET_VALUE,
+				       offset_value);
+
+	writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF);
+	writel_relaxed(skip_bytes_offset, cdns_ctrl->reg + SKIP_BYTES_OFFSET);
+
+	return 0;
+}
+
+/* Functions enables/disables hardware detection of erased data */
+static void cadence_nand_set_erase_detection(struct cdns_nand_ctrl *cdns_ctrl,
+					     bool enable,
+					     u8 bitflips_threshold)
+{
+	u32 reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0);
+
+	if (enable)
+		reg |= ECC_CONFIG_0_ERASE_DET_EN;
+	else
+		reg &= ~ECC_CONFIG_0_ERASE_DET_EN;
+
+	writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0);
+	writel_relaxed(bitflips_threshold, cdns_ctrl->reg + ECC_CONFIG_1);
+}
+
+static int cadence_nand_set_access_width16(struct cdns_nand_ctrl *cdns_ctrl,
+					   bool bit_bus16)
+{
+	u32 reg;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	reg = readl_relaxed(cdns_ctrl->reg + COMMON_SET);
+
+	if (!bit_bus16)
+		reg &= ~COMMON_SET_DEVICE_16BIT;
+	else
+		reg |= COMMON_SET_DEVICE_16BIT;
+	writel_relaxed(reg, cdns_ctrl->reg + COMMON_SET);
+
+	return 0;
+}
+
+static void
+cadence_nand_clear_interrupt(struct cdns_nand_ctrl *cdns_ctrl,
+			     struct cadence_nand_irq_status *irq_status)
+{
+	writel_relaxed(irq_status->status, cdns_ctrl->reg + INTR_STATUS);
+	writel_relaxed(irq_status->trd_status,
+		       cdns_ctrl->reg + TRD_COMP_INT_STATUS);
+	writel_relaxed(irq_status->trd_error,
+		       cdns_ctrl->reg + TRD_ERR_INT_STATUS);
+}
+
+static void
+cadence_nand_read_int_status(struct cdns_nand_ctrl *cdns_ctrl,
+			     struct cadence_nand_irq_status *irq_status)
+{
+	irq_status->status = readl_relaxed(cdns_ctrl->reg + INTR_STATUS);
+	irq_status->trd_status = readl_relaxed(cdns_ctrl->reg
+					       + TRD_COMP_INT_STATUS);
+	irq_status->trd_error = readl_relaxed(cdns_ctrl->reg
+					      + TRD_ERR_INT_STATUS);
+}
+
+static u32 irq_detected(struct cdns_nand_ctrl *cdns_ctrl,
+			struct cadence_nand_irq_status *irq_status)
+{
+	cadence_nand_read_int_status(cdns_ctrl, irq_status);
+
+	return irq_status->status || irq_status->trd_status ||
+		irq_status->trd_error;
+}
+
+static void cadence_nand_reset_irq(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdns_ctrl->irq_lock, flags);
+	memset(&cdns_ctrl->irq_status, 0, sizeof(cdns_ctrl->irq_status));
+	memset(&cdns_ctrl->irq_mask, 0, sizeof(cdns_ctrl->irq_mask));
+	spin_unlock_irqrestore(&cdns_ctrl->irq_lock, flags);
+}
+
+/*
+ * This is the interrupt service routine. It handles all interrupts
+ * sent to this device.
+ */
+static irqreturn_t cadence_nand_isr(int irq, void *dev_id)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = dev_id;
+	struct cadence_nand_irq_status irq_status;
+	irqreturn_t result = IRQ_NONE;
+
+	spin_lock(&cdns_ctrl->irq_lock);
+
+	if (irq_detected(cdns_ctrl, &irq_status)) {
+		/* Handle interrupt. */
+		/* First acknowledge it. */
+		cadence_nand_clear_interrupt(cdns_ctrl, &irq_status);
+		/* Status in the device context for someone to read. */
+		cdns_ctrl->irq_status.status |= irq_status.status;
+		cdns_ctrl->irq_status.trd_status |= irq_status.trd_status;
+		cdns_ctrl->irq_status.trd_error |= irq_status.trd_error;
+		/* Notify anyone who cares that it happened. */
+		complete(&cdns_ctrl->complete);
+		/* Tell the OS that we've handled this. */
+		result = IRQ_HANDLED;
+	}
+	spin_unlock(&cdns_ctrl->irq_lock);
+
+	return result;
+}
+
+static void cadence_nand_set_irq_mask(struct cdns_nand_ctrl *cdns_ctrl,
+				      struct cadence_nand_irq_status *irq_mask)
+{
+	writel_relaxed(INTR_ENABLE_INTR_EN | irq_mask->status,
+		       cdns_ctrl->reg + INTR_ENABLE);
+
+	writel_relaxed(irq_mask->trd_error,
+		       cdns_ctrl->reg + TRD_ERR_INT_STATUS_EN);
+}
+
+static void
+cadence_nand_wait_for_irq(struct cdns_nand_ctrl *cdns_ctrl,
+			  struct cadence_nand_irq_status *irq_mask,
+			  struct cadence_nand_irq_status *irq_status)
+{
+	unsigned long timeout = msecs_to_jiffies(10000);
+	unsigned long time_left;
+
+	time_left = wait_for_completion_timeout(&cdns_ctrl->complete,
+						timeout);
+
+	*irq_status = cdns_ctrl->irq_status;
+	if (time_left == 0) {
+		/* Timeout error. */
+		dev_err(cdns_ctrl->dev, "timeout occurred:\n");
+		dev_err(cdns_ctrl->dev, "\tstatus = 0x%x, mask = 0x%x\n",
+			irq_status->status, irq_mask->status);
+		dev_err(cdns_ctrl->dev,
+			"\ttrd_status = 0x%x, trd_status mask = 0x%x\n",
+			irq_status->trd_status, irq_mask->trd_status);
+		dev_err(cdns_ctrl->dev,
+			"\t trd_error = 0x%x, trd_error mask = 0x%x\n",
+			irq_status->trd_error, irq_mask->trd_error);
+	}
+}
+
+/* Execute generic command on NAND controller. */
+static int cadence_nand_generic_cmd_send(struct cdns_nand_ctrl *cdns_ctrl,
+					 u8 chip_nr,
+					 u64 mini_ctrl_cmd)
+{
+	u32 mini_ctrl_cmd_l, mini_ctrl_cmd_h, reg;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_CS, chip_nr);
+	mini_ctrl_cmd_l = mini_ctrl_cmd & 0xFFFFFFFF;
+	mini_ctrl_cmd_h = mini_ctrl_cmd >> 32;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_reset_irq(cdns_ctrl);
+
+	writel_relaxed(mini_ctrl_cmd_l, cdns_ctrl->reg + CMD_REG2);
+	writel_relaxed(mini_ctrl_cmd_h, cdns_ctrl->reg + CMD_REG3);
+
+	/* Select generic command. */
+	reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_GEN);
+	/* Thread number. */
+	reg |= FIELD_PREP(CMD_REG0_TN, 0);
+
+	/* Issue command. */
+	writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0);
+
+	return 0;
+}
+
+/* Wait for data on slave DMA interface. */
+static int cadence_nand_wait_on_sdma(struct cdns_nand_ctrl *cdns_ctrl,
+				     u8 *out_sdma_trd,
+				     u32 *out_sdma_size)
+{
+	struct cadence_nand_irq_status irq_mask, irq_status;
+
+	irq_mask.trd_status = 0;
+	irq_mask.trd_error = 0;
+	irq_mask.status = INTR_STATUS_SDMA_TRIGG
+		| INTR_STATUS_SDMA_ERR
+		| INTR_STATUS_UNSUPP_CMD;
+
+	cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask);
+	cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status);
+	if (irq_status.status == 0) {
+		dev_err(cdns_ctrl->dev, "Timeout while waiting for SDMA\n");
+		return -ETIMEDOUT;
+	}
+
+	if (irq_status.status & INTR_STATUS_SDMA_TRIGG) {
+		*out_sdma_size = readl_relaxed(cdns_ctrl->reg + SDMA_SIZE);
+		*out_sdma_trd  = readl_relaxed(cdns_ctrl->reg + SDMA_TRD_NUM);
+		*out_sdma_trd =
+			FIELD_GET(SDMA_TRD_NUM_SDMA_TRD, *out_sdma_trd);
+	} else {
+		dev_err(cdns_ctrl->dev, "SDMA error - irq_status %x\n",
+			irq_status.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void cadence_nand_get_caps(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	u32  reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + CTRL_FEATURES);
+
+	cdns_ctrl->caps2.max_banks = 1 << FIELD_GET(CTRL_FEATURES_N_BANKS, reg);
+
+	if (FIELD_GET(CTRL_FEATURES_DMA_DWITH64, reg))
+		cdns_ctrl->caps2.data_dma_width = 8;
+	else
+		cdns_ctrl->caps2.data_dma_width = 4;
+
+	if (reg & CTRL_FEATURES_CONTROL_DATA)
+		cdns_ctrl->caps2.data_control_supp = true;
+
+	if (reg & (CTRL_FEATURES_NVDDR_2_3
+		   | CTRL_FEATURES_NVDDR))
+		cdns_ctrl->caps2.is_phy_type_dll = true;
+}
+
+/* Prepare CDMA descriptor. */
+static void
+cadence_nand_cdma_desc_prepare(struct cdns_nand_ctrl *cdns_ctrl,
+			       char nf_mem, u32 flash_ptr, char *mem_ptr,
+			       char *ctrl_data_ptr, u16 ctype)
+{
+	struct cadence_nand_cdma_desc *cdma_desc = cdns_ctrl->cdma_desc;
+
+	memset(cdma_desc, 0, sizeof(struct cadence_nand_cdma_desc));
+
+	/* Set fields for one descriptor. */
+	cdma_desc->flash_pointer = flash_ptr;
+	if (cdns_ctrl->ctrl_rev >= 13)
+		cdma_desc->bank = nf_mem;
+	else
+		cdma_desc->flash_pointer |= (nf_mem << CDMA_CFPTR_MEM_SHIFT);
+
+	cdma_desc->command_flags |= CDMA_CF_DMA_MASTER;
+	cdma_desc->command_flags  |= CDMA_CF_INT;
+
+	cdma_desc->memory_pointer = (uintptr_t)mem_ptr;
+	cdma_desc->status = 0;
+	cdma_desc->sync_flag_pointer = 0;
+	cdma_desc->sync_arguments = 0;
+
+	cdma_desc->command_type = ctype;
+	cdma_desc->ctrl_data_ptr = (uintptr_t)ctrl_data_ptr;
+}
+
+static u8 cadence_nand_check_desc_error(struct cdns_nand_ctrl *cdns_ctrl,
+					u32 desc_status)
+{
+	if (desc_status & CDMA_CS_ERP)
+		return STAT_ERASED;
+
+	if (desc_status & CDMA_CS_UNCE)
+		return STAT_ECC_UNCORR;
+
+	if (desc_status & CDMA_CS_ERR) {
+		dev_err(cdns_ctrl->dev, ":CDMA desc error flag detected.\n");
+		return STAT_FAIL;
+	}
+
+	if (FIELD_GET(CDMA_CS_MAXERR, desc_status))
+		return STAT_ECC_CORR;
+
+	return STAT_FAIL;
+}
+
+static int cadence_nand_cdma_finish(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct cadence_nand_cdma_desc *desc_ptr = cdns_ctrl->cdma_desc;
+	u8 status = STAT_BUSY;
+
+	if (desc_ptr->status & CDMA_CS_FAIL) {
+		status = cadence_nand_check_desc_error(cdns_ctrl,
+						       desc_ptr->status);
+		dev_err(cdns_ctrl->dev, ":CDMA error %x\n", desc_ptr->status);
+	} else if (desc_ptr->status & CDMA_CS_COMP) {
+		/* Descriptor finished with no errors. */
+		if (desc_ptr->command_flags & CDMA_CF_CONT) {
+			dev_info(cdns_ctrl->dev, "DMA unsupported flag is set");
+			status = STAT_UNKNOWN;
+		} else {
+			/* Last descriptor.  */
+			status = STAT_OK;
+		}
+	}
+
+	return status;
+}
+
+static int cadence_nand_cdma_send(struct cdns_nand_ctrl *cdns_ctrl,
+				  u8 thread)
+{
+	u32 reg;
+	int status;
+
+	/* Wait for thread ready. */
+	status = cadence_nand_wait_for_value(cdns_ctrl, TRD_STATUS,
+					     1000000,
+					     BIT(thread), true);
+	if (status)
+		return status;
+
+	cadence_nand_reset_irq(cdns_ctrl);
+
+	writel_relaxed((u32)cdns_ctrl->dma_cdma_desc,
+		       cdns_ctrl->reg + CMD_REG2);
+	writel_relaxed(0, cdns_ctrl->reg + CMD_REG3);
+
+	/* Select CDMA mode. */
+	reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_CDMA);
+	/* Thread number. */
+	reg |= FIELD_PREP(CMD_REG0_TN, thread);
+	/* Issue command. */
+	writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0);
+
+	return 0;
+}
+
+/* Send SDMA command and wait for finish. */
+static u32
+cadence_nand_cdma_send_and_wait(struct cdns_nand_ctrl *cdns_ctrl,
+				u8 thread)
+{
+	struct cadence_nand_irq_status irq_mask, irq_status = {0};
+	int status;
+
+	irq_mask.trd_status = BIT(thread);
+	irq_mask.trd_error = BIT(thread);
+	irq_mask.status = INTR_STATUS_CDMA_TERR;
+
+	cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask);
+
+	status = cadence_nand_cdma_send(cdns_ctrl, thread);
+	if (status)
+		return status;
+
+	cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status);
+
+	if (irq_status.status == 0 && irq_status.trd_status == 0 &&
+	    irq_status.trd_error == 0) {
+		dev_err(cdns_ctrl->dev, "CDMA command timeout\n");
+		return -ETIMEDOUT;
+	}
+	if (irq_status.status & irq_mask.status) {
+		dev_err(cdns_ctrl->dev, "CDMA command failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * ECC size depends on configured ECC strength and on maximum supported
+ * ECC step size.
+ */
+static int cadence_nand_calc_ecc_bytes(int max_step_size, int strength)
+{
+	int nbytes = DIV_ROUND_UP(fls(8 * max_step_size) * strength, 8);
+
+	return ALIGN(nbytes, 2);
+}
+
+#define CADENCE_NAND_CALC_ECC_BYTES(max_step_size) \
+	static int \
+	cadence_nand_calc_ecc_bytes_##max_step_size(int step_size, \
+						    int strength)\
+	{\
+		return cadence_nand_calc_ecc_bytes(max_step_size, strength);\
+	}
+
+CADENCE_NAND_CALC_ECC_BYTES(256)
+CADENCE_NAND_CALC_ECC_BYTES(512)
+CADENCE_NAND_CALC_ECC_BYTES(1024)
+CADENCE_NAND_CALC_ECC_BYTES(2048)
+CADENCE_NAND_CALC_ECC_BYTES(4096)
+
+/* Function reads BCH capabilities. */
+static int cadence_nand_read_bch_caps(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct nand_ecc_caps *ecc_caps = &cdns_ctrl->ecc_caps;
+	int max_step_size = 0, nstrengths, i;
+	u32 reg;
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_0);
+	cdns_ctrl->ecc_strengths[0] = FIELD_GET(BCH_CFG_0_CORR_CAP_0, reg);
+	cdns_ctrl->ecc_strengths[1] = FIELD_GET(BCH_CFG_0_CORR_CAP_1, reg);
+	cdns_ctrl->ecc_strengths[2] = FIELD_GET(BCH_CFG_0_CORR_CAP_2, reg);
+	cdns_ctrl->ecc_strengths[3] = FIELD_GET(BCH_CFG_0_CORR_CAP_3, reg);
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_1);
+	cdns_ctrl->ecc_strengths[4] = FIELD_GET(BCH_CFG_1_CORR_CAP_4, reg);
+	cdns_ctrl->ecc_strengths[5] = FIELD_GET(BCH_CFG_1_CORR_CAP_5, reg);
+	cdns_ctrl->ecc_strengths[6] = FIELD_GET(BCH_CFG_1_CORR_CAP_6, reg);
+	cdns_ctrl->ecc_strengths[7] = FIELD_GET(BCH_CFG_1_CORR_CAP_7, reg);
+
+	reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_2);
+	cdns_ctrl->ecc_stepinfos[0].stepsize =
+		FIELD_GET(BCH_CFG_2_SECT_0, reg);
+
+	cdns_ctrl->ecc_stepinfos[1].stepsize =
+		FIELD_GET(BCH_CFG_2_SECT_1, reg);
+
+	nstrengths = 0;
+	for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) {
+		if (cdns_ctrl->ecc_strengths[i] != 0)
+			nstrengths++;
+	}
+
+	ecc_caps->nstepinfos = 0;
+	for (i = 0; i < BCH_MAX_NUM_SECTOR_SIZES; i++) {
+		/* ECC strengths are common for all step infos. */
+		cdns_ctrl->ecc_stepinfos[i].nstrengths = nstrengths;
+		cdns_ctrl->ecc_stepinfos[i].strengths =
+			cdns_ctrl->ecc_strengths;
+
+		if (cdns_ctrl->ecc_stepinfos[i].stepsize != 0)
+			ecc_caps->nstepinfos++;
+
+		if (cdns_ctrl->ecc_stepinfos[i].stepsize > max_step_size)
+			max_step_size = cdns_ctrl->ecc_stepinfos[i].stepsize;
+	}
+	ecc_caps->stepinfos = &cdns_ctrl->ecc_stepinfos[0];
+
+	switch (max_step_size) {
+	case 256:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_256;
+		break;
+	case 512:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_512;
+		break;
+	case 1024:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_1024;
+		break;
+	case 2048:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_2048;
+		break;
+	case 4096:
+		ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_4096;
+		break;
+	default:
+		dev_err(cdns_ctrl->dev,
+			"Unsupported sector size(ecc step size) %d\n",
+			max_step_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/* Hardware initialization. */
+static int cadence_nand_hw_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	int status;
+	u32 reg;
+
+	status = cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					     1000000,
+					     CTRL_STATUS_INIT_COMP, false);
+	if (status)
+		return status;
+
+	reg = readl_relaxed(cdns_ctrl->reg + CTRL_VERSION);
+	cdns_ctrl->ctrl_rev = FIELD_GET(CTRL_VERSION_REV, reg);
+
+	dev_info(cdns_ctrl->dev,
+		 "%s: cadence nand controller version reg %x\n",
+		 __func__, reg);
+
+	/* Disable cache and multiplane. */
+	writel_relaxed(0, cdns_ctrl->reg + MULTIPLANE_CFG);
+	writel_relaxed(0, cdns_ctrl->reg + CACHE_CFG);
+
+	/* Clear all interrupts. */
+	writel_relaxed(0xFFFFFFFF, cdns_ctrl->reg + INTR_STATUS);
+
+	cadence_nand_get_caps(cdns_ctrl);
+	cadence_nand_read_bch_caps(cdns_ctrl);
+
+	/*
+	 * Set IO width access to 8.
+	 * It is because during SW device discovering width access
+	 * is expected to be 8.
+	 */
+	status = cadence_nand_set_access_width16(cdns_ctrl, false);
+
+	return status;
+}
+
+#define TT_MAIN_OOB_AREAS	2
+#define TT_RAW_PAGE		3
+#define TT_BBM			4
+#define TT_MAIN_OOB_AREA_EXT	5
+
+/* Prepare size of data to transfer. */
+static void
+cadence_nand_prepare_data_size(struct nand_chip *chip,
+			       int transfer_type)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 sec_size = 0, offset = 0, sec_cnt = 1;
+	u32 last_sec_size = cdns_chip->sector_size;
+	u32 data_ctrl_size = 0;
+	u32 reg = 0;
+
+	if (cdns_ctrl->curr_trans_type == transfer_type)
+		return;
+
+	switch (transfer_type) {
+	case TT_MAIN_OOB_AREA_EXT:
+		sec_cnt = cdns_chip->sector_count;
+		sec_size = cdns_chip->sector_size;
+		data_ctrl_size = cdns_chip->avail_oob_size;
+		break;
+	case TT_MAIN_OOB_AREAS:
+		sec_cnt = cdns_chip->sector_count;
+		last_sec_size = cdns_chip->sector_size
+			+ cdns_chip->avail_oob_size;
+		sec_size = cdns_chip->sector_size;
+		break;
+	case TT_RAW_PAGE:
+		last_sec_size = mtd->writesize + mtd->oobsize;
+		break;
+	case TT_BBM:
+		offset = mtd->writesize + cdns_chip->bbm_offs;
+		last_sec_size = 8;
+		break;
+	}
+
+	reg = 0;
+	reg |= FIELD_PREP(TRAN_CFG_0_OFFSET, offset);
+	reg |= FIELD_PREP(TRAN_CFG_0_SEC_CNT, sec_cnt);
+	writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_0);
+
+	reg = 0;
+	reg |= FIELD_PREP(TRAN_CFG_1_LAST_SEC_SIZE, last_sec_size);
+	reg |= FIELD_PREP(TRAN_CFG_1_SECTOR_SIZE, sec_size);
+	writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_1);
+
+	if (cdns_ctrl->caps2.data_control_supp) {
+		reg = readl_relaxed(cdns_ctrl->reg + CONTROL_DATA_CTRL);
+		reg &= ~CONTROL_DATA_CTRL_SIZE;
+		reg |= FIELD_PREP(CONTROL_DATA_CTRL_SIZE, data_ctrl_size);
+		writel_relaxed(reg, cdns_ctrl->reg + CONTROL_DATA_CTRL);
+	}
+
+	cdns_ctrl->curr_trans_type = transfer_type;
+}
+
+static int
+cadence_nand_cdma_transfer(struct cdns_nand_ctrl *cdns_ctrl, u8 chip_nr,
+			   int page, void *buf, void *ctrl_dat, u32 buf_size,
+			   u32 ctrl_dat_size, enum dma_data_direction dir,
+			   bool with_ecc)
+{
+	dma_addr_t dma_buf, dma_ctrl_dat = 0;
+	u8 thread_nr = chip_nr;
+	int status;
+	u16 ctype;
+
+	if (dir == DMA_FROM_DEVICE)
+		ctype = CDMA_CT_RD;
+	else
+		ctype = CDMA_CT_WR;
+
+	cadence_nand_set_ecc_enable(cdns_ctrl, with_ecc);
+
+	dma_buf = dma_map_single(cdns_ctrl->dev, buf, buf_size, dir);
+	if (dma_mapping_error(cdns_ctrl->dev, dma_buf)) {
+		dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+		return -EIO;
+	}
+
+	if (ctrl_dat && ctrl_dat_size) {
+		dma_ctrl_dat = dma_map_single(cdns_ctrl->dev, ctrl_dat,
+					      ctrl_dat_size, dir);
+		if (dma_mapping_error(cdns_ctrl->dev, dma_ctrl_dat)) {
+			dma_unmap_single(cdns_ctrl->dev, dma_buf,
+					 buf_size, dir);
+			dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+			return -EIO;
+		}
+	}
+
+	cadence_nand_cdma_desc_prepare(cdns_ctrl, chip_nr, page,
+				       (void *)dma_buf, (void *)dma_ctrl_dat,
+				       ctype);
+
+	status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
+
+	dma_unmap_single(cdns_ctrl->dev, dma_buf,
+			 buf_size, dir);
+
+	if (ctrl_dat && ctrl_dat_size)
+		dma_unmap_single(cdns_ctrl->dev, dma_ctrl_dat,
+				 ctrl_dat_size, dir);
+	if (status)
+		return status;
+
+	return cadence_nand_cdma_finish(cdns_ctrl);
+}
+
+static void cadence_nand_set_timings(struct cdns_nand_ctrl *cdns_ctrl,
+				     struct cadence_nand_timings *t)
+{
+	writel_relaxed(t->async_toggle_timings,
+		       cdns_ctrl->reg + ASYNC_TOGGLE_TIMINGS);
+	writel_relaxed(t->timings0, cdns_ctrl->reg + TIMINGS0);
+	writel_relaxed(t->timings1, cdns_ctrl->reg + TIMINGS1);
+	writel_relaxed(t->timings2, cdns_ctrl->reg + TIMINGS2);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		writel_relaxed(t->dll_phy_ctrl, cdns_ctrl->reg + DLL_PHY_CTRL);
+
+	writel_relaxed(t->phy_ctrl, cdns_ctrl->reg + PHY_CTRL);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		writel_relaxed(0, cdns_ctrl->reg + PHY_TSEL);
+		writel_relaxed(2, cdns_ctrl->reg + PHY_DQ_TIMING);
+		writel_relaxed(t->phy_dqs_timing,
+			       cdns_ctrl->reg + PHY_DQS_TIMING);
+		writel_relaxed(t->phy_gate_lpbk_ctrl,
+			       cdns_ctrl->reg + PHY_GATE_LPBK_CTRL);
+		writel_relaxed(PHY_DLL_MASTER_CTRL_BYPASS_MODE,
+			       cdns_ctrl->reg + PHY_DLL_MASTER_CTRL);
+		writel_relaxed(0, cdns_ctrl->reg + PHY_DLL_SLAVE_CTRL);
+	}
+}
+
+static int cadence_nand_select_target(struct nand_chip *chip)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (chip == cdns_ctrl->selected_chip)
+		return 0;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_set_timings(cdns_ctrl, &cdns_chip->timings);
+
+	cadence_nand_set_ecc_strength(cdns_ctrl,
+				      cdns_chip->corr_str_idx);
+
+	cadence_nand_set_erase_detection(cdns_ctrl, true,
+					 chip->ecc.strength);
+
+	cdns_ctrl->curr_trans_type = -1;
+	cdns_ctrl->selected_chip = chip;
+
+	return 0;
+}
+
+static int cadence_nand_erase(struct nand_chip *chip, u32 page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	int status;
+	u8 thread_nr = cdns_chip->cs[chip->cur_cs];
+
+	cadence_nand_cdma_desc_prepare(cdns_ctrl,
+				       cdns_chip->cs[chip->cur_cs],
+				       page, NULL, NULL,
+				       CDMA_CT_ERASE);
+	status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr);
+	if (status) {
+		dev_err(cdns_ctrl->dev, "erase operation failed\n");
+		return -EIO;
+	}
+
+	status = cadence_nand_cdma_finish(cdns_ctrl);
+	if (status)
+		return status;
+
+	return 0;
+}
+
+static int cadence_nand_read_bbm(struct nand_chip *chip, int page, u8 *buf)
+{
+	int status;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	cadence_nand_prepare_data_size(chip, TT_BBM);
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	/*
+	 * Read only bad block marker from offset
+	 * defined by a memory manufacturer.
+	 */
+	status = cadence_nand_cdma_transfer(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    page, cdns_ctrl->buf, NULL,
+					    mtd->oobsize,
+					    0, DMA_FROM_DEVICE, false);
+	if (status) {
+		dev_err(cdns_ctrl->dev, "read BBM failed\n");
+		return -EIO;
+	}
+
+	memcpy(buf + cdns_chip->bbm_offs, cdns_ctrl->buf, cdns_chip->bbm_len);
+
+	return 0;
+}
+
+static int cadence_nand_write_page(struct nand_chip *chip,
+				   const u8 *buf, int oob_required,
+				   int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int status;
+	u16 marker_val = 0xFFFF;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len,
+					 mtd->writesize
+					 + cdns_chip->bbm_offs,
+					 1);
+
+	if (oob_required) {
+		marker_val = *(u16 *)(chip->oob_poi
+				      + cdns_chip->bbm_offs);
+	} else {
+		/* Set oob data to 0xFF. */
+		memset(cdns_ctrl->buf + mtd->writesize, 0xFF,
+		       cdns_chip->avail_oob_size);
+	}
+
+	cadence_nand_set_skip_marker_val(cdns_ctrl, marker_val);
+
+	cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT);
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) &&
+	    cdns_ctrl->caps2.data_control_supp) {
+		u8 *oob;
+
+		if (oob_required)
+			oob = chip->oob_poi;
+		else
+			oob = cdns_ctrl->buf + mtd->writesize;
+
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, (void *)buf, oob,
+						    mtd->writesize,
+						    cdns_chip->avail_oob_size,
+						    DMA_TO_DEVICE, true);
+		if (status) {
+			dev_err(cdns_ctrl->dev, "write page failed\n");
+			return -EIO;
+		}
+
+		return 0;
+	}
+
+	if (oob_required) {
+		/* Transfer the data to the oob area. */
+		memcpy(cdns_ctrl->buf + mtd->writesize, chip->oob_poi,
+		       cdns_chip->avail_oob_size);
+	}
+
+	memcpy(cdns_ctrl->buf, buf, mtd->writesize);
+
+	cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS);
+
+	return cadence_nand_cdma_transfer(cdns_ctrl,
+					  cdns_chip->cs[chip->cur_cs],
+					  page, cdns_ctrl->buf, NULL,
+					  mtd->writesize
+					  + cdns_chip->avail_oob_size,
+					  0, DMA_TO_DEVICE, true);
+}
+
+static int cadence_nand_write_oob(struct nand_chip *chip, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	memset(cdns_ctrl->buf, 0xFF, mtd->writesize);
+
+	return cadence_nand_write_page(chip, cdns_ctrl->buf, 1, page);
+}
+
+static int cadence_nand_write_page_raw(struct nand_chip *chip,
+				       const u8 *buf, int oob_required,
+				       int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int writesize = mtd->writesize;
+	int oobsize = mtd->oobsize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *tmp_buf = cdns_ctrl->buf;
+	int oob_skip = cdns_chip->bbm_len;
+	size_t size = writesize + oobsize;
+	int i, pos, len;
+	int status = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	/*
+	 * Fill the buffer with 0xff first except the full page transfer.
+	 * This simplifies the logic.
+	 */
+	if (!buf || !oob_required)
+		memset(tmp_buf, 0xff, size);
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	/* Arrange the buffer for syndrome payload/ecc layout. */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(tmp_buf + pos, buf, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(tmp_buf + writesize + oob_skip, buf,
+				       len);
+				buf += len;
+			}
+		}
+	}
+
+	if (oob_required) {
+		const u8 *oob = chip->oob_poi;
+		u32 oob_data_offset = (cdns_chip->sector_count - 1) *
+			(cdns_chip->sector_size + chip->ecc.bytes)
+			+ cdns_chip->sector_size + oob_skip;
+
+		/* BBM at the beginning of the OOB area. */
+		memcpy(tmp_buf + writesize, oob, oob_skip);
+
+		/* OOB free. */
+		memcpy(tmp_buf + oob_data_offset, oob,
+		       cdns_chip->avail_oob_size);
+		oob += cdns_chip->avail_oob_size;
+
+		/* OOB ECC. */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			if (i == (ecc_steps - 1))
+				pos += cdns_chip->avail_oob_size;
+
+			len = ecc_bytes;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(tmp_buf + pos, oob, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(tmp_buf + writesize + oob_skip, oob,
+				       len);
+				oob += len;
+			}
+		}
+	}
+
+	cadence_nand_prepare_data_size(chip, TT_RAW_PAGE);
+
+	return cadence_nand_cdma_transfer(cdns_ctrl,
+					  cdns_chip->cs[chip->cur_cs],
+					  page, cdns_ctrl->buf, NULL,
+					  mtd->writesize +
+					  mtd->oobsize,
+					  0, DMA_TO_DEVICE, false);
+}
+
+static int cadence_nand_write_oob_raw(struct nand_chip *chip,
+				      int page)
+{
+	return cadence_nand_write_page_raw(chip, NULL, true, page);
+}
+
+static int cadence_nand_read_page(struct nand_chip *chip,
+				  u8 *buf, int oob_required, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int status = 0;
+	int ecc_err_count = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len,
+					 mtd->writesize
+					 + cdns_chip->bbm_offs, 1);
+
+	/*
+	 * If data buffer can be accessed by DMA and data_control feature
+	 * is supported then transfer data and oob directly.
+	 */
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) &&
+	    cdns_ctrl->caps2.data_control_supp) {
+		u8 *oob;
+
+		if (oob_required)
+			oob = chip->oob_poi;
+		else
+			oob = cdns_ctrl->buf + mtd->writesize;
+
+		cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT);
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, buf, oob,
+						    mtd->writesize,
+						    cdns_chip->avail_oob_size,
+						    DMA_FROM_DEVICE, true);
+	/* Otherwise use bounce buffer. */
+	} else {
+		cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS);
+		status = cadence_nand_cdma_transfer(cdns_ctrl,
+						    cdns_chip->cs[chip->cur_cs],
+						    page, cdns_ctrl->buf,
+						    NULL, mtd->writesize
+						    + cdns_chip->avail_oob_size,
+						    0, DMA_FROM_DEVICE, true);
+
+		memcpy(buf, cdns_ctrl->buf, mtd->writesize);
+		if (oob_required)
+			memcpy(chip->oob_poi,
+			       cdns_ctrl->buf + mtd->writesize,
+			       mtd->oobsize);
+	}
+
+	switch (status) {
+	case STAT_ECC_UNCORR:
+		mtd->ecc_stats.failed++;
+		ecc_err_count++;
+		break;
+	case STAT_ECC_CORR:
+		ecc_err_count = FIELD_GET(CDMA_CS_MAXERR,
+					  cdns_ctrl->cdma_desc->status);
+		mtd->ecc_stats.corrected += ecc_err_count;
+		break;
+	case STAT_ERASED:
+	case STAT_OK:
+		break;
+	default:
+		dev_err(cdns_ctrl->dev, "read page failed\n");
+		return -EIO;
+	}
+
+	if (oob_required)
+		if (cadence_nand_read_bbm(chip, page, chip->oob_poi))
+			return -EIO;
+
+	return ecc_err_count;
+}
+
+/* Reads OOB data from the device. */
+static int cadence_nand_read_oob(struct nand_chip *chip, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+
+	return cadence_nand_read_page(chip, cdns_ctrl->buf, 1, page);
+}
+
+static int cadence_nand_read_page_raw(struct nand_chip *chip,
+				      u8 *buf, int oob_required, int page)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int oob_skip = cdns_chip->bbm_len;
+	int writesize = mtd->writesize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *tmp_buf = cdns_ctrl->buf;
+	int i, pos, len;
+	int status = 0;
+
+	status = cadence_nand_select_target(chip);
+	if (status)
+		return status;
+
+	cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0);
+
+	cadence_nand_prepare_data_size(chip, TT_RAW_PAGE);
+	status = cadence_nand_cdma_transfer(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    page, cdns_ctrl->buf, NULL,
+					    mtd->writesize
+					    + mtd->oobsize,
+					    0, DMA_FROM_DEVICE, false);
+
+	switch (status) {
+	case STAT_ERASED:
+	case STAT_OK:
+		break;
+	default:
+		dev_err(cdns_ctrl->dev, "read raw page failed\n");
+		return -EIO;
+	}
+
+	/* Arrange the buffer for syndrome payload/ecc layout. */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(buf, tmp_buf + pos, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(buf, tmp_buf + writesize + oob_skip,
+				       len);
+				buf += len;
+			}
+		}
+	}
+
+	if (oob_required) {
+		u8 *oob = chip->oob_poi;
+		u32 oob_data_offset = (cdns_chip->sector_count - 1) *
+			(cdns_chip->sector_size + chip->ecc.bytes)
+			+ cdns_chip->sector_size + oob_skip;
+
+		/* OOB free. */
+		memcpy(oob, tmp_buf + oob_data_offset,
+		       cdns_chip->avail_oob_size);
+
+		/* BBM at the beginning of the OOB area. */
+		memcpy(oob, tmp_buf + writesize, oob_skip);
+
+		oob += cdns_chip->avail_oob_size;
+
+		/* OOB ECC */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			len = ecc_bytes;
+
+			if (i == (ecc_steps - 1))
+				pos += cdns_chip->avail_oob_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(oob, tmp_buf + pos, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(oob, tmp_buf + writesize + oob_skip,
+				       len);
+				oob += len;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int cadence_nand_read_oob_raw(struct nand_chip *chip,
+				     int page)
+{
+	return cadence_nand_read_page_raw(chip, NULL, true, page);
+}
+
+static void cadence_nand_slave_dma_transfer_finished(void *data)
+{
+	struct completion *finished = data;
+
+	complete(finished);
+}
+
+static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
+					   void *buf,
+					   dma_addr_t dev_dma, size_t len,
+					   enum dma_data_direction dir)
+{
+	DECLARE_COMPLETION_ONSTACK(finished);
+	struct dma_chan *chan;
+	struct dma_device *dma_dev;
+	dma_addr_t src_dma, dst_dma, buf_dma;
+	struct dma_async_tx_descriptor *tx;
+	dma_cookie_t cookie;
+
+	chan = cdns_ctrl->dmac;
+	dma_dev = chan->device;
+
+	buf_dma = dma_map_single(dma_dev->dev, buf, len, dir);
+	if (dma_mapping_error(dma_dev->dev, buf_dma)) {
+		dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n");
+		goto err;
+	}
+
+	if (dir == DMA_FROM_DEVICE) {
+		src_dma = cdns_ctrl->io.dma;
+		dst_dma = buf_dma;
+	} else {
+		src_dma = buf_dma;
+		dst_dma = cdns_ctrl->io.dma;
+	}
+
+	tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len,
+				       DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(cdns_ctrl->dev, "Failed to prepare DMA memcpy\n");
+		goto err_unmap;
+	}
+
+	tx->callback = cadence_nand_slave_dma_transfer_finished;
+	tx->callback_param = &finished;
+
+	cookie = dmaengine_submit(tx);
+	if (dma_submit_error(cookie)) {
+		dev_err(cdns_ctrl->dev, "Failed to do DMA tx_submit\n");
+		goto err_unmap;
+	}
+
+	dma_async_issue_pending(cdns_ctrl->dmac);
+	wait_for_completion(&finished);
+
+	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+
+	return 0;
+
+err_unmap:
+	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+
+err:
+	dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n");
+
+	return -EIO;
+}
+
+static int cadence_nand_read_buf(struct cdns_nand_ctrl *cdns_ctrl,
+				 u8 *buf, int len)
+{
+	u8 thread_nr = 0;
+	u32 sdma_size;
+	int status;
+
+	/* Wait until slave DMA interface is ready to data transfer. */
+	status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size);
+	if (status)
+		return status;
+
+	if (!cdns_ctrl->caps1->has_dma) {
+		int len_in_words = len >> 2;
+
+		/* read alingment data */
+		ioread32_rep(cdns_ctrl->io.virt, buf, len_in_words);
+		if (sdma_size > len) {
+			/* read rest data from slave DMA interface if any */
+			ioread32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf,
+				     sdma_size / 4 - len_in_words);
+			/* copy rest of data */
+			memcpy(buf + (len_in_words << 2), cdns_ctrl->buf,
+			       len - (len_in_words << 2));
+		}
+		return 0;
+	}
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) {
+		status = cadence_nand_slave_dma_transfer(cdns_ctrl, buf,
+							 cdns_ctrl->io.dma,
+							 len, DMA_FROM_DEVICE);
+		if (status == 0)
+			return 0;
+
+		dev_warn(cdns_ctrl->dev,
+			 "Slave DMA transfer failed. Try again using bounce buffer.");
+	}
+
+	/* If DMA transfer is not possible or failed then use bounce buffer. */
+	status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf,
+						 cdns_ctrl->io.dma,
+						 sdma_size, DMA_FROM_DEVICE);
+
+	if (status) {
+		dev_err(cdns_ctrl->dev, "Slave DMA transfer failed");
+		return status;
+	}
+
+	memcpy(buf, cdns_ctrl->buf, len);
+
+	return 0;
+}
+
+static int cadence_nand_write_buf(struct cdns_nand_ctrl *cdns_ctrl,
+				  const u8 *buf, int len)
+{
+	u8 thread_nr = 0;
+	u32 sdma_size;
+	int status;
+
+	/* Wait until slave DMA interface is ready to data transfer. */
+	status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size);
+	if (status)
+		return status;
+
+	if (!cdns_ctrl->caps1->has_dma) {
+		int len_in_words = len >> 2;
+
+		iowrite32_rep(cdns_ctrl->io.virt, buf, len_in_words);
+		if (sdma_size > len) {
+			/* copy rest of data */
+			memcpy(cdns_ctrl->buf, buf + (len_in_words << 2),
+			       len - (len_in_words << 2));
+			/* write all expected by nand controller data */
+			iowrite32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf,
+				      sdma_size / 4 - len_in_words);
+		}
+
+		return 0;
+	}
+
+	if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) {
+		status = cadence_nand_slave_dma_transfer(cdns_ctrl, (void *)buf,
+							 cdns_ctrl->io.dma,
+							 len, DMA_TO_DEVICE);
+		if (status == 0)
+			return 0;
+
+		dev_warn(cdns_ctrl->dev,
+			 "Slave DMA transfer failed. Try again using bounce buffer.");
+	}
+
+	/* If DMA transfer is not possible or failed then use bounce buffer. */
+	memcpy(cdns_ctrl->buf, buf, len);
+
+	status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf,
+						 cdns_ctrl->io.dma,
+						 sdma_size, DMA_TO_DEVICE);
+
+	if (status)
+		dev_err(cdns_ctrl->dev, "Slave DMA transfer failed");
+
+	return status;
+}
+
+static int cadence_nand_force_byte_access(struct nand_chip *chip,
+					  bool force_8bit)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	int status;
+
+	/*
+	 * Callers of this function do not verify if the NAND is using a 16-bit
+	 * an 8-bit bus for normal operations, so we need to take care of that
+	 * here by leaving the configuration unchanged if the NAND does not have
+	 * the NAND_BUSWIDTH_16 flag set.
+	 */
+	if (!(chip->options & NAND_BUSWIDTH_16))
+		return 0;
+
+	status = cadence_nand_set_access_width16(cdns_ctrl, !force_8bit);
+
+	return status;
+}
+
+static int cadence_nand_cmd_opcode(struct nand_chip *chip,
+				   const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	int ret;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_CMD);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_CMD,
+				    instr->ctx.cmd.opcode);
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret)
+		dev_err(cdns_ctrl->dev, "send cmd %x failed\n",
+			instr->ctx.cmd.opcode);
+
+	return ret;
+}
+
+static int cadence_nand_cmd_address(struct nand_chip *chip,
+				    const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	unsigned int offset, naddrs;
+	u64 address = 0;
+	const u8 *addrs;
+	int ret;
+	int i;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_ADDR);
+
+	offset = nand_subop_get_addr_start_off(subop, op_id);
+	naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+	addrs = &instr->ctx.addr.addrs[offset];
+
+	for (i = 0; i < naddrs; i++)
+		address |= (u64)addrs[i] << (8 * i);
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR,
+				    address);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR_SIZE,
+				    naddrs - 1);
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret)
+		dev_err(cdns_ctrl->dev, "send address %llx failed\n", address);
+
+	return ret;
+}
+
+static int cadence_nand_cmd_erase(struct nand_chip *chip,
+				  const struct nand_subop *subop)
+{
+	unsigned int op_id;
+
+	if (subop->instrs[0].ctx.cmd.opcode == NAND_CMD_ERASE1) {
+		int i;
+		const struct nand_op_instr *instr = NULL;
+		unsigned int offset, naddrs;
+		const u8 *addrs;
+		u32 page = 0;
+
+		instr = &subop->instrs[1];
+		offset = nand_subop_get_addr_start_off(subop, 1);
+		naddrs = nand_subop_get_num_addr_cyc(subop, 1);
+		addrs = &instr->ctx.addr.addrs[offset];
+
+		for (i = 0; i < naddrs; i++)
+			page |= (u32)addrs[i] << (8 * i);
+
+		return cadence_nand_erase(chip, page);
+	}
+
+	/*
+	 * If it is not an erase operation then handle operation
+	 * by calling exec_op function.
+	 */
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		int ret;
+		const struct nand_operation nand_op = {
+			.cs = chip->cur_cs,
+			.instrs =  &subop->instrs[op_id],
+			.ninstrs = 1};
+		ret = chip->controller->ops->exec_op(chip, &nand_op, false);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int cadence_nand_cmd_data(struct nand_chip *chip,
+				 const struct nand_subop *subop)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr;
+	unsigned int offset, op_id = 0;
+	u64 mini_ctrl_cmd = 0;
+	int len = 0;
+	int ret;
+
+	instr = &subop->instrs[op_id];
+
+	if (instr->delay_ns > 0)
+		mini_ctrl_cmd |= GCMD_LAY_TWB;
+
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR,
+				    GCMD_LAY_INSTR_DATA);
+
+	if (instr->type == NAND_OP_DATA_OUT_INSTR)
+		mini_ctrl_cmd |= FIELD_PREP(GCMD_DIR,
+					    GCMD_DIR_WRITE);
+
+	len = nand_subop_get_data_len(subop, op_id);
+	offset = nand_subop_get_data_start_off(subop, op_id);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_SECT_CNT, 1);
+	mini_ctrl_cmd |= FIELD_PREP(GCMD_LAST_SIZE, len);
+	if (instr->ctx.data.force_8bit) {
+		ret = cadence_nand_force_byte_access(chip, true);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"cannot change byte access generic data cmd failed\n");
+			return ret;
+		}
+	}
+
+	ret = cadence_nand_generic_cmd_send(cdns_ctrl,
+					    cdns_chip->cs[chip->cur_cs],
+					    mini_ctrl_cmd);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "send generic data cmd failed\n");
+		return ret;
+	}
+
+	if (instr->type == NAND_OP_DATA_IN_INSTR) {
+		void *buf = instr->ctx.data.buf.in + offset;
+
+		ret = cadence_nand_read_buf(cdns_ctrl, buf, len);
+	} else {
+		const void *buf = instr->ctx.data.buf.out + offset;
+
+		ret = cadence_nand_write_buf(cdns_ctrl, buf, len);
+	}
+
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "data transfer failed for generic command\n");
+		return ret;
+	}
+
+	if (instr->ctx.data.force_8bit) {
+		ret = cadence_nand_force_byte_access(chip, false);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"cannot change byte access generic data cmd failed\n");
+		}
+	}
+
+	return ret;
+}
+
+static int cadence_nand_cmd_waitrdy(struct nand_chip *chip,
+				    const struct nand_subop *subop)
+{
+	int status;
+	unsigned int op_id = 0;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	const struct nand_op_instr *instr = &subop->instrs[op_id];
+	u32 timeout_us = instr->ctx.waitrdy.timeout_ms * 1000;
+
+	status = cadence_nand_wait_for_value(cdns_ctrl, RBN_SETINGS,
+					     timeout_us,
+					     BIT(cdns_chip->cs[chip->cur_cs]),
+					     false);
+	return status;
+}
+
+static const struct nand_op_parser cadence_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_erase,
+		NAND_OP_PARSER_PAT_CMD_ELEM(false),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ERASE_ADDRESS_CYC),
+		NAND_OP_PARSER_PAT_CMD_ELEM(false),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(false)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_opcode,
+		NAND_OP_PARSER_PAT_CMD_ELEM(false)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_address,
+		NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ADDRESS_CYC)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_data,
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(false, MAX_DATA_SIZE)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_data,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, MAX_DATA_SIZE)),
+	NAND_OP_PARSER_PATTERN(
+		cadence_nand_cmd_waitrdy,
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(false))
+	);
+
+static int cadence_nand_exec_op(struct nand_chip *chip,
+				const struct nand_operation *op,
+				bool check_only)
+{
+	int status = cadence_nand_select_target(chip);
+
+	if (status)
+		return status;
+
+	return nand_op_parser_exec_op(chip, &cadence_nand_op_parser, op,
+				      check_only);
+}
+
+static int cadence_nand_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = cdns_chip->bbm_len;
+	oobregion->length = cdns_chip->avail_oob_size
+		- cdns_chip->bbm_len;
+
+	return 0;
+}
+
+static int cadence_nand_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = cdns_chip->avail_oob_size;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops cadence_nand_ooblayout_ops = {
+	.free = cadence_nand_ooblayout_free,
+	.ecc = cadence_nand_ooblayout_ecc,
+};
+
+static int calc_cycl(u32 timing, u32 clock)
+{
+	if (timing == 0 || clock == 0)
+		return 0;
+
+	if ((timing % clock) > 0)
+		return timing / clock;
+	else
+		return timing / clock - 1;
+}
+
+/* Calculate max data valid window. */
+static inline u32 calc_tdvw_max(u32 trp_cnt, u32 clk_period, u32 trhoh_min,
+				u32 board_delay_skew_min, u32 ext_mode)
+{
+	if (ext_mode == 0)
+		clk_period /= 2;
+
+	return (trp_cnt + 1) * clk_period + trhoh_min +
+		board_delay_skew_min;
+}
+
+/* Calculate data valid window. */
+static inline u32 calc_tdvw(u32 trp_cnt, u32 clk_period, u32 trhoh_min,
+			    u32 trea_max, u32 ext_mode)
+{
+	if (ext_mode == 0)
+		clk_period /= 2;
+
+	return (trp_cnt + 1) * clk_period + trhoh_min - trea_max;
+}
+
+static int
+cadence_nand_setup_data_interface(struct nand_chip *chip, int chipnr,
+				  const struct nand_data_interface *conf)
+{
+	const struct nand_sdr_timings *sdr;
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	struct cadence_nand_timings *t = &cdns_chip->timings;
+	u32 reg;
+	u32 board_delay = cdns_ctrl->board_delay;
+	u32 clk_period = DIV_ROUND_DOWN_ULL(1000000000000ULL,
+					    cdns_ctrl->nf_clk_rate);
+	u32 tceh_cnt, tcs_cnt, tadl_cnt, tccs_cnt;
+	u32 tfeat_cnt, trhz_cnt, tvdly_cnt;
+	u32 trhw_cnt, twb_cnt, twh_cnt = 0, twhr_cnt;
+	u32 twp_cnt = 0, trp_cnt = 0, trh_cnt = 0;
+	u32 if_skew = cdns_ctrl->caps1->if_skew;
+	u32 board_delay_skew_min = board_delay - if_skew;
+	u32 board_delay_skew_max = board_delay + if_skew;
+	u32 dqs_sampl_res, phony_dqs_mod;
+	u32 tdvw, tdvw_min, tdvw_max;
+	u32 ext_rd_mode, ext_wr_mode;
+	u32 dll_phy_dqs_timing = 0, phony_dqs_timing = 0, rd_del_sel = 0;
+	u32 sampling_point;
+
+	sdr = nand_get_sdr_timings(conf);
+	if (IS_ERR(sdr))
+		return PTR_ERR(sdr);
+
+	memset(t, 0, sizeof(*t));
+	/* Sampling point calculation. */
+
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		phony_dqs_mod = 2;
+	else
+		phony_dqs_mod = 1;
+
+	dqs_sampl_res = clk_period / phony_dqs_mod;
+
+	tdvw_min = sdr->tREA_max + board_delay_skew_max;
+	/*
+	 * The idea of those calculation is to get the optimum value
+	 * for tRP and tRH timings. If it is NOT possible to sample data
+	 * with optimal tRP/tRH settings, the parameters will be extended.
+	 * If clk_period is 50ns (the lowest value) this condition is met
+	 * for asynchronous timing modes 1, 2, 3, 4 and 5.
+	 * If clk_period is 20ns the condition is met only
+	 * for asynchronous timing mode 5.
+	 */
+	if (sdr->tRC_min <= clk_period &&
+	    sdr->tRP_min <= (clk_period / 2) &&
+	    sdr->tREH_min <= (clk_period / 2)) {
+		/* Performance mode. */
+		ext_rd_mode = 0;
+		tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min,
+				 sdr->tREA_max, ext_rd_mode);
+		tdvw_max = calc_tdvw_max(trp_cnt, clk_period, sdr->tRHOH_min,
+					 board_delay_skew_min,
+					 ext_rd_mode);
+		/*
+		 * Check if data valid window and sampling point can be found
+		 * and is not on the edge (ie. we have hold margin).
+		 * If not extend the tRP timings.
+		 */
+		if (tdvw > 0) {
+			if (tdvw_max <= tdvw_min ||
+			    (tdvw_max % dqs_sampl_res) == 0) {
+				/*
+				 * No valid sampling point so the RE pulse need
+				 * to be widen widening by half clock cycle.
+				 */
+				ext_rd_mode = 1;
+			}
+		} else {
+			/*
+			 * There is no valid window
+			 * to be able to sample data the tRP need to be widen.
+			 * Very safe calculations are performed here.
+			 */
+			trp_cnt = (sdr->tREA_max + board_delay_skew_max
+				   + dqs_sampl_res) / clk_period;
+			ext_rd_mode = 1;
+		}
+
+	} else {
+		/* Extended read mode. */
+		u32 trh;
+
+		ext_rd_mode = 1;
+		trp_cnt = calc_cycl(sdr->tRP_min, clk_period);
+		trh = sdr->tRC_min - ((trp_cnt + 1) * clk_period);
+		if (sdr->tREH_min >= trh)
+			trh_cnt = calc_cycl(sdr->tREH_min, clk_period);
+		else
+			trh_cnt = calc_cycl(trh, clk_period);
+
+		tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min,
+				 sdr->tREA_max, ext_rd_mode);
+		/*
+		 * Check if data valid window and sampling point can be found
+		 * or if it is at the edge check if previous is valid
+		 * - if not extend the tRP timings.
+		 */
+		if (tdvw > 0) {
+			tdvw_max = calc_tdvw_max(trp_cnt, clk_period,
+						 sdr->tRHOH_min,
+						 board_delay_skew_min,
+						 ext_rd_mode);
+
+			if ((((tdvw_max / dqs_sampl_res)
+			      * dqs_sampl_res) <= tdvw_min) ||
+			    (((tdvw_max % dqs_sampl_res) == 0) &&
+			     (((tdvw_max / dqs_sampl_res - 1)
+			       * dqs_sampl_res) <= tdvw_min))) {
+				/*
+				 * Data valid window width is lower than
+				 * sampling resolution and do not hit any
+				 * sampling point to be sure the sampling point
+				 * will be found the RE low pulse width will be
+				 *  extended by one clock cycle.
+				 */
+				trp_cnt = trp_cnt + 1;
+			}
+		} else {
+			/*
+			 * There is no valid window to be able to sample data.
+			 * The tRP need to be widen.
+			 * Very safe calculations are performed here.
+			 */
+			trp_cnt = (sdr->tREA_max + board_delay_skew_max
+				   + dqs_sampl_res) / clk_period;
+		}
+	}
+
+	tdvw_max = calc_tdvw_max(trp_cnt, clk_period,
+				 sdr->tRHOH_min,
+				 board_delay_skew_min, ext_rd_mode);
+
+	if (sdr->tWC_min <= clk_period &&
+	    (sdr->tWP_min + if_skew) <= (clk_period / 2) &&
+	    (sdr->tWH_min + if_skew) <= (clk_period / 2)) {
+		ext_wr_mode = 0;
+	} else {
+		u32 twh;
+
+		ext_wr_mode = 1;
+		twp_cnt = calc_cycl(sdr->tWP_min + if_skew, clk_period);
+		if ((twp_cnt + 1) * clk_period < (sdr->tALS_min + if_skew))
+			twp_cnt = calc_cycl(sdr->tALS_min + if_skew,
+					    clk_period);
+
+		twh = (sdr->tWC_min - (twp_cnt + 1) * clk_period);
+		if (sdr->tWH_min >= twh)
+			twh = sdr->tWH_min;
+
+		twh_cnt = calc_cycl(twh + if_skew, clk_period);
+	}
+
+	reg = FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRH, trh_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRP, trp_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWH, twh_cnt);
+	reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWP, twp_cnt);
+	t->async_toggle_timings = reg;
+	dev_dbg(cdns_ctrl->dev, "ASYNC_TOGGLE_TIMINGS_SDR\t%x\n", reg);
+
+	tadl_cnt = calc_cycl((sdr->tADL_min + if_skew), clk_period);
+	tccs_cnt = calc_cycl((sdr->tCCS_min + if_skew), clk_period);
+	twhr_cnt = calc_cycl((sdr->tWHR_min + if_skew), clk_period);
+	trhw_cnt = calc_cycl((sdr->tRHW_min + if_skew), clk_period);
+	reg = FIELD_PREP(TIMINGS0_TADL, tadl_cnt);
+
+	/*
+	 * If timing exceeds delay field in timing register
+	 * then use maximum value.
+	 */
+	if (FIELD_FIT(TIMINGS0_TCCS, tccs_cnt))
+		reg |= FIELD_PREP(TIMINGS0_TCCS, tccs_cnt);
+	else
+		reg |= TIMINGS0_TCCS;
+
+	reg |= FIELD_PREP(TIMINGS0_TWHR, twhr_cnt);
+	reg |= FIELD_PREP(TIMINGS0_TRHW, trhw_cnt);
+	t->timings0 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS0_SDR\t%x\n", reg);
+
+	/* The following is related to single signal so skew is not needed. */
+	trhz_cnt = calc_cycl(sdr->tRHZ_max, clk_period);
+	trhz_cnt = trhz_cnt + 1;
+	twb_cnt = calc_cycl((sdr->tWB_max + board_delay), clk_period);
+	/*
+	 * Because of the two stage syncflop the value must be increased by 3
+	 * first value is related with sync, second value is related
+	 * with output if delay.
+	 */
+	twb_cnt = twb_cnt + 3 + 5;
+	/*
+	 * The following is related to the we edge of the random data input
+	 * sequence so skew is not needed.
+	 */
+	tvdly_cnt = calc_cycl(500000 + if_skew, clk_period);
+	reg = FIELD_PREP(TIMINGS1_TRHZ, trhz_cnt);
+	reg |= FIELD_PREP(TIMINGS1_TWB, twb_cnt);
+	reg |= FIELD_PREP(TIMINGS1_TVDLY, tvdly_cnt);
+	t->timings1 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS1_SDR\t%x\n", reg);
+
+	tfeat_cnt = calc_cycl(sdr->tFEAT_max, clk_period);
+	if (tfeat_cnt < twb_cnt)
+		tfeat_cnt = twb_cnt;
+
+	tceh_cnt = calc_cycl(sdr->tCEH_min, clk_period);
+	tcs_cnt = calc_cycl((sdr->tCS_min + if_skew), clk_period);
+
+	reg = FIELD_PREP(TIMINGS2_TFEAT, tfeat_cnt);
+	reg |= FIELD_PREP(TIMINGS2_CS_HOLD_TIME, tceh_cnt);
+	reg |= FIELD_PREP(TIMINGS2_CS_SETUP_TIME, tcs_cnt);
+	t->timings2 = reg;
+	dev_dbg(cdns_ctrl->dev, "TIMINGS2_SDR\t%x\n", reg);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		reg = DLL_PHY_CTRL_DLL_RST_N;
+		if (ext_wr_mode)
+			reg |= DLL_PHY_CTRL_EXTENDED_WR_MODE;
+		if (ext_rd_mode)
+			reg |= DLL_PHY_CTRL_EXTENDED_RD_MODE;
+
+		reg |= FIELD_PREP(DLL_PHY_CTRL_RS_HIGH_WAIT_CNT, 7);
+		reg |= FIELD_PREP(DLL_PHY_CTRL_RS_IDLE_CNT, 7);
+		t->dll_phy_ctrl = reg;
+		dev_dbg(cdns_ctrl->dev, "DLL_PHY_CTRL_SDR\t%x\n", reg);
+	}
+
+	/* Sampling point calculation. */
+	if ((tdvw_max % dqs_sampl_res) > 0)
+		sampling_point = tdvw_max / dqs_sampl_res;
+	else
+		sampling_point = (tdvw_max / dqs_sampl_res - 1);
+
+	if (sampling_point * dqs_sampl_res > tdvw_min) {
+		dll_phy_dqs_timing =
+			FIELD_PREP(PHY_DQS_TIMING_DQS_SEL_OE_END, 4);
+		dll_phy_dqs_timing |= PHY_DQS_TIMING_USE_PHONY_DQS;
+		phony_dqs_timing = sampling_point / phony_dqs_mod;
+
+		if ((sampling_point % 2) > 0) {
+			dll_phy_dqs_timing |= PHY_DQS_TIMING_PHONY_DQS_SEL;
+			if ((tdvw_max % dqs_sampl_res) == 0)
+				/*
+				 * Calculation for sampling point at the edge
+				 * of data and being odd number.
+				 */
+				phony_dqs_timing = (tdvw_max / dqs_sampl_res)
+					/ phony_dqs_mod - 1;
+
+			if (!cdns_ctrl->caps2.is_phy_type_dll)
+				phony_dqs_timing--;
+
+		} else {
+			phony_dqs_timing--;
+		}
+		rd_del_sel = phony_dqs_timing + 3;
+	} else {
+		dev_warn(cdns_ctrl->dev,
+			 "ERROR : cannot find valid sampling point\n");
+	}
+
+	reg = FIELD_PREP(PHY_CTRL_PHONY_DQS, phony_dqs_timing);
+	if (cdns_ctrl->caps2.is_phy_type_dll)
+		reg  |= PHY_CTRL_SDR_DQS;
+	t->phy_ctrl = reg;
+	dev_dbg(cdns_ctrl->dev, "PHY_CTRL_REG_SDR\t%x\n", reg);
+
+	if (cdns_ctrl->caps2.is_phy_type_dll) {
+		dev_dbg(cdns_ctrl->dev, "PHY_TSEL_REG_SDR\t%x\n", 0);
+		dev_dbg(cdns_ctrl->dev, "PHY_DQ_TIMING_REG_SDR\t%x\n", 2);
+		dev_dbg(cdns_ctrl->dev, "PHY_DQS_TIMING_REG_SDR\t%x\n",
+			dll_phy_dqs_timing);
+		t->phy_dqs_timing = dll_phy_dqs_timing;
+
+		reg = FIELD_PREP(PHY_GATE_LPBK_CTRL_RDS, rd_del_sel);
+		dev_dbg(cdns_ctrl->dev, "PHY_GATE_LPBK_CTRL_REG_SDR\t%x\n",
+			reg);
+		t->phy_gate_lpbk_ctrl = reg;
+
+		dev_dbg(cdns_ctrl->dev, "PHY_DLL_MASTER_CTRL_REG_SDR\t%lx\n",
+			PHY_DLL_MASTER_CTRL_BYPASS_MODE);
+		dev_dbg(cdns_ctrl->dev, "PHY_DLL_SLAVE_CTRL_REG_SDR\t%x\n", 0);
+	}
+
+	return 0;
+}
+
+int cadence_nand_attach_chip(struct nand_chip *chip)
+{
+	struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller);
+	struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip);
+	u32 ecc_size = cdns_chip->sector_count * chip->ecc.bytes;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 max_oob_data_size;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		ret = cadence_nand_set_access_width16(cdns_ctrl, true);
+		if (ret)
+			return ret;
+	}
+
+	chip->bbt_options |= NAND_BBT_USE_FLASH;
+	chip->bbt_options |= NAND_BBT_NO_OOB;
+	chip->ecc.mode = NAND_ECC_HW;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+
+	cdns_chip->bbm_offs = chip->badblockpos;
+	if (chip->options & NAND_BUSWIDTH_16) {
+		cdns_chip->bbm_offs &= ~0x01;
+		cdns_chip->bbm_len = 2;
+	} else {
+		cdns_chip->bbm_len = 1;
+	}
+
+	ret = nand_ecc_choose_conf(chip,
+				   &cdns_ctrl->ecc_caps,
+				   mtd->oobsize - cdns_chip->bbm_len);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "ECC configuration failed\n");
+		return ret;
+	}
+
+	dev_dbg(cdns_ctrl->dev,
+		"chosen ECC settings: step=%d, strength=%d, bytes=%d\n",
+		chip->ecc.size, chip->ecc.strength, chip->ecc.bytes);
+
+	/* Error correction configuration. */
+	cdns_chip->sector_size = chip->ecc.size;
+	cdns_chip->sector_count = mtd->writesize / cdns_chip->sector_size;
+
+	cdns_chip->avail_oob_size = mtd->oobsize - ecc_size;
+
+	max_oob_data_size = MAX_OOB_SIZE_PER_SECTOR;
+
+	if (cdns_chip->avail_oob_size > max_oob_data_size)
+		cdns_chip->avail_oob_size = max_oob_data_size;
+
+	if ((cdns_chip->avail_oob_size + cdns_chip->bbm_len + ecc_size)
+	    > mtd->oobsize)
+		cdns_chip->avail_oob_size -= 4;
+
+	ret = cadence_nand_get_ecc_strength_idx(cdns_ctrl, chip->ecc.strength);
+	if (ret < 0)
+		return -EINVAL;
+
+	cdns_chip->corr_str_idx = (u8)ret;
+
+	if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS,
+					1000000,
+					CTRL_STATUS_CTRL_BUSY, true))
+		return -ETIMEDOUT;
+
+	cadence_nand_set_ecc_strength(cdns_ctrl,
+				      cdns_chip->corr_str_idx);
+
+	cadence_nand_set_erase_detection(cdns_ctrl, true,
+					 chip->ecc.strength);
+
+	/* Override the default read operations. */
+	chip->ecc.read_page = cadence_nand_read_page;
+	chip->ecc.read_page_raw = cadence_nand_read_page_raw;
+	chip->ecc.write_page = cadence_nand_write_page;
+	chip->ecc.write_page_raw = cadence_nand_write_page_raw;
+	chip->ecc.read_oob = cadence_nand_read_oob;
+	chip->ecc.write_oob = cadence_nand_write_oob;
+	chip->ecc.read_oob_raw = cadence_nand_read_oob_raw;
+	chip->ecc.write_oob_raw = cadence_nand_write_oob_raw;
+
+	if ((mtd->writesize + mtd->oobsize) > cdns_ctrl->buf_size)
+		cdns_ctrl->buf_size = mtd->writesize + mtd->oobsize;
+
+	/* Is 32-bit DMA supported? */
+	ret = dma_set_mask(cdns_ctrl->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "no usable DMA configuration\n");
+		return ret;
+	}
+
+	mtd_set_ooblayout(mtd, &cadence_nand_ooblayout_ops);
+
+	return 0;
+}
+
+static const struct nand_controller_ops cadence_nand_controller_ops = {
+	.attach_chip = cadence_nand_attach_chip,
+	.exec_op = cadence_nand_exec_op,
+	.setup_data_interface = cadence_nand_setup_data_interface,
+};
+
+static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl,
+				  struct device_node *np)
+{
+	struct cdns_nand_chip *cdns_chip;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int nsels, ret, i;
+	u32 cs;
+
+	nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32));
+	if (nsels <= 0) {
+		dev_err(cdns_ctrl->dev, "missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Allocate the nand chip structure. */
+	cdns_chip = devm_kzalloc(cdns_ctrl->dev, sizeof(*cdns_chip) +
+				 (nsels * sizeof(u8)),
+				 GFP_KERNEL);
+	if (!cdns_chip) {
+		dev_err(cdns_ctrl->dev, "could not allocate chip structure\n");
+		return -ENOMEM;
+	}
+
+	cdns_chip->nsels = nsels;
+
+	for (i = 0; i < nsels; i++) {
+		/* Retrieve CS id. */
+		ret = of_property_read_u32_index(np, "reg", i, &cs);
+		if (ret) {
+			dev_err(cdns_ctrl->dev,
+				"could not retrieve reg property: %d\n",
+				ret);
+			return ret;
+		}
+
+		if (cs >= cdns_ctrl->caps2.max_banks) {
+			dev_err(cdns_ctrl->dev,
+				"invalid reg value: %u (max CS = %d)\n",
+				cs, cdns_ctrl->caps2.max_banks);
+			return -EINVAL;
+		}
+
+		if (test_and_set_bit(cs, &cdns_ctrl->assigned_cs)) {
+			dev_err(cdns_ctrl->dev,
+				"CS %d already assigned\n", cs);
+			return -EINVAL;
+		}
+
+		cdns_chip->cs[i] = cs;
+	}
+
+	chip = &cdns_chip->chip;
+	chip->controller = &cdns_ctrl->controller;
+	nand_set_flash_node(chip, np);
+
+	mtd = nand_to_mtd(chip);
+	mtd->dev.parent = cdns_ctrl->dev;
+
+	/*
+	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
+	 * in the DT node, this entry will be overwritten in nand_scan_ident().
+	 */
+	chip->ecc.mode = NAND_ECC_HW;
+
+	ret = nand_scan(chip, cdns_chip->nsels);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "could not scan the nand chip\n");
+		return ret;
+	}
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(cdns_ctrl->dev,
+			"failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	list_add_tail(&cdns_chip->node, &cdns_ctrl->chips);
+
+	return 0;
+}
+
+static void cadence_nand_chips_cleanup(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct cdns_nand_chip *entry, *temp;
+
+	list_for_each_entry_safe(entry, temp, &cdns_ctrl->chips, node) {
+		nand_release(&entry->chip);
+		list_del(&entry->node);
+	}
+}
+
+static int cadence_nand_chips_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	struct device_node *np = cdns_ctrl->dev->of_node;
+	struct device_node *nand_np;
+	int max_cs = cdns_ctrl->caps2.max_banks;
+	int nchips, ret;
+
+	nchips = of_get_child_count(np);
+
+	if (nchips > max_cs) {
+		dev_err(cdns_ctrl->dev,
+			"too many NAND chips: %d (max = %d CS)\n",
+			nchips, max_cs);
+		return -EINVAL;
+	}
+
+	for_each_child_of_node(np, nand_np) {
+		ret = cadence_nand_chip_init(cdns_ctrl, nand_np);
+		if (ret) {
+			of_node_put(nand_np);
+			cadence_nand_chips_cleanup(cdns_ctrl);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void
+cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
+{
+	/* Disable interrupts. */
+	writel_relaxed(INTR_ENABLE_INTR_EN, cdns_ctrl->reg + INTR_ENABLE);
+}
+
+static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	dma_cap_mask_t mask;
+	int ret;
+
+	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
+						  sizeof(*cdns_ctrl->cdma_desc),
+						  &cdns_ctrl->dma_cdma_desc,
+						  GFP_KERNEL);
+	if (!cdns_ctrl->dma_cdma_desc)
+		return -ENOMEM;
+
+	cdns_ctrl->buf_size = SZ_16K;
+	cdns_ctrl->buf = kmalloc(cdns_ctrl->buf_size, GFP_KERNEL);
+	if (!cdns_ctrl->buf) {
+		ret = -ENOMEM;
+		goto free_buf_desc;
+	}
+
+	if (devm_request_irq(cdns_ctrl->dev, cdns_ctrl->irq, cadence_nand_isr,
+			     IRQF_SHARED, "cadence-nand-controller",
+			     cdns_ctrl)) {
+		dev_err(cdns_ctrl->dev, "Unable to allocate IRQ\n");
+		ret = -ENODEV;
+		goto free_buf;
+	}
+
+	spin_lock_init(&cdns_ctrl->irq_lock);
+	init_completion(&cdns_ctrl->complete);
+
+	ret = cadence_nand_hw_init(cdns_ctrl);
+	if (ret)
+		goto disable_irq;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+
+	if (cdns_ctrl->caps1->has_dma) {
+		cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL);
+		if (!cdns_ctrl->dmac) {
+			dev_err(cdns_ctrl->dev,
+				"Unable to get a DMA channel\n");
+			ret = -EBUSY;
+			goto disable_irq;
+		}
+	}
+
+	nand_controller_init(&cdns_ctrl->controller);
+	INIT_LIST_HEAD(&cdns_ctrl->chips);
+
+	cdns_ctrl->controller.ops = &cadence_nand_controller_ops;
+	cdns_ctrl->curr_corr_str_idx = 0xFF;
+
+	ret = cadence_nand_chips_init(cdns_ctrl);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n",
+			ret);
+		goto dma_release_chnl;
+	}
+
+	kfree(cdns_ctrl->buf);
+	cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL);
+	if (!cdns_ctrl->buf) {
+		ret = -ENOMEM;
+		goto dma_release_chnl;
+	}
+
+	return 0;
+
+dma_release_chnl:
+	if (cdns_ctrl->dmac)
+		dma_release_channel(cdns_ctrl->dmac);
+
+disable_irq:
+	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
+
+free_buf:
+	kfree(cdns_ctrl->buf);
+
+free_buf_desc:
+	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
+			  cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc);
+
+	return ret;
+}
+
+/* Driver exit point. */
+static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
+{
+	cadence_nand_chips_cleanup(cdns_ctrl);
+	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
+	kfree(cdns_ctrl->buf);
+	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
+			  cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc);
+
+	if (cdns_ctrl->dmac)
+		dma_release_channel(cdns_ctrl->dmac);
+}
+
+struct cadence_nand_dt {
+	struct cdns_nand_ctrl cdns_ctrl;
+	struct clk *clk;
+};
+
+static const struct cadence_nand_dt_devdata cadence_nand_default = {
+	.if_skew = 0,
+	.has_dma = 1,
+};
+
+static const struct of_device_id cadence_nand_dt_ids[] = {
+	{
+		.compatible = "cdns,hp-nfc",
+		.data = &cadence_nand_default
+	}, {}
+};
+
+MODULE_DEVICE_TABLE(of, cadence_nand_dt_ids);
+
+static int cadence_nand_dt_probe(struct platform_device *ofdev)
+{
+	struct resource *res;
+	struct cadence_nand_dt *dt;
+	struct cdns_nand_ctrl *cdns_ctrl;
+	int ret;
+	const struct of_device_id *of_id;
+	const struct cadence_nand_dt_devdata *devdata;
+	u32 val;
+
+	of_id = of_match_device(cadence_nand_dt_ids, &ofdev->dev);
+	if (of_id) {
+		ofdev->id_entry = of_id->data;
+		devdata = of_id->data;
+	} else {
+		pr_err("Failed to find the right device id.\n");
+		return -ENOMEM;
+	}
+
+	dt = devm_kzalloc(&ofdev->dev, sizeof(*dt), GFP_KERNEL);
+	if (!dt)
+		return -ENOMEM;
+
+	cdns_ctrl = &dt->cdns_ctrl;
+	cdns_ctrl->caps1 = devdata;
+
+	cdns_ctrl->dev = &ofdev->dev;
+	cdns_ctrl->irq = platform_get_irq(ofdev, 0);
+	if (cdns_ctrl->irq < 0)
+		return cdns_ctrl->irq;
+
+	dev_info(cdns_ctrl->dev, "IRQ: nr %d\n", cdns_ctrl->irq);
+
+	cdns_ctrl->reg = devm_platform_ioremap_resource(ofdev, 0);
+	if (IS_ERR(cdns_ctrl->reg)) {
+		dev_err(&ofdev->dev, "devm_ioremap_resource res 0 failed\n");
+		return PTR_ERR(cdns_ctrl->reg);
+	}
+
+	res = platform_get_resource(ofdev, IORESOURCE_MEM, 1);
+	cdns_ctrl->io.dma = res->start;
+	cdns_ctrl->io.virt = devm_ioremap_resource(&ofdev->dev, res);
+	if (IS_ERR(cdns_ctrl->io.virt)) {
+		dev_err(cdns_ctrl->dev, "devm_ioremap_resource res 1 failed\n");
+		return PTR_ERR(cdns_ctrl->io.virt);
+	}
+
+	dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk");
+	if (IS_ERR(dt->clk))
+		return PTR_ERR(dt->clk);
+
+	cdns_ctrl->nf_clk_rate = clk_get_rate(dt->clk);
+
+	ret = of_property_read_u32(ofdev->dev.of_node,
+				   "cdns,board-delay-ps", &val);
+	if (ret) {
+		val = 4830;
+		dev_info(cdns_ctrl->dev,
+			 "missing cdns,board-delay-ps property, %d was set\n",
+			 val);
+	}
+	cdns_ctrl->board_delay = val;
+
+	ret = cadence_nand_init(cdns_ctrl);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(ofdev, dt);
+	return 0;
+}
+
+static int cadence_nand_dt_remove(struct platform_device *ofdev)
+{
+	struct cadence_nand_dt *dt = platform_get_drvdata(ofdev);
+
+	cadence_nand_remove(&dt->cdns_ctrl);
+
+	return 0;
+}
+
+static struct platform_driver cadence_nand_dt_driver = {
+	.probe		= cadence_nand_dt_probe,
+	.remove		= cadence_nand_dt_remove,
+	.driver		= {
+		.name	= "cadence-nand-controller",
+		.of_match_table = cadence_nand_dt_ids,
+	},
+};
+
+module_platform_driver(cadence_nand_dt_driver);
+
+MODULE_AUTHOR("Piotr Sroka <piotrs@cadence.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Driver for Cadence NAND flash controller");
+
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 5e14836f6bd5..8b779a899dcf 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -102,47 +102,6 @@ static int denali_dt_chip_init(struct denali_controller *denali,
 	return denali_chip_init(denali, dchip);
 }
 
-/* Backward compatibility for old platforms */
-static int denali_dt_legacy_chip_init(struct denali_controller *denali)
-{
-	struct denali_chip *dchip;
-	int nsels, i;
-
-	nsels = denali->nbanks;
-
-	dchip = devm_kzalloc(denali->dev, struct_size(dchip, sels, nsels),
-			     GFP_KERNEL);
-	if (!dchip)
-		return -ENOMEM;
-
-	dchip->nsels = nsels;
-
-	for (i = 0; i < nsels; i++)
-		dchip->sels[i].bank = i;
-
-	nand_set_flash_node(&dchip->chip, denali->dev->of_node);
-
-	return denali_chip_init(denali, dchip);
-}
-
-/*
- * Check the DT binding.
- * The new binding expects chip subnodes in the controller node.
- * So, #address-cells = <1>; #size-cells = <0>; are required.
- * Check the #size-cells to distinguish the binding.
- */
-static bool denali_dt_is_legacy_binding(struct device_node *np)
-{
-	u32 cells;
-	int ret;
-
-	ret = of_property_read_u32(np, "#size-cells", &cells);
-	if (ret)
-		return true;
-
-	return cells != 0;
-}
-
 static int denali_dt_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -167,10 +126,8 @@ static int denali_dt_probe(struct platform_device *pdev)
 
 	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
-	if (denali->irq < 0) {
-		dev_err(dev, "no irq defined\n");
+	if (denali->irq < 0)
 		return denali->irq;
-	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
 	denali->reg = devm_ioremap_resource(dev, res);
@@ -213,17 +170,11 @@ static int denali_dt_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_disable_clk_ecc;
 
-	if (denali_dt_is_legacy_binding(dev->of_node)) {
-		ret = denali_dt_legacy_chip_init(denali);
-		if (ret)
+	for_each_child_of_node(dev->of_node, np) {
+		ret = denali_dt_chip_init(denali, np);
+		if (ret) {
+			of_node_put(np);
 			goto out_remove_denali;
-	} else {
-		for_each_child_of_node(dev->of_node, np) {
-			ret = denali_dt_chip_init(denali, np);
-			if (ret) {
-				of_node_put(np);
-				goto out_remove_denali;
-			}
 		}
 	}
 
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index 6a4626a8bf95..0b48be54ba6f 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -751,10 +751,8 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 	mtd  = nand_to_mtd(chip);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "no IRQ resource defined\n");
+	if (irq < 0)
 		return -ENXIO;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->iobase = devm_ioremap_resource(dev, res);
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 78b31f845c50..241b58b83240 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -773,7 +773,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 
 	host->irq = platform_get_irq(pdev, 0);
 	if (host->irq < 0) {
-		dev_err(&pdev->dev, "failed to get platform irq\n");
 		res = -EINVAL;
 		goto release_dma_chan;
 	}
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index fc49e13d81ec..fb5abdcfb007 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2862,10 +2862,8 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->regs);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	nfc->core_clk = devm_clk_get(&pdev->dev, "core");
 
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 1b82b687e5a5..9f17b5b8efbf 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1399,10 +1399,8 @@ static int meson_nfc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "no NFC IRQ resource\n");
+	if (irq < 0)
 		return -EINVAL;
-	}
 
 	ret = meson_nfc_clk_init(nfc);
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c
index 74595b644b7c..75f1fa3d4d35 100644
--- a/drivers/mtd/nand/raw/mtk_ecc.c
+++ b/drivers/mtd/nand/raw/mtk_ecc.c
@@ -527,10 +527,8 @@ static int mtk_ecc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to get irq: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 373d47d1ba4c..b8305e39ab51 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1540,7 +1540,6 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(dev, "no nfi irq resource\n");
 		ret = -EINVAL;
 		goto clk_disable;
 	}
diff --git a/drivers/mtd/nand/raw/mxic_nand.c b/drivers/mtd/nand/raw/mxic_nand.c
index 9d49e6c845e1..ed7a4e021bf5 100644
--- a/drivers/mtd/nand/raw/mxic_nand.c
+++ b/drivers/mtd/nand/raw/mxic_nand.c
@@ -524,10 +524,8 @@ static int mxic_nfc_probe(struct platform_device *pdev)
 	nand_chip->controller = &nfc->controller;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	mxic_nfc_hw_init(nfc);
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 5c2c30a7dffa..f64e3b6605c6 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -292,12 +292,16 @@ int nand_bbm_get_next_page(struct nand_chip *chip, int page)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int last_page = ((mtd->erasesize - mtd->writesize) >>
 			 chip->page_shift) & chip->pagemask;
+	unsigned int bbm_flags = NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE
+		| NAND_BBM_LASTPAGE;
 
+	if (page == 0 && !(chip->options & bbm_flags))
+		return 0;
 	if (page == 0 && chip->options & NAND_BBM_FIRSTPAGE)
 		return 0;
-	else if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE)
+	if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE)
 		return 1;
-	else if (page <= last_page && chip->options & NAND_BBM_LASTPAGE)
+	if (page <= last_page && chip->options & NAND_BBM_LASTPAGE)
 		return last_page;
 
 	return -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 8ca9fad6e6ad..56654030ec7f 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -446,8 +446,10 @@ static int micron_nand_init(struct nand_chip *chip)
 	if (ret)
 		goto err_free_manuf_data;
 
+	chip->options |= NAND_BBM_FIRSTPAGE;
+
 	if (mtd->writesize == 2048)
-		chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE;
+		chip->options |= NAND_BBM_SECONDPAGE;
 
 	ondie = micron_supports_on_die_ecc(chip);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 6ec65f48501c..ad77c112a78a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -1967,10 +1967,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case NAND_OMAP_PREFETCH_IRQ:
 		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
-		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(dev, "Error getting fifo IRQ\n");
+		if (info->gpmc_irq_fifo <= 0)
 			return -ENODEV;
-		}
 		err = devm_request_irq(dev, info->gpmc_irq_fifo,
 				       omap_nand_irq, IRQF_SHARED,
 				       "gpmc-nand-fifo", info);
@@ -1982,10 +1980,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		}
 
 		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
-		if (info->gpmc_irq_count <= 0) {
-			dev_err(dev, "Error getting IRQ count\n");
+		if (info->gpmc_irq_count <= 0)
 			return -ENODEV;
-		}
 		err = devm_request_irq(dev, info->gpmc_irq_count,
 				       omap_nand_irq, IRQF_SHARED,
 				       "gpmc-nand-count", info);
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index e509c93737c4..058e99d0cbcf 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1129,10 +1129,8 @@ static int flctl_probe(struct platform_device *pdev)
 	flctl->fifo = res->start + 0x24; /* FLDTFIFO */
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get flste irq data: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, irq, flctl_handle_flste, IRQF_SHARED,
 			       "flste", flctl);
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 8cc852dc7d54..9e63800f768a 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1880,11 +1880,8 @@ static int stm32_fmc2_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		if (irq != -EPROBE_DEFER)
-			dev_err(dev, "IRQ error missing or invalid\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(dev, irq, stm32_fmc2_irq, 0,
 			       dev_name(dev), fmc2);
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 89773293c64d..37a4ac0dd85b 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -2071,10 +2071,8 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->regs);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "failed to retrieve irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	nfc->ahb_clk = devm_clk_get(dev, "ahb");
 	if (IS_ERR(nfc->ahb_clk)) {
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
index 009c1da8574c..2b7cabbb680c 100644
--- a/drivers/mtd/spi-nor/aspeed-smc.c
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -320,7 +320,8 @@ static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 	mutex_unlock(&chip->controller->mutex);
 }
 
-static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			       size_t len)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
@@ -331,8 +332,8 @@ static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return 0;
 }
 
-static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-				int len)
+static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+				size_t len)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
@@ -746,6 +747,15 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 	return 0;
 }
 
+static const struct spi_nor_controller_ops aspeed_smc_controller_ops = {
+	.prepare = aspeed_smc_prep,
+	.unprepare = aspeed_smc_unprep,
+	.read_reg = aspeed_smc_read_reg,
+	.write_reg = aspeed_smc_write_reg,
+	.read = aspeed_smc_read_user,
+	.write = aspeed_smc_write_user,
+};
+
 static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 				  struct device_node *np, struct resource *r)
 {
@@ -805,12 +815,7 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 		nor->dev = dev;
 		nor->priv = chip;
 		spi_nor_set_flash_node(nor, child);
-		nor->read = aspeed_smc_read_user;
-		nor->write = aspeed_smc_write_user;
-		nor->read_reg = aspeed_smc_read_reg;
-		nor->write_reg = aspeed_smc_write_reg;
-		nor->prepare = aspeed_smc_prep;
-		nor->unprepare = aspeed_smc_unprep;
+		nor->controller_ops = &aspeed_smc_controller_ops;
 
 		ret = aspeed_smc_chip_setup_init(chip, r);
 		if (ret)
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 7bef63947b29..06f997247d0f 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -285,7 +285,7 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static unsigned int cqspi_calc_rdreg(struct spi_nor *nor, const u8 opcode)
+static unsigned int cqspi_calc_rdreg(struct spi_nor *nor)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	u32 rdreg = 0;
@@ -354,27 +354,27 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
 	return cqspi_wait_idle(cqspi);
 }
 
-static int cqspi_command_read(struct spi_nor *nor,
-			      const u8 *txbuf, const unsigned n_tx,
-			      u8 *rxbuf, const unsigned n_rx)
+static int cqspi_command_read(struct spi_nor *nor, u8 opcode,
+			      u8 *rxbuf, size_t n_rx)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
 	unsigned int rdreg;
 	unsigned int reg;
-	unsigned int read_len;
+	size_t read_len;
 	int status;
 
 	if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
-		dev_err(nor->dev, "Invalid input argument, len %d rxbuf 0x%p\n",
+		dev_err(nor->dev,
+			"Invalid input argument, len %zu rxbuf 0x%p\n",
 			n_rx, rxbuf);
 		return -EINVAL;
 	}
 
-	reg = txbuf[0] << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
 
-	rdreg = cqspi_calc_rdreg(nor, txbuf[0]);
+	rdreg = cqspi_calc_rdreg(nor);
 	writel(rdreg, reg_base + CQSPI_REG_RD_INSTR);
 
 	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
@@ -404,19 +404,19 @@ static int cqspi_command_read(struct spi_nor *nor,
 }
 
 static int cqspi_command_write(struct spi_nor *nor, const u8 opcode,
-			       const u8 *txbuf, const unsigned n_tx)
+			       const u8 *txbuf, size_t n_tx)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
 	unsigned int reg;
 	unsigned int data;
-	u32 write_len;
+	size_t write_len;
 	int ret;
 
 	if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) {
 		dev_err(nor->dev,
-			"Invalid input argument, cmdlen %d txbuf 0x%p\n",
+			"Invalid input argument, cmdlen %zu txbuf 0x%p\n",
 			n_tx, txbuf);
 		return -EINVAL;
 	}
@@ -470,7 +470,7 @@ static int cqspi_read_setup(struct spi_nor *nor)
 	unsigned int reg;
 
 	reg = nor->read_opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
-	reg |= cqspi_calc_rdreg(nor, nor->read_opcode);
+	reg |= cqspi_calc_rdreg(nor);
 
 	/* Setup dummy clock cycles */
 	dummy_clk = nor->read_dummy;
@@ -603,7 +603,7 @@ static int cqspi_write_setup(struct spi_nor *nor)
 	/* Set opcode. */
 	reg = nor->program_opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
 	writel(reg, reg_base + CQSPI_REG_WR_INSTR);
-	reg = cqspi_calc_rdreg(nor, nor->program_opcode);
+	reg = cqspi_calc_rdreg(nor);
 	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
 
 	reg = readl(reg_base + CQSPI_REG_SIZE);
@@ -1050,7 +1050,7 @@ static int cqspi_erase(struct spi_nor *nor, loff_t offs)
 		return ret;
 
 	/* Send write enable, then erase commands. */
-	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
+	ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
 	if (ret)
 		return ret;
 
@@ -1080,18 +1080,19 @@ static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 	mutex_unlock(&cqspi->bus_mutex);
 }
 
-static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len)
 {
 	int ret;
 
 	ret = cqspi_set_protocol(nor, 0);
 	if (!ret)
-		ret = cqspi_command_read(nor, &opcode, 1, buf, len);
+		ret = cqspi_command_read(nor, opcode, buf, len);
 
 	return ret;
 }
 
-static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			   size_t len)
 {
 	int ret;
 
@@ -1216,6 +1217,16 @@ static void cqspi_request_mmap_dma(struct cqspi_st *cqspi)
 	init_completion(&cqspi->rx_dma_complete);
 }
 
+static const struct spi_nor_controller_ops cqspi_controller_ops = {
+	.prepare = cqspi_prep,
+	.unprepare = cqspi_unprep,
+	.read_reg = cqspi_read_reg,
+	.write_reg = cqspi_write_reg,
+	.read = cqspi_read,
+	.write = cqspi_write,
+	.erase = cqspi_erase,
+};
+
 static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 {
 	struct platform_device *pdev = cqspi->pdev;
@@ -1265,14 +1276,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 		nor->dev = dev;
 		spi_nor_set_flash_node(nor, np);
 		nor->priv = f_pdata;
-
-		nor->read_reg = cqspi_read_reg;
-		nor->write_reg = cqspi_write_reg;
-		nor->read = cqspi_read;
-		nor->write = cqspi_write;
-		nor->erase = cqspi_erase;
-		nor->prepare = cqspi_prep;
-		nor->unprepare = cqspi_unprep;
+		nor->controller_ops = &cqspi_controller_ops;
 
 		mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%s.%d",
 					   dev_name(dev), cs);
@@ -1366,10 +1370,8 @@ static int cqspi_probe(struct platform_device *pdev)
 
 	/* Obtain IRQ line. */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "Cannot obtain IRQ.\n");
+	if (irq < 0)
 		return -ENXIO;
-	}
 
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
index 6dac9dd8bf42..a1258216f89d 100644
--- a/drivers/mtd/spi-nor/hisi-sfc.c
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -177,7 +177,7 @@ static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 }
 
 static int hisi_spi_nor_op_reg(struct spi_nor *nor,
-				u8 opcode, int len, u8 optype)
+				u8 opcode, size_t len, u8 optype)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -200,7 +200,7 @@ static int hisi_spi_nor_op_reg(struct spi_nor *nor,
 }
 
 static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-		int len)
+				 size_t len)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -215,7 +215,7 @@ static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 }
 
 static int hisi_spi_nor_write_reg(struct spi_nor *nor, u8 opcode,
-				u8 *buf, int len)
+				  const u8 *buf, size_t len)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -311,6 +311,15 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to,
 	return len;
 }
 
+static const struct spi_nor_controller_ops hisi_controller_ops = {
+	.prepare = hisi_spi_nor_prep,
+	.unprepare = hisi_spi_nor_unprep,
+	.read_reg = hisi_spi_nor_read_reg,
+	.write_reg = hisi_spi_nor_write_reg,
+	.read = hisi_spi_nor_read,
+	.write = hisi_spi_nor_write,
+};
+
 /**
  * Get spi flash device information and register it as a mtd device.
  */
@@ -357,14 +366,8 @@ static int hisi_spi_nor_register(struct device_node *np,
 	}
 	priv->host = host;
 	nor->priv = priv;
+	nor->controller_ops = &hisi_controller_ops;
 
-	nor->prepare = hisi_spi_nor_prep;
-	nor->unprepare = hisi_spi_nor_unprep;
-	nor->read_reg = hisi_spi_nor_read_reg;
-	nor->write_reg = hisi_spi_nor_write_reg;
-	nor->read = hisi_spi_nor_read;
-	nor->write = hisi_spi_nor_write;
-	nor->erase = NULL;
 	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c
index 3cda8e7a68f8..3d8987baea2a 100644
--- a/drivers/mtd/spi-nor/intel-spi-pci.c
+++ b/drivers/mtd/spi-nor/intel-spi-pci.c
@@ -20,6 +20,10 @@ static const struct intel_spi_boardinfo bxt_info = {
 	.type = INTEL_SPI_BXT,
 };
 
+static const struct intel_spi_boardinfo cnl_info = {
+	.type = INTEL_SPI_CNL,
+};
+
 static int intel_spi_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
@@ -61,6 +65,7 @@ static void intel_spi_pci_remove(struct pci_dev *pdev)
 
 static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x02a4), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0x06a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x18e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x19e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x34a4), (unsigned long)&bxt_info },
@@ -68,6 +73,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index 43e55a2e9b27..61d2a0ad2131 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -108,6 +108,10 @@
 #define BXT_FREG_NUM			12
 #define BXT_PR_NUM			6
 
+#define CNL_PR				0x84
+#define CNL_FREG_NUM			6
+#define CNL_PR_NUM			5
+
 #define LVSCC				0xc4
 #define UVSCC				0xc8
 #define ERASE_OPCODE_SHIFT		8
@@ -187,12 +191,16 @@ static void intel_spi_dump_regs(struct intel_spi *ispi)
 		dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
 			readl(ispi->pregs + PR(i)));
 
-	value = readl(ispi->sregs + SSFSTS_CTL);
-	dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
-	dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
-		readl(ispi->sregs + PREOP_OPTYPE));
-	dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0));
-	dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1));
+	if (ispi->sregs) {
+		value = readl(ispi->sregs + SSFSTS_CTL);
+		dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
+		dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
+			readl(ispi->sregs + PREOP_OPTYPE));
+		dev_dbg(ispi->dev, "OPMENU0=0x%08x\n",
+			readl(ispi->sregs + OPMENU0));
+		dev_dbg(ispi->dev, "OPMENU1=0x%08x\n",
+			readl(ispi->sregs + OPMENU1));
+	}
 
 	if (ispi->info->type == INTEL_SPI_BYT)
 		dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
@@ -340,6 +348,13 @@ static int intel_spi_init(struct intel_spi *ispi)
 		ispi->erase_64k = true;
 		break;
 
+	case INTEL_SPI_CNL:
+		ispi->sregs = NULL;
+		ispi->pregs = ispi->base + CNL_PR;
+		ispi->nregions = CNL_FREG_NUM;
+		ispi->pr_num = CNL_PR_NUM;
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -367,6 +382,11 @@ static int intel_spi_init(struct intel_spi *ispi)
 		    !(uvscc & ERASE_64K_OPCODE_MASK))
 			ispi->erase_64k = false;
 
+	if (ispi->sregs == NULL && (ispi->swseq_reg || ispi->swseq_erase)) {
+		dev_err(ispi->dev, "software sequencer not supported, but required\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * Some controllers can only do basic operations using hardware
 	 * sequencer. All other operations are supposed to be carried out
@@ -383,7 +403,7 @@ static int intel_spi_init(struct intel_spi *ispi)
 	val = readl(ispi->base + HSFSTS_CTL);
 	ispi->locked = !!(val & HSFSTS_CTL_FLOCKDN);
 
-	if (ispi->locked) {
+	if (ispi->locked && ispi->sregs) {
 		/*
 		 * BIOS programs allowed opcodes and then locks down the
 		 * register. So read back what opcodes it decided to support.
@@ -426,7 +446,7 @@ static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode, int optype)
 	return 0;
 }
 
-static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len)
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, size_t len)
 {
 	u32 val, status;
 	int ret;
@@ -469,7 +489,7 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len)
 	return 0;
 }
 
-static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len,
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, size_t len,
 			      int optype)
 {
 	u32 val = 0, status;
@@ -535,7 +555,8 @@ static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len,
 	return 0;
 }
 
-static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			      size_t len)
 {
 	struct intel_spi *ispi = nor->priv;
 	int ret;
@@ -555,7 +576,8 @@ static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return intel_spi_read_block(ispi, buf, len);
 }
 
-static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			       size_t len)
 {
 	struct intel_spi *ispi = nor->priv;
 	int ret;
@@ -864,6 +886,14 @@ static void intel_spi_fill_partition(struct intel_spi *ispi,
 	}
 }
 
+static const struct spi_nor_controller_ops intel_spi_controller_ops = {
+	.read_reg = intel_spi_read_reg,
+	.write_reg = intel_spi_write_reg,
+	.read = intel_spi_read,
+	.write = intel_spi_write,
+	.erase = intel_spi_erase,
+};
+
 struct intel_spi *intel_spi_probe(struct device *dev,
 	struct resource *mem, const struct intel_spi_boardinfo *info)
 {
@@ -897,11 +927,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 
 	ispi->nor.dev = ispi->dev;
 	ispi->nor.priv = ispi;
-	ispi->nor.read_reg = intel_spi_read_reg;
-	ispi->nor.write_reg = intel_spi_write_reg;
-	ispi->nor.read = intel_spi_read;
-	ispi->nor.write = intel_spi_write;
-	ispi->nor.erase = intel_spi_erase;
+	ispi->nor.controller_ops = &intel_spi_controller_ops;
 
 	ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps);
 	if (ret) {
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index 34db01ab6cab..b1691680d174 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -151,9 +151,9 @@ static int mtk_nor_execute_cmd(struct mtk_nor *mtk_nor, u8 cmdval)
 }
 
 static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op,
-			    u8 *tx, int txlen, u8 *rx, int rxlen)
+			    const u8 *tx, size_t txlen, u8 *rx, size_t rxlen)
 {
-	int len = 1 + txlen + rxlen;
+	size_t len = 1 + txlen + rxlen;
 	int i, ret, idx;
 
 	if (len > MTK_NOR_MAX_SHIFT)
@@ -193,7 +193,7 @@ static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op,
 }
 
 /* Do a WRSR (Write Status Register) command */
-static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, u8 sr)
+static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, const u8 sr)
 {
 	writeb(sr, mtk_nor->base + MTK_NOR_PRGDATA5_REG);
 	writeb(8, mtk_nor->base + MTK_NOR_CNT_REG);
@@ -354,7 +354,7 @@ static ssize_t mtk_nor_write(struct spi_nor *nor, loff_t to, size_t len,
 	return len;
 }
 
-static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len)
 {
 	int ret;
 	struct mtk_nor *mtk_nor = nor->priv;
@@ -376,8 +376,8 @@ static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return ret;
 }
 
-static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
-			     int len)
+static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			     size_t len)
 {
 	int ret;
 	struct mtk_nor *mtk_nor = nor->priv;
@@ -419,6 +419,13 @@ static int mtk_nor_enable_clk(struct mtk_nor *mtk_nor)
 	return 0;
 }
 
+static const struct spi_nor_controller_ops mtk_controller_ops = {
+	.read_reg = mtk_nor_read_reg,
+	.write_reg = mtk_nor_write_reg,
+	.read = mtk_nor_read,
+	.write = mtk_nor_write,
+};
+
 static int mtk_nor_init(struct mtk_nor *mtk_nor,
 			struct device_node *flash_node)
 {
@@ -438,12 +445,8 @@ static int mtk_nor_init(struct mtk_nor *mtk_nor,
 	nor->dev = mtk_nor->dev;
 	nor->priv = mtk_nor;
 	spi_nor_set_flash_node(nor, flash_node);
+	nor->controller_ops = &mtk_controller_ops;
 
-	/* fill the hooks to spi nor */
-	nor->read = mtk_nor_read;
-	nor->read_reg = mtk_nor_read_reg;
-	nor->write = mtk_nor_write;
-	nor->write_reg = mtk_nor_write_reg;
 	nor->mtd.name = "mtk_nor";
 	/* initialized with NULL */
 	ret = spi_nor_scan(nor, NULL, &hwcaps);
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 4a871587392b..9a5b1a7c636a 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -123,7 +123,8 @@ static int nxp_spifi_set_memory_mode_on(struct nxp_spifi *spifi)
 	return ret;
 }
 
-static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+			      size_t len)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	u32 cmd;
@@ -145,7 +146,8 @@ static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return nxp_spifi_wait_for_cmd(spifi);
 }
 
-static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf,
+			       size_t len)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	u32 cmd;
@@ -263,9 +265,18 @@ static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi)
 static void nxp_spifi_dummy_id_read(struct spi_nor *nor)
 {
 	u8 id[SPI_NOR_MAX_ID_LEN];
-	nor->read_reg(nor, SPINOR_OP_RDID, id, SPI_NOR_MAX_ID_LEN);
+	nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id,
+				      SPI_NOR_MAX_ID_LEN);
 }
 
+static const struct spi_nor_controller_ops nxp_spifi_controller_ops = {
+	.read_reg  = nxp_spifi_read_reg,
+	.write_reg = nxp_spifi_write_reg,
+	.read  = nxp_spifi_read,
+	.write = nxp_spifi_write,
+	.erase = nxp_spifi_erase,
+};
+
 static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 				 struct device_node *np)
 {
@@ -332,11 +343,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 	spifi->nor.dev   = spifi->dev;
 	spi_nor_set_flash_node(&spifi->nor, np);
 	spifi->nor.priv  = spifi;
-	spifi->nor.read  = nxp_spifi_read;
-	spifi->nor.write = nxp_spifi_write;
-	spifi->nor.erase = nxp_spifi_erase;
-	spifi->nor.read_reg  = nxp_spifi_read_reg;
-	spifi->nor.write_reg = nxp_spifi_write_reg;
+	spifi->nor.controller_ops = &nxp_spifi_controller_ops;
 
 	/*
 	 * The first read on a hard reset isn't reliable so do a
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 7acf4a93b592..f4afe123e9dc 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -338,7 +338,7 @@ static ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len,
 	if (nor->spimem)
 		return spi_nor_spimem_read_data(nor, from, len, buf);
 
-	return nor->read(nor, from, len, buf);
+	return nor->controller_ops->read(nor, from, len, buf);
 }
 
 /**
@@ -385,239 +385,172 @@ static ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len,
 	if (nor->spimem)
 		return spi_nor_spimem_write_data(nor, to, len, buf);
 
-	return nor->write(nor, to, len, buf);
+	return nor->controller_ops->write(nor, to, len, buf);
 }
 
-/*
- * Read the status register, returning its value in the location
- * Return the status register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_write_enable() - Set write enable latch with Write Enable command.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_sr(struct spi_nor *nor)
+static int spi_nor_write_enable(struct spi_nor *nor)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_NO_DATA);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDSR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN,
+						     NULL, 0);
 	}
 
-	if (ret < 0) {
-		pr_err("error %d reading SR\n", (int) ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d on Write Enable\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Read the flag status register, returning its value in the location
- * Return the status register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_write_disable() - Send Write Disable instruction to the chip.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_fsr(struct spi_nor *nor)
+static int spi_nor_write_disable(struct spi_nor *nor)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_NO_DATA);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDFSR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRDI,
+						     NULL, 0);
 	}
 
-	if (ret < 0) {
-		pr_err("error %d reading FSR\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d on Write Disable\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Read configuration register, returning its value in the
- * location. Return the configuration register value.
- * Returns negative if error occurred.
+/**
+ * spi_nor_read_sr() - Read the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to a DMA-able buffer where the value of the
+ *              Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int read_cr(struct spi_nor *nor)
+static int spi_nor_read_sr(struct spi_nor *nor, u8 *sr)
 {
 	int ret;
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_DATA_IN(1, sr, 1));
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		ret = nor->read_reg(nor, SPINOR_OP_RDCR, nor->bouncebuf, 1);
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR,
+						    sr, 1);
 	}
 
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading CR\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading SR\n", ret);
 
-	return nor->bouncebuf[0];
+	return ret;
 }
 
-/*
- * Write status register 1 byte
- * Returns negative if error occurred.
+/**
+ * spi_nor_read_fsr() - Read the Flag Status Register.
+ * @nor:	pointer to 'struct spi_nor'
+ * @fsr:	pointer to a DMA-able buffer where the value of the
+ *              Flag Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int write_sr(struct spi_nor *nor, u8 val)
+static int spi_nor_read_fsr(struct spi_nor *nor, u8 *fsr)
 {
-	nor->bouncebuf[0] = val;
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
-
-	return nor->write_reg(nor, SPINOR_OP_WRSR, nor->bouncebuf, 1);
-}
+	int ret;
 
-/*
- * Set write enable latch with Write Enable command.
- * Returns negative if error occurred.
- */
-static int write_enable(struct spi_nor *nor)
-{
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_NO_DATA);
+				   SPI_MEM_OP_DATA_IN(1, fsr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDFSR,
+						    fsr, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading FSR\n", ret);
+
+	return ret;
 }
 
-/*
- * Send write disable instruction to the chip.
+/**
+ * spi_nor_read_cr() - Read the Configuration Register using the
+ * SPINOR_OP_RDCR (35h) command.
+ * @nor:	pointer to 'struct spi_nor'
+ * @cr:		pointer to a DMA-able buffer where the value of the
+ *              Configuration Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
-static int write_disable(struct spi_nor *nor)
+static int spi_nor_read_cr(struct spi_nor *nor, u8 *cr)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_NO_DATA);
+				   SPI_MEM_OP_DATA_IN(1, cr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDCR, cr, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WRDI, NULL, 0);
-}
-
-static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
-{
-	return mtd->priv;
-}
-
-
-static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
-{
-	size_t i;
-
-	for (i = 0; i < size; i++)
-		if (table[i][0] == opcode)
-			return table[i][1];
-
-	/* No conversion found, keep input op code. */
-	return opcode;
-}
-
-static u8 spi_nor_convert_3to4_read(u8 opcode)
-{
-	static const u8 spi_nor_3to4_read[][2] = {
-		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
-		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
-		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
-		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
-		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
-		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
-		{ SPINOR_OP_READ_1_1_8,	SPINOR_OP_READ_1_1_8_4B },
-		{ SPINOR_OP_READ_1_8_8,	SPINOR_OP_READ_1_8_8_4B },
-
-		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
-		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
-		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
-				      ARRAY_SIZE(spi_nor_3to4_read));
-}
-
-static u8 spi_nor_convert_3to4_program(u8 opcode)
-{
-	static const u8 spi_nor_3to4_program[][2] = {
-		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
-		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
-		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
-		{ SPINOR_OP_PP_1_1_8,	SPINOR_OP_PP_1_1_8_4B },
-		{ SPINOR_OP_PP_1_8_8,	SPINOR_OP_PP_1_8_8_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
-				      ARRAY_SIZE(spi_nor_3to4_program));
-}
-
-static u8 spi_nor_convert_3to4_erase(u8 opcode)
-{
-	static const u8 spi_nor_3to4_erase[][2] = {
-		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
-		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
-		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
-	};
-
-	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
-				      ARRAY_SIZE(spi_nor_3to4_erase));
-}
-
-static void spi_nor_set_4byte_opcodes(struct spi_nor *nor)
-{
-	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
-	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
-	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
-
-	if (!spi_nor_has_uniform_erase(nor)) {
-		struct spi_nor_erase_map *map = &nor->params.erase_map;
-		struct spi_nor_erase_type *erase;
-		int i;
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading CR\n", ret);
 
-		for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) {
-			erase = &map->erase_type[i];
-			erase->opcode =
-				spi_nor_convert_3to4_erase(erase->opcode);
-		}
-	}
+	return ret;
 }
 
+/**
+ * macronix_set_4byte() - Set 4-byte address mode for Macronix flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int macronix_set_4byte(struct spi_nor *nor, bool enable)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(enable ?
@@ -628,26 +561,55 @@ static int macronix_set_4byte(struct spi_nor *nor, bool enable)
 				  SPI_MEM_OP_NO_DUMMY,
 				  SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor,
+						     enable ? SPINOR_OP_EN4B :
+							      SPINOR_OP_EX4B,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B,
-			      NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret);
+
+	return ret;
 }
 
+/**
+ * st_micron_set_4byte() - Set 4-byte address mode for ST and Micron flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int st_micron_set_4byte(struct spi_nor *nor, bool enable)
 {
 	int ret;
 
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
 	ret = macronix_set_4byte(nor, enable);
-	write_disable(nor);
+	if (ret)
+		return ret;
 
-	return ret;
+	return spi_nor_write_disable(nor);
 }
 
+/**
+ * spansion_set_4byte() - Set 4-byte address mode for Spansion flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spansion_set_4byte(struct spi_nor *nor, bool enable)
 {
+	int ret;
+
 	nor->bouncebuf[0] = enable << 7;
 
 	if (nor->spimem) {
@@ -657,14 +619,29 @@ static int spansion_set_4byte(struct spi_nor *nor, bool enable)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_BRWR,
+						     nor->bouncebuf, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_BRWR, nor->bouncebuf, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret);
+
+	return ret;
 }
 
+/**
+ * spi_nor_write_ear() - Write Extended Address Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @ear:	value to write to the Extended Address Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
 {
+	int ret;
+
 	nor->bouncebuf[0] = ear;
 
 	if (nor->spimem) {
@@ -674,12 +651,26 @@ static int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREAR,
+						     nor->bouncebuf, 1);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_WREAR, nor->bouncebuf, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d writing EAR\n", ret);
+
+	return ret;
 }
 
+/**
+ * winbond_set_4byte() - Set 4-byte address mode for Winbond flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @enable:	true to enter the 4-byte address mode, false to exit the 4-byte
+ *		address mode.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int winbond_set_4byte(struct spi_nor *nor, bool enable)
 {
 	int ret;
@@ -693,15 +684,29 @@ static int winbond_set_4byte(struct spi_nor *nor, bool enable)
 	 * Register to be set to 1, so all 3-byte-address reads come from the
 	 * second 16M. We must clear the register to enable normal behavior.
 	 */
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
 	ret = spi_nor_write_ear(nor, 0);
-	write_disable(nor);
+	if (ret)
+		return ret;
 
-	return ret;
+	return spi_nor_write_disable(nor);
 }
 
+/**
+ * spi_nor_xread_sr() - Read the Status Register on S3AN flashes.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to a DMA-able buffer where the value of the
+ *              Status Register will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_XRDSR, 1),
@@ -709,27 +714,44 @@ static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_IN(1, sr, 1));
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_XRDSR,
+						    sr, 1);
 	}
 
-	return nor->read_reg(nor, SPINOR_OP_XRDSR, sr, 1);
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading XRDSR\n", ret);
+
+	return ret;
 }
 
+/**
+ * s3an_sr_ready() - Query the Status Register of the S3AN flash to see if the
+ * flash is ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int s3an_sr_ready(struct spi_nor *nor)
 {
 	int ret;
 
 	ret = spi_nor_xread_sr(nor, nor->bouncebuf);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+	if (ret)
 		return ret;
-	}
 
 	return !!(nor->bouncebuf[0] & XSR_RDY);
 }
 
-static int spi_nor_clear_sr(struct spi_nor *nor)
+/**
+ * spi_nor_clear_sr() - Clear the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ */
+static void spi_nor_clear_sr(struct spi_nor *nor)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 1),
@@ -737,20 +759,33 @@ static int spi_nor_clear_sr(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLSR,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CLSR, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d clearing SR\n", ret);
 }
 
+/**
+ * spi_nor_sr_ready() - Query the Status Register to see if the flash is ready
+ * for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_sr_ready(struct spi_nor *nor)
 {
-	int sr = read_sr(nor);
-	if (sr < 0)
-		return sr;
+	int ret = spi_nor_read_sr(nor, nor->bouncebuf);
+
+	if (ret)
+		return ret;
 
-	if (nor->flags & SNOR_F_USE_CLSR && sr & (SR_E_ERR | SR_P_ERR)) {
-		if (sr & SR_E_ERR)
+	if (nor->flags & SNOR_F_USE_CLSR &&
+	    nor->bouncebuf[0] & (SR_E_ERR | SR_P_ERR)) {
+		if (nor->bouncebuf[0] & SR_E_ERR)
 			dev_err(nor->dev, "Erase Error occurred\n");
 		else
 			dev_err(nor->dev, "Programming Error occurred\n");
@@ -759,11 +794,17 @@ static int spi_nor_sr_ready(struct spi_nor *nor)
 		return -EIO;
 	}
 
-	return !(sr & SR_WIP);
+	return !(nor->bouncebuf[0] & SR_WIP);
 }
 
-static int spi_nor_clear_fsr(struct spi_nor *nor)
+/**
+ * spi_nor_clear_fsr() - Clear the Flag Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ */
+static void spi_nor_clear_fsr(struct spi_nor *nor)
 {
+	int ret;
+
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 1),
@@ -771,25 +812,37 @@ static int spi_nor_clear_fsr(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLFSR,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CLFSR, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d clearing FSR\n", ret);
 }
 
+/**
+ * spi_nor_fsr_ready() - Query the Flag Status Register to see if the flash is
+ * ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_fsr_ready(struct spi_nor *nor)
 {
-	int fsr = read_fsr(nor);
-	if (fsr < 0)
-		return fsr;
+	int ret = spi_nor_read_fsr(nor, nor->bouncebuf);
 
-	if (fsr & (FSR_E_ERR | FSR_P_ERR)) {
-		if (fsr & FSR_E_ERR)
+	if (ret)
+		return ret;
+
+	if (nor->bouncebuf[0] & (FSR_E_ERR | FSR_P_ERR)) {
+		if (nor->bouncebuf[0] & FSR_E_ERR)
 			dev_err(nor->dev, "Erase operation failed.\n");
 		else
 			dev_err(nor->dev, "Program operation failed.\n");
 
-		if (fsr & FSR_PT_ERR)
+		if (nor->bouncebuf[0] & FSR_PT_ERR)
 			dev_err(nor->dev,
 			"Attempted to modify a protected sector.\n");
 
@@ -797,9 +850,15 @@ static int spi_nor_fsr_ready(struct spi_nor *nor)
 		return -EIO;
 	}
 
-	return fsr & FSR_READY;
+	return nor->bouncebuf[0] & FSR_READY;
 }
 
+/**
+ * spi_nor_ready() - Query the flash to see if it is ready for new commands.
+ * @nor:	pointer to 'struct spi_nor'.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_ready(struct spi_nor *nor)
 {
 	int sr, fsr;
@@ -816,9 +875,13 @@ static int spi_nor_ready(struct spi_nor *nor)
 	return sr && fsr;
 }
 
-/*
- * Service routine to read status register until ready, or timeout occurs.
- * Returns non-zero if error.
+/**
+ * spi_nor_wait_till_ready_with_timeout() - Service routine to read the
+ * Status Register until ready, or timeout occurs.
+ * @nor:		pointer to "struct spi_nor".
+ * @timeout_jiffies:	jiffies to wait until timeout.
+ *
+ * Return: 0 on success, -errno otherwise.
  */
 static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor,
 						unsigned long timeout_jiffies)
@@ -841,24 +904,305 @@ static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor,
 		cond_resched();
 	}
 
-	dev_err(nor->dev, "flash operation timed out\n");
+	dev_dbg(nor->dev, "flash operation timed out\n");
 
 	return -ETIMEDOUT;
 }
 
+/**
+ * spi_nor_wait_till_ready() - Wait for a predefined amount of time for the
+ * flash to be ready, or timeout occurs.
+ * @nor:	pointer to "struct spi_nor".
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
 static int spi_nor_wait_till_ready(struct spi_nor *nor)
 {
 	return spi_nor_wait_till_ready_with_timeout(nor,
 						    DEFAULT_READY_WAIT_JIFFIES);
 }
 
-/*
- * Erase the whole flash memory
+/**
+ * spi_nor_write_sr() - Write the Status Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr:		pointer to DMA-able buffer to write to the Status Register.
+ * @len:	number of bytes to write to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len)
+{
+	int ret;
+
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_OUT(len, sr, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR,
+						     sr, len);
+	}
+
+	if (ret) {
+		dev_dbg(nor->dev, "error %d writing SR\n", ret);
+		return ret;
+	}
+
+	return spi_nor_wait_till_ready(nor);
+}
+
+/**
+ * spi_nor_write_sr1_and_check() - Write one byte to the Status Register 1 and
+ * ensure that the byte written match the received value.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr1_and_check(struct spi_nor *nor, u8 sr1)
+{
+	int ret;
+
+	nor->bouncebuf[0] = sr1;
+
+	ret = spi_nor_write_sr(nor, nor->bouncebuf, 1);
+	if (ret)
+		return ret;
+
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	if (nor->bouncebuf[0] != sr1) {
+		dev_dbg(nor->dev, "SR1: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_16bit_sr_and_check() - Write the Status Register 1 and the
+ * Status Register 2 in one shot. Ensure that the byte written in the Status
+ * Register 1 match the received value, and that the 16-bit Write did not
+ * affect what was already in the Status Register 2.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register 1.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1)
+{
+	int ret;
+	u8 *sr_cr = nor->bouncebuf;
+	u8 cr_written;
+
+	/* Make sure we don't overwrite the contents of Status Register 2. */
+	if (!(nor->flags & SNOR_F_NO_READ_CR)) {
+		ret = spi_nor_read_cr(nor, &sr_cr[1]);
+		if (ret)
+			return ret;
+	} else if (nor->params.quad_enable) {
+		/*
+		 * If the Status Register 2 Read command (35h) is not
+		 * supported, we should at least be sure we don't
+		 * change the value of the SR2 Quad Enable bit.
+		 *
+		 * We can safely assume that when the Quad Enable method is
+		 * set, the value of the QE bit is one, as a consequence of the
+		 * nor->params.quad_enable() call.
+		 *
+		 * We can safely assume that the Quad Enable bit is present in
+		 * the Status Register 2 at BIT(1). According to the JESD216
+		 * revB standard, BFPT DWORDS[15], bits 22:20, the 16-bit
+		 * Write Status (01h) command is available just for the cases
+		 * in which the QE bit is described in SR2 at BIT(1).
+		 */
+		sr_cr[1] = SR2_QUAD_EN_BIT1;
+	} else {
+		sr_cr[1] = 0;
+	}
+
+	sr_cr[0] = sr1;
+
+	ret = spi_nor_write_sr(nor, sr_cr, 2);
+	if (ret)
+		return ret;
+
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return 0;
+
+	cr_written = sr_cr[1];
+
+	ret = spi_nor_read_cr(nor, &sr_cr[1]);
+	if (ret)
+		return ret;
+
+	if (cr_written != sr_cr[1]) {
+		dev_dbg(nor->dev, "CR: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_16bit_cr_and_check() - Write the Status Register 1 and the
+ * Configuration Register in one shot. Ensure that the byte written in the
+ * Configuration Register match the received value, and that the 16-bit Write
+ * did not affect what was already in the Status Register 1.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @cr:		byte value to be written to the Configuration Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_16bit_cr_and_check(struct spi_nor *nor, u8 cr)
+{
+	int ret;
+	u8 *sr_cr = nor->bouncebuf;
+	u8 sr_written;
+
+	/* Keep the current value of the Status Register 1. */
+	ret = spi_nor_read_sr(nor, sr_cr);
+	if (ret)
+		return ret;
+
+	sr_cr[1] = cr;
+
+	ret = spi_nor_write_sr(nor, sr_cr, 2);
+	if (ret)
+		return ret;
+
+	sr_written = sr_cr[0];
+
+	ret = spi_nor_read_sr(nor, sr_cr);
+	if (ret)
+		return ret;
+
+	if (sr_written != sr_cr[0]) {
+		dev_dbg(nor->dev, "SR: Read back test failed\n");
+		return -EIO;
+	}
+
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return 0;
+
+	ret = spi_nor_read_cr(nor, &sr_cr[1]);
+	if (ret)
+		return ret;
+
+	if (cr != sr_cr[1]) {
+		dev_dbg(nor->dev, "CR: read back test failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * spi_nor_write_sr_and_check() - Write the Status Register 1 and ensure that
+ * the byte written match the received value without affecting other bits in the
+ * Status Register 1 and 2.
+ * @nor:	pointer to a 'struct spi_nor'.
+ * @sr1:	byte value to be written to the Status Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 sr1)
+{
+	if (nor->flags & SNOR_F_HAS_16BIT_SR)
+		return spi_nor_write_16bit_sr_and_check(nor, sr1);
+
+	return spi_nor_write_sr1_and_check(nor, sr1);
+}
+
+/**
+ * spi_nor_write_sr2() - Write the Status Register 2 using the
+ * SPINOR_OP_WRSR2 (3eh) command.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr2:	pointer to DMA-able buffer to write to the Status Register 2.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_write_sr2(struct spi_nor *nor, const u8 *sr2)
+{
+	int ret;
+
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		return ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_OUT(1, sr2, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR2,
+						     sr2, 1);
+	}
+
+	if (ret) {
+		dev_dbg(nor->dev, "error %d writing SR2\n", ret);
+		return ret;
+	}
+
+	return spi_nor_wait_till_ready(nor);
+}
+
+/**
+ * spi_nor_read_sr2() - Read the Status Register 2 using the
+ * SPINOR_OP_RDSR2 (3fh) command.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @sr2:	pointer to DMA-able buffer where the value of the
+ *		Status Register 2 will be written.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
+{
+	int ret;
+
+	if (nor->spimem) {
+		struct spi_mem_op op =
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1),
+				   SPI_MEM_OP_NO_ADDR,
+				   SPI_MEM_OP_NO_DUMMY,
+				   SPI_MEM_OP_DATA_IN(1, sr2, 1));
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR2,
+						    sr2, 1);
+	}
+
+	if (ret)
+		dev_dbg(nor->dev, "error %d reading SR2\n", ret);
+
+	return ret;
+}
+
+/**
+ * spi_nor_erase_chip() - Erase the entire flash memory.
+ * @nor:	pointer to 'struct spi_nor'.
  *
- * Returns 0 if successful, non-zero otherwise.
+ * Return: 0 on success, -errno otherwise.
  */
-static int erase_chip(struct spi_nor *nor)
+static int spi_nor_erase_chip(struct spi_nor *nor)
 {
+	int ret;
+
 	dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10));
 
 	if (nor->spimem) {
@@ -868,10 +1212,99 @@ static int erase_chip(struct spi_nor *nor)
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
-		return spi_mem_exec_op(nor->spimem, &op);
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CHIP_ERASE,
+						     NULL, 0);
 	}
 
-	return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0);
+	if (ret)
+		dev_dbg(nor->dev, "error %d erasing chip\n", ret);
+
+	return ret;
+}
+
+static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
+{
+	return mtd->priv;
+}
+
+static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == opcode)
+			return table[i][1];
+
+	/* No conversion found, keep input op code. */
+	return opcode;
+}
+
+static u8 spi_nor_convert_3to4_read(u8 opcode)
+{
+	static const u8 spi_nor_3to4_read[][2] = {
+		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
+		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
+		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
+		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
+		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
+		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
+		{ SPINOR_OP_READ_1_1_8,	SPINOR_OP_READ_1_1_8_4B },
+		{ SPINOR_OP_READ_1_8_8,	SPINOR_OP_READ_1_8_8_4B },
+
+		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
+		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
+		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
+				      ARRAY_SIZE(spi_nor_3to4_read));
+}
+
+static u8 spi_nor_convert_3to4_program(u8 opcode)
+{
+	static const u8 spi_nor_3to4_program[][2] = {
+		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
+		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
+		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
+		{ SPINOR_OP_PP_1_1_8,	SPINOR_OP_PP_1_1_8_4B },
+		{ SPINOR_OP_PP_1_8_8,	SPINOR_OP_PP_1_8_8_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
+				      ARRAY_SIZE(spi_nor_3to4_program));
+}
+
+static u8 spi_nor_convert_3to4_erase(u8 opcode)
+{
+	static const u8 spi_nor_3to4_erase[][2] = {
+		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
+		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
+		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
+				      ARRAY_SIZE(spi_nor_3to4_erase));
+}
+
+static void spi_nor_set_4byte_opcodes(struct spi_nor *nor)
+{
+	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
+	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
+	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
+
+	if (!spi_nor_has_uniform_erase(nor)) {
+		struct spi_nor_erase_map *map = &nor->params.erase_map;
+		struct spi_nor_erase_type *erase;
+		int i;
+
+		for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) {
+			erase = &map->erase_type[i];
+			erase->opcode =
+				spi_nor_convert_3to4_erase(erase->opcode);
+		}
+	}
 }
 
 static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
@@ -880,10 +1313,9 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 	mutex_lock(&nor->lock);
 
-	if (nor->prepare) {
-		ret = nor->prepare(nor, ops);
+	if (nor->controller_ops &&  nor->controller_ops->prepare) {
+		ret = nor->controller_ops->prepare(nor, ops);
 		if (ret) {
-			dev_err(nor->dev, "failed in the preparation.\n");
 			mutex_unlock(&nor->lock);
 			return ret;
 		}
@@ -893,8 +1325,8 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 {
-	if (nor->unprepare)
-		nor->unprepare(nor, ops);
+	if (nor->controller_ops && nor->controller_ops->unprepare)
+		nor->controller_ops->unprepare(nor, ops);
 	mutex_unlock(&nor->lock);
 }
 
@@ -935,9 +1367,6 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 
 	addr = spi_nor_convert_addr(nor, addr);
 
-	if (nor->erase)
-		return nor->erase(nor, addr);
-
 	if (nor->spimem) {
 		struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 1),
@@ -946,6 +1375,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 				   SPI_MEM_OP_NO_DATA);
 
 		return spi_mem_exec_op(nor->spimem, &op);
+	} else if (nor->controller_ops->erase) {
+		return nor->controller_ops->erase(nor, addr);
 	}
 
 	/*
@@ -957,8 +1388,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 		addr >>= 8;
 	}
 
-	return nor->write_reg(nor, nor->erase_opcode, nor->bouncebuf,
-			      nor->addr_width);
+	return nor->controller_ops->write_reg(nor, nor->erase_opcode,
+					      nor->bouncebuf, nor->addr_width);
 }
 
 /**
@@ -1208,7 +1639,9 @@ static int spi_nor_erase_multi_sectors(struct spi_nor *nor, u64 addr, u32 len)
 	list_for_each_entry_safe(cmd, next, &erase_list, list) {
 		nor->erase_opcode = cmd->opcode;
 		while (cmd->count) {
-			write_enable(nor);
+			ret = spi_nor_write_enable(nor);
+			if (ret)
+				goto destroy_erase_cmd_list;
 
 			ret = spi_nor_erase_sector(nor, addr);
 			if (ret)
@@ -1263,12 +1696,13 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
 		unsigned long timeout;
 
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto erase_err;
 
-		if (erase_chip(nor)) {
-			ret = -EIO;
+		ret = spi_nor_erase_chip(nor);
+		if (ret)
 			goto erase_err;
-		}
 
 		/*
 		 * Scale the timeout linearly with the size of the flash, with
@@ -1291,7 +1725,9 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	/* "sector"-at-a-time erase */
 	} else if (spi_nor_has_uniform_erase(nor)) {
 		while (len) {
-			write_enable(nor);
+			ret = spi_nor_write_enable(nor);
+			if (ret)
+				goto erase_err;
 
 			ret = spi_nor_erase_sector(nor, addr);
 			if (ret)
@@ -1312,7 +1748,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 			goto erase_err;
 	}
 
-	write_disable(nor);
+	ret = spi_nor_write_disable(nor);
 
 erase_err:
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
@@ -1320,27 +1756,6 @@ erase_err:
 	return ret;
 }
 
-/* Write status register and ensure bits in mask match written values */
-static int write_sr_and_check(struct spi_nor *nor, u8 status_new, u8 mask)
-{
-	int ret;
-
-	write_enable(nor);
-	ret = write_sr(nor, status_new);
-	if (ret)
-		return ret;
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret)
-		return ret;
-
-	ret = read_sr(nor);
-	if (ret < 0)
-		return ret;
-
-	return ((ret & mask) != (status_new & mask)) ? -EIO : 0;
-}
-
 static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs,
 				 uint64_t *len)
 {
@@ -1433,16 +1848,18 @@ static int stm_is_unlocked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
 static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
 	struct mtd_info *mtd = &nor->mtd;
-	int status_old, status_new;
+	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
 	bool use_top;
 
-	status_old = read_sr(nor);
-	if (status_old < 0)
-		return status_old;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	status_old = nor->bouncebuf[0];
 
 	/* If nothing in our range is unlocked, we don't need to do anything */
 	if (stm_is_locked_sr(nor, ofs, len, status_old))
@@ -1502,7 +1919,7 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if ((status_new & mask) < (status_old & mask))
 		return -EINVAL;
 
-	return write_sr_and_check(nor, status_new, mask);
+	return spi_nor_write_sr_and_check(nor, status_new);
 }
 
 /*
@@ -1513,16 +1930,18 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
 	struct mtd_info *mtd = &nor->mtd;
-	int status_old, status_new;
+	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
 	bool use_top;
 
-	status_old = read_sr(nor);
-	if (status_old < 0)
-		return status_old;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
+
+	status_old = nor->bouncebuf[0];
 
 	/* If nothing in our range is locked, we don't need to do anything */
 	if (stm_is_unlocked_sr(nor, ofs, len, status_old))
@@ -1585,7 +2004,7 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if ((status_new & mask) > (status_old & mask))
 		return -EINVAL;
 
-	return write_sr_and_check(nor, status_new, mask);
+	return spi_nor_write_sr_and_check(nor, status_new);
 }
 
 /*
@@ -1597,13 +2016,13 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
  */
 static int stm_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len)
 {
-	int status;
+	int ret;
 
-	status = read_sr(nor);
-	if (status < 0)
-		return status;
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
+	if (ret)
+		return ret;
 
-	return stm_is_locked_sr(nor, ofs, len, status);
+	return stm_is_locked_sr(nor, ofs, len, nor->bouncebuf[0]);
 }
 
 static const struct spi_nor_locking_ops stm_locking_ops = {
@@ -1657,242 +2076,59 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	return ret;
 }
 
-/*
- * Write status Register and configuration register with 2 bytes
- * The first byte will be written to the status register, while the
- * second byte will be written to the configuration register.
- * Return negative if error occurred.
- */
-static int write_sr_cr(struct spi_nor *nor, u8 *sr_cr)
-{
-	int ret;
-
-	write_enable(nor);
-
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(2, sr_cr, 1));
-
-		ret = spi_mem_exec_op(nor->spimem, &op);
-	} else {
-		ret = nor->write_reg(nor, SPINOR_OP_WRSR, sr_cr, 2);
-	}
-
-	if (ret < 0) {
-		dev_err(nor->dev,
-			"error while writing configuration register\n");
-		return -EINVAL;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret) {
-		dev_err(nor->dev,
-			"timeout while writing configuration register\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-/**
- * macronix_quad_enable() - set QE bit in Status Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Status Register.
- *
- * bit 6 of the Status Register is the QE bit for Macronix like QSPI memories.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int macronix_quad_enable(struct spi_nor *nor)
-{
-	int ret, val;
-
-	val = read_sr(nor);
-	if (val < 0)
-		return val;
-	if (val & SR_QUAD_EN_MX)
-		return 0;
-
-	write_enable(nor);
-
-	write_sr(nor, val | SR_QUAD_EN_MX);
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret)
-		return ret;
-
-	ret = read_sr(nor);
-	if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) {
-		dev_err(nor->dev, "Macronix Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /**
- * spansion_quad_enable() - set QE bit in Configuraiton Register.
+ * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status
+ * Register 1.
  * @nor:	pointer to a 'struct spi_nor'
  *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function is kept for legacy purpose because it has been used for a
- * long time without anybody complaining but it should be considered as
- * deprecated and maybe buggy.
- * First, this function doesn't care about the previous values of the Status
- * and Configuration Registers when it sets the QE bit (bit 1) in the
- * Configuration Register: all other bits are cleared, which may have unwanted
- * side effects like removing some block protections.
- * Secondly, it uses the Read Configuration Register (35h) instruction though
- * some very old and few memories don't support this instruction. If a pull-up
- * resistor is present on the MISO/IO1 line, we might still be able to pass the
- * "read back" test because the QSPI memory doesn't recognize the command,
- * so leaves the MISO/IO1 line state unchanged, hence read_cr() returns 0xFF.
- *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
+ * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spansion_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor)
 {
-	u8 *sr_cr = nor->bouncebuf;
 	int ret;
 
-	sr_cr[0] = 0;
-	sr_cr[1] = CR_QUAD_EN_SPAN;
-	ret = write_sr_cr(nor, sr_cr);
+	ret = spi_nor_read_sr(nor, nor->bouncebuf);
 	if (ret)
 		return ret;
 
-	/* read back and check it */
-	ret = read_cr(nor);
-	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
-		dev_err(nor->dev, "Spansion Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * spansion_no_read_cr_quad_enable() - set QE bit in Configuration Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function should be used with QSPI memories not supporting the Read
- * Configuration Register (35h) instruction.
- *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spansion_no_read_cr_quad_enable(struct spi_nor *nor)
-{
-	u8 *sr_cr = nor->bouncebuf;
-	int ret;
+	if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)
+		return 0;
 
-	/* Keep the current value of the Status Register. */
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while reading status register\n");
-		return -EINVAL;
-	}
-	sr_cr[0] = ret;
-	sr_cr[1] = CR_QUAD_EN_SPAN;
+	nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6;
 
-	return write_sr_cr(nor, sr_cr);
+	return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * spansion_read_cr_quad_enable() - set QE bit in Configuration Register.
- * @nor:	pointer to a 'struct spi_nor'
- *
- * Set the Quad Enable (QE) bit in the Configuration Register.
- * This function should be used with QSPI memories supporting the Read
- * Configuration Register (35h) instruction.
+ * spi_nor_sr2_bit1_quad_enable() - set the Quad Enable BIT(1) in the Status
+ * Register 2.
+ * @nor:       pointer to a 'struct spi_nor'.
  *
- * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI
- * memories.
+ * Bit 1 of the Status Register 2 is the QE bit for Spansion like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spansion_read_cr_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor)
 {
-	struct device *dev = nor->dev;
-	u8 *sr_cr = nor->bouncebuf;
 	int ret;
 
-	/* Check current Quad Enable bit value. */
-	ret = read_cr(nor);
-	if (ret < 0) {
-		dev_err(dev, "error while reading configuration register\n");
-		return -EINVAL;
-	}
-
-	if (ret & CR_QUAD_EN_SPAN)
-		return 0;
+	if (nor->flags & SNOR_F_NO_READ_CR)
+		return spi_nor_write_16bit_cr_and_check(nor, SR2_QUAD_EN_BIT1);
 
-	sr_cr[1] = ret | CR_QUAD_EN_SPAN;
-
-	/* Keep the current value of the Status Register. */
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(dev, "error while reading status register\n");
-		return -EINVAL;
-	}
-	sr_cr[0] = ret;
-
-	ret = write_sr_cr(nor, sr_cr);
+	ret = spi_nor_read_cr(nor, nor->bouncebuf);
 	if (ret)
 		return ret;
 
-	/* Read back and check it. */
-	ret = read_cr(nor);
-	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
-		dev_err(nor->dev, "Spansion Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int spi_nor_write_sr2(struct spi_nor *nor, u8 *sr2)
-{
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, sr2, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
-
-	return nor->write_reg(nor, SPINOR_OP_WRSR2, sr2, 1);
-}
-
-static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
-{
-	if (nor->spimem) {
-		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1),
-				   SPI_MEM_OP_NO_ADDR,
-				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, sr2, 1));
-
-		return spi_mem_exec_op(nor->spimem, &op);
-	}
+	if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)
+		return 0;
 
-	return nor->read_reg(nor, SPINOR_OP_RDSR2, sr2, 1);
+	return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * sr2_bit7_quad_enable() - set QE bit in Status Register 2.
+ * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2.
  * @nor:	pointer to a 'struct spi_nor'
  *
  * Set the Quad Enable (QE) bit in the Status Register 2.
@@ -1903,10 +2139,11 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int sr2_bit7_quad_enable(struct spi_nor *nor)
+static int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor)
 {
 	u8 *sr2 = nor->bouncebuf;
 	int ret;
+	u8 sr2_written;
 
 	/* Check current Quad Enable bit value. */
 	ret = spi_nor_read_sr2(nor, sr2);
@@ -1918,117 +2155,23 @@ static int sr2_bit7_quad_enable(struct spi_nor *nor)
 	/* Update the Quad Enable bit. */
 	*sr2 |= SR2_QUAD_EN_BIT7;
 
-	write_enable(nor);
-
 	ret = spi_nor_write_sr2(nor, sr2);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while writing status register 2\n");
-		return -EINVAL;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "timeout while writing status register 2\n");
+	if (ret)
 		return ret;
-	}
+
+	sr2_written = *sr2;
 
 	/* Read back and check it. */
 	ret = spi_nor_read_sr2(nor, sr2);
-	if (!(ret > 0 && (*sr2 & SR2_QUAD_EN_BIT7))) {
-		dev_err(nor->dev, "SR2 Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * spi_nor_clear_sr_bp() - clear the Status Register Block Protection bits.
- * @nor:        pointer to a 'struct spi_nor'
- *
- * Read-modify-write function that clears the Block Protection bits from the
- * Status Register without affecting other bits.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spi_nor_clear_sr_bp(struct spi_nor *nor)
-{
-	int ret;
-	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
-
-	ret = read_sr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while reading status register\n");
-		return ret;
-	}
-
-	write_enable(nor);
-
-	ret = write_sr(nor, ret & ~mask);
-	if (ret) {
-		dev_err(nor->dev, "write to status register failed\n");
-		return ret;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
-		dev_err(nor->dev, "timeout while writing status register\n");
-	return ret;
-}
-
-/**
- * spi_nor_spansion_clear_sr_bp() - clear the Status Register Block Protection
- * bits on spansion flashes.
- * @nor:        pointer to a 'struct spi_nor'
- *
- * Read-modify-write function that clears the Block Protection bits from the
- * Status Register without affecting other bits. The function is tightly
- * coupled with the spansion_quad_enable() function. Both assume that the Write
- * Register with 16 bits, together with the Read Configuration Register (35h)
- * instructions are supported.
- *
- * Return: 0 on success, -errno otherwise.
- */
-static int spi_nor_spansion_clear_sr_bp(struct spi_nor *nor)
-{
-	int ret;
-	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
-	u8 *sr_cr =  nor->bouncebuf;
-
-	/* Check current Quad Enable bit value. */
-	ret = read_cr(nor);
-	if (ret < 0) {
-		dev_err(nor->dev,
-			"error while reading configuration register\n");
 		return ret;
-	}
-
-	/*
-	 * When the configuration register Quad Enable bit is one, only the
-	 * Write Status (01h) command with two data bytes may be used.
-	 */
-	if (ret & CR_QUAD_EN_SPAN) {
-		sr_cr[1] = ret;
 
-		ret = read_sr(nor);
-		if (ret < 0) {
-			dev_err(nor->dev,
-				"error while reading status register\n");
-			return ret;
-		}
-		sr_cr[0] = ret & ~mask;
-
-		ret = write_sr_cr(nor, sr_cr);
-		if (ret)
-			dev_err(nor->dev, "16-bit write register failed\n");
-		return ret;
+	if (*sr2 != sr2_written) {
+		dev_dbg(nor->dev, "SR2: Read back test failed\n");
+		return -EIO;
 	}
 
-	/*
-	 * If the Quad Enable bit is zero, use the Write Status (01h) command
-	 * with one data byte.
-	 */
-	return spi_nor_clear_sr_bp(nor);
+	return 0;
 }
 
 /* Used when the "_ext_id" is two bytes at most */
@@ -2136,7 +2279,7 @@ static void gd25q256_default_init(struct spi_nor *nor)
 	 * indicate the quad_enable method for this case, we need
 	 * to set it in the default_init fixup hook.
 	 */
-	nor->params.quad_enable = macronix_quad_enable;
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
 }
 
 static struct spi_nor_fixups gd25q256_fixups = {
@@ -2179,6 +2322,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "en25q64",    INFO(0x1c3017, 0, 64 * 1024,  128, SECT_4K) },
 	{ "en25q80a",   INFO(0x1c3014, 0, 64 * 1024,   16,
 			SECT_4K | SPI_NOR_DUAL_READ) },
+	{ "en25qh16",   INFO(0x1c7015, 0, 64 * 1024,   32,
+			SECT_4K | SPI_NOR_DUAL_READ) },
 	{ "en25qh32",   INFO(0x1c7016, 0, 64 * 1024,   64, 0) },
 	{ "en25qh64",   INFO(0x1c7017, 0, 64 * 1024,  128,
 			SECT_4K | SPI_NOR_DUAL_READ) },
@@ -2267,6 +2412,10 @@ static const struct flash_info spi_nor_ids[] = {
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "is25wp128",  INFO(0x9d7018, 0, 64 * 1024, 256,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "is25wp256", INFO(0x9d7019, 0, 64 * 1024, 512,
+			    SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			    SPI_NOR_4B_OPCODES)
+		       .fixups = &is25lp256_fixups },
 
 	/* Macronix */
 	{ "mx25l512e",   INFO(0xc22010, 0, 64 * 1024,   1, SECT_4K) },
@@ -2482,6 +2631,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "w25q256jvm", INFO(0xef7019, 0, 64 * 1024, 512,
 			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "w25q256jw", INFO(0xef6019, 0, 64 * 1024, 512,
+			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024,
 			SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) },
 
@@ -2520,11 +2671,11 @@ static const struct flash_info *spi_nor_read_id(struct spi_nor *nor)
 
 		tmp = spi_mem_exec_op(nor->spimem, &op);
 	} else {
-		tmp = nor->read_reg(nor, SPINOR_OP_RDID, id,
-				    SPI_NOR_MAX_ID_LEN);
+		tmp = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id,
+						    SPI_NOR_MAX_ID_LEN);
 	}
-	if (tmp < 0) {
-		dev_err(nor->dev, "error %d reading JEDEC ID\n", tmp);
+	if (tmp) {
+		dev_dbg(nor->dev, "error %d reading JEDEC ID\n", tmp);
 		return ERR_PTR(tmp);
 	}
 
@@ -2544,7 +2695,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 			size_t *retlen, u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	int ret;
+	ssize_t ret;
 
 	dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
 
@@ -2583,7 +2734,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	size_t actual;
+	size_t actual = 0;
 	int ret;
 
 	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
@@ -2592,26 +2743,28 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	write_enable(nor);
+	ret = spi_nor_write_enable(nor);
+	if (ret)
+		goto out;
 
 	nor->sst_write_second = false;
 
-	actual = to % 2;
 	/* Start write from odd address. */
-	if (actual) {
+	if (to % 2) {
 		nor->program_opcode = SPINOR_OP_BP;
 
 		/* write one byte. */
 		ret = spi_nor_write_data(nor, to, 1, buf);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
+			goto out;
+
+		to++;
+		actual++;
 	}
-	to += actual;
 
 	/* Write out most of the data here. */
 	for (; actual < len - 1; actual += 2) {
@@ -2620,39 +2773,44 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		/* write two bytes. */
 		ret = spi_nor_write_data(nor, to, 2, buf + actual);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 2, "While writing 2 bytes written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 2, "While writing 2 bytes written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
+			goto out;
 		to += 2;
 		nor->sst_write_second = true;
 	}
 	nor->sst_write_second = false;
 
-	write_disable(nor);
+	ret = spi_nor_write_disable(nor);
+	if (ret)
+		goto out;
+
 	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
-		goto sst_write_err;
+		goto out;
 
 	/* Write out trailing byte if it exists. */
 	if (actual != len) {
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto out;
 
 		nor->program_opcode = SPINOR_OP_BP;
 		ret = spi_nor_write_data(nor, to, 1, buf + actual);
 		if (ret < 0)
-			goto sst_write_err;
-		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
-		     (int)ret);
+			goto out;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto sst_write_err;
-		write_disable(nor);
+			goto out;
+
 		actual += 1;
+
+		ret = spi_nor_write_disable(nor);
 	}
-sst_write_err:
+out:
 	*retlen += actual;
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
 	return ret;
@@ -2701,7 +2859,10 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 		addr = spi_nor_convert_addr(nor, addr);
 
-		write_enable(nor);
+		ret = spi_nor_write_enable(nor);
+		if (ret)
+			goto write_err;
+
 		ret = spi_nor_write_data(nor, addr, page_remain, buf + i);
 		if (ret < 0)
 			goto write_err;
@@ -2722,13 +2883,21 @@ write_err:
 static int spi_nor_check(struct spi_nor *nor)
 {
 	if (!nor->dev ||
-	    (!nor->spimem &&
-	    (!nor->read || !nor->write || !nor->read_reg ||
-	      !nor->write_reg))) {
+	    (!nor->spimem && !nor->controller_ops) ||
+	    (!nor->spimem && nor->controller_ops &&
+	    (!nor->controller_ops->read ||
+	     !nor->controller_ops->write ||
+	     !nor->controller_ops->read_reg ||
+	     !nor->controller_ops->write_reg))) {
 		pr_err("spi-nor: please fill all the necessary fields!\n");
 		return -EINVAL;
 	}
 
+	if (nor->spimem && nor->controller_ops) {
+		dev_err(nor->dev, "nor->spimem and nor->controller_ops are mutually exclusive, please set just one of them.\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -2738,10 +2907,8 @@ static int s3an_nor_setup(struct spi_nor *nor,
 	int ret;
 
 	ret = spi_nor_xread_sr(nor, nor->bouncebuf);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+	if (ret)
 		return ret;
-	}
 
 	nor->erase_opcode = SPINOR_OP_XSE;
 	nor->program_opcode = SPINOR_OP_XPP;
@@ -2865,7 +3032,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
  */
 static int spi_nor_read_raw(struct spi_nor *nor, u32 addr, size_t len, u8 *buf)
 {
-	int ret;
+	ssize_t ret;
 
 	while (len) {
 		ret = spi_nor_read_data(nor, addr, len, buf);
@@ -3489,20 +3656,39 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor,
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT1_BUGGY:
+		/*
+		 * Writing only one byte to the Status Register has the
+		 * side-effect of clearing Status Register 2.
+		 */
 	case BFPT_DWORD15_QER_SR2_BIT1_NO_RD:
-		params->quad_enable = spansion_no_read_cr_quad_enable;
+		/*
+		 * Read Configuration Register (35h) instruction is not
+		 * supported.
+		 */
+		nor->flags |= SNOR_F_HAS_16BIT_SR | SNOR_F_NO_READ_CR;
+		params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR1_BIT6:
-		params->quad_enable = macronix_quad_enable;
+		nor->flags &= ~SNOR_F_HAS_16BIT_SR;
+		params->quad_enable = spi_nor_sr1_bit6_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT7:
-		params->quad_enable = sr2_bit7_quad_enable;
+		nor->flags &= ~SNOR_F_HAS_16BIT_SR;
+		params->quad_enable = spi_nor_sr2_bit7_quad_enable;
 		break;
 
 	case BFPT_DWORD15_QER_SR2_BIT1:
-		params->quad_enable = spansion_read_cr_quad_enable;
+		/*
+		 * JESD216 rev B or later does not specify if writing only one
+		 * byte to the Status Register clears or not the Status
+		 * Register 2, so let's be cautious and keep the default
+		 * assumption of a 16-bit Write Status (01h) command.
+		 */
+		nor->flags |= SNOR_F_HAS_16BIT_SR;
+
+		params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 		break;
 
 	default:
@@ -4101,7 +4287,7 @@ static int spi_nor_parse_sfdp(struct spi_nor *nor,
 		err = spi_nor_read_sfdp(nor, sizeof(header),
 					psize, param_headers);
 		if (err < 0) {
-			dev_err(dev, "failed to read SFDP parameter headers\n");
+			dev_dbg(dev, "failed to read SFDP parameter headers\n");
 			goto exit;
 		}
 	}
@@ -4348,7 +4534,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the (Fast) Read command. */
 	err = spi_nor_select_read(nor, shared_mask);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select read settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4356,7 +4542,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the Page Program command. */
 	err = spi_nor_select_pp(nor, shared_mask);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select write settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4364,7 +4550,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 	/* Select the Sector Erase command. */
 	err = spi_nor_select_erase(nor);
 	if (err) {
-		dev_err(nor->dev,
+		dev_dbg(nor->dev,
 			"can't select erase settings supported by both the SPI controller and memory.\n");
 		return err;
 	}
@@ -4381,12 +4567,32 @@ static int spi_nor_setup(struct spi_nor *nor,
 	return nor->params.setup(nor, hwcaps);
 }
 
+static void atmel_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
+static void intel_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
+static void issi_set_default_init(struct spi_nor *nor)
+{
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
+}
+
 static void macronix_set_default_init(struct spi_nor *nor)
 {
-	nor->params.quad_enable = macronix_quad_enable;
+	nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable;
 	nor->params.set_4byte = macronix_set_4byte;
 }
 
+static void sst_set_default_init(struct spi_nor *nor)
+{
+	nor->flags |= SNOR_F_HAS_LOCK;
+}
+
 static void st_micron_set_default_init(struct spi_nor *nor)
 {
 	nor->flags |= SNOR_F_HAS_LOCK;
@@ -4408,6 +4614,18 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor)
 {
 	/* Init flash parameters based on MFR */
 	switch (JEDEC_MFR(nor->info)) {
+	case SNOR_MFR_ATMEL:
+		atmel_set_default_init(nor);
+		break;
+
+	case SNOR_MFR_INTEL:
+		intel_set_default_init(nor);
+		break;
+
+	case SNOR_MFR_ISSI:
+		issi_set_default_init(nor);
+		break;
+
 	case SNOR_MFR_MACRONIX:
 		macronix_set_default_init(nor);
 		break;
@@ -4417,6 +4635,10 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor)
 		st_micron_set_default_init(nor);
 		break;
 
+	case SNOR_MFR_SST:
+		sst_set_default_init(nor);
+		break;
+
 	case SNOR_MFR_WINBOND:
 		winbond_set_default_init(nor);
 		break;
@@ -4465,9 +4687,11 @@ static void spi_nor_info_init_params(struct spi_nor *nor)
 	u8 i, erase_mask;
 
 	/* Initialize legacy flash parameters and settings. */
-	params->quad_enable = spansion_quad_enable;
+	params->quad_enable = spi_nor_sr2_bit1_quad_enable;
 	params->set_4byte = spansion_set_4byte;
 	params->setup = spi_nor_default_setup;
+	/* Default to 16-bit Write Status (01h) Command */
+	nor->flags |= SNOR_F_HAS_16BIT_SR;
 
 	/* Set SPI NOR sizes. */
 	params->size = (u64)info->sector_size * info->n_sectors;
@@ -4675,25 +4899,36 @@ static int spi_nor_quad_enable(struct spi_nor *nor)
 	return nor->params.quad_enable(nor);
 }
 
+/**
+ * spi_nor_unlock_all() - Unlocks the entire flash memory array.
+ * @nor:	pointer to a 'struct spi_nor'.
+ *
+ * Some SPI NOR flashes are write protected by default after a power-on reset
+ * cycle, in order to avoid inadvertent writes during power-up. Backward
+ * compatibility imposes to unlock the entire flash memory array at power-up
+ * by default.
+ */
+static int spi_nor_unlock_all(struct spi_nor *nor)
+{
+	if (nor->flags & SNOR_F_HAS_LOCK)
+		return spi_nor_unlock(&nor->mtd, 0, nor->params.size);
+
+	return 0;
+}
+
 static int spi_nor_init(struct spi_nor *nor)
 {
 	int err;
 
-	if (nor->clear_sr_bp) {
-		if (nor->params.quad_enable == spansion_quad_enable)
-			nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
-
-		err = nor->clear_sr_bp(nor);
-		if (err) {
-			dev_err(nor->dev,
-				"fail to clear block protection bits\n");
-			return err;
-		}
+	err = spi_nor_quad_enable(nor);
+	if (err) {
+		dev_dbg(nor->dev, "quad mode not supported\n");
+		return err;
 	}
 
-	err = spi_nor_quad_enable(nor);
+	err = spi_nor_unlock_all(nor);
 	if (err) {
-		dev_err(nor->dev, "quad mode not supported\n");
+		dev_dbg(nor->dev, "Failed to unlock the entire flash memory array\n");
 		return err;
 	}
 
@@ -4761,7 +4996,7 @@ static int spi_nor_set_addr_width(struct spi_nor *nor)
 	}
 
 	if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) {
-		dev_err(nor->dev, "address width is too large: %u\n",
+		dev_dbg(nor->dev, "address width is too large: %u\n",
 			nor->addr_width);
 		return -EINVAL;
 	}
@@ -4879,16 +5114,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	if (info->flags & SPI_NOR_HAS_LOCK)
 		nor->flags |= SNOR_F_HAS_LOCK;
 
-	/*
-	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
-	 * with the software protection bits set.
-	 */
-	if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL ||
-	    JEDEC_MFR(nor->info) == SNOR_MFR_INTEL ||
-	    JEDEC_MFR(nor->info) == SNOR_MFR_SST ||
-	    nor->info->flags & SPI_NOR_HAS_LOCK)
-		nor->clear_sr_bp = spi_nor_clear_sr_bp;
-
 	/* Init flash parameters based on flash_info struct and SFDP */
 	spi_nor_init_params(nor);
 
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index a1dff92ceedf..0f847d510950 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -509,11 +509,9 @@ static const struct file_operations eraseblk_count_fops = {
  */
 int ubi_debugfs_init_dev(struct ubi_device *ubi)
 {
-	int err, n;
 	unsigned long ubi_num = ubi->ubi_num;
-	const char *fname;
-	struct dentry *dent;
 	struct ubi_debug_info *d = &ubi->dbg;
+	int n;
 
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
@@ -522,95 +520,52 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi)
 		     ubi->ubi_num);
 	if (n == UBI_DFS_DIR_LEN) {
 		/* The array size is too small */
-		fname = UBI_DFS_DIR_NAME;
-		dent = ERR_PTR(-EINVAL);
-		goto out;
+		return -EINVAL;
 	}
 
-	fname = d->dfs_dir_name;
-	dent = debugfs_create_dir(fname, dfs_rootdir);
-	if (IS_ERR_OR_NULL(dent))
-		goto out;
-	d->dfs_dir = dent;
-
-	fname = "chk_gen";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_gen = dent;
-
-	fname = "chk_io";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_io = dent;
-
-	fname = "chk_fastmap";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_chk_fastmap = dent;
-
-	fname = "tst_disable_bgt";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_disable_bgt = dent;
-
-	fname = "tst_emulate_bitflips";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_bitflips = dent;
-
-	fname = "tst_emulate_io_failures";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_io_failures = dent;
-
-	fname = "tst_emulate_power_cut";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_emulate_power_cut = dent;
-
-	fname = "tst_emulate_power_cut_min";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_power_cut_min = dent;
-
-	fname = "tst_emulate_power_cut_max";
-	dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num,
-				   &dfs_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
-	d->dfs_power_cut_max = dent;
-
-	fname = "detailed_erase_block_info";
-	dent = debugfs_create_file(fname, S_IRUSR, d->dfs_dir, (void *)ubi_num,
-				   &eraseblk_count_fops);
-	if (IS_ERR_OR_NULL(dent))
-		goto out_remove;
+	d->dfs_dir = debugfs_create_dir(d->dfs_dir_name, dfs_rootdir);
 
-	return 0;
+	d->dfs_chk_gen = debugfs_create_file("chk_gen", S_IWUSR, d->dfs_dir,
+					     (void *)ubi_num, &dfs_fops);
 
-out_remove:
-	debugfs_remove_recursive(d->dfs_dir);
-out:
-	err = dent ? PTR_ERR(dent) : -ENODEV;
-	ubi_err(ubi, "cannot create \"%s\" debugfs file or directory, error %d\n",
-		fname, err);
-	return err;
+	d->dfs_chk_io = debugfs_create_file("chk_io", S_IWUSR, d->dfs_dir,
+					    (void *)ubi_num, &dfs_fops);
+
+	d->dfs_chk_fastmap = debugfs_create_file("chk_fastmap", S_IWUSR,
+						 d->dfs_dir, (void *)ubi_num,
+						 &dfs_fops);
+
+	d->dfs_disable_bgt = debugfs_create_file("tst_disable_bgt", S_IWUSR,
+						 d->dfs_dir, (void *)ubi_num,
+						 &dfs_fops);
+
+	d->dfs_emulate_bitflips = debugfs_create_file("tst_emulate_bitflips",
+						      S_IWUSR, d->dfs_dir,
+						      (void *)ubi_num,
+						      &dfs_fops);
+
+	d->dfs_emulate_io_failures = debugfs_create_file("tst_emulate_io_failures",
+							 S_IWUSR, d->dfs_dir,
+							 (void *)ubi_num,
+							 &dfs_fops);
+
+	d->dfs_emulate_power_cut = debugfs_create_file("tst_emulate_power_cut",
+						       S_IWUSR, d->dfs_dir,
+						       (void *)ubi_num,
+						       &dfs_fops);
+
+	d->dfs_power_cut_min = debugfs_create_file("tst_emulate_power_cut_min",
+						   S_IWUSR, d->dfs_dir,
+						   (void *)ubi_num, &dfs_fops);
+
+	d->dfs_power_cut_max = debugfs_create_file("tst_emulate_power_cut_max",
+						   S_IWUSR, d->dfs_dir,
+						   (void *)ubi_num, &dfs_fops);
+
+	debugfs_create_file("detailed_erase_block_info", S_IRUSR, d->dfs_dir,
+			    (void *)ubi_num, &eraseblk_count_fops);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 8c79bad2a9a5..4f2e6910c623 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	struct bond_vlan_tag *tags;
 
 	if (is_vlan_dev(upper) &&
-	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+	    bond->dev->lower_level == upper->lower_level - 1) {
 		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 931d9d935686..62f65573eb04 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1733,8 +1733,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
-	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
-
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1816,7 +1814,8 @@ err_detach:
 	slave_disable_netpoll(new_slave);
 
 err_close:
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
 
 err_restore_mac:
@@ -1956,9 +1955,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
-		bond->nest_level = SINGLE_DEPTH_NESTING;
-	} else {
-		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
@@ -2017,7 +2013,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	else
 		dev_set_mtu(slave_dev, slave->original_mtu);
 
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 
 	bond_free_slave(slave);
 
@@ -2086,8 +2083,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 	ignore_updelay = !rcu_dereference(bond->curr_active_slave);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
-		slave->link_new_state = slave->link;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
 
@@ -2121,7 +2117,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			}
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				commit++;
 				continue;
 			}
@@ -2158,7 +2154,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				slave->delay = 0;
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 				ignore_updelay = false;
 				continue;
@@ -2196,7 +2192,7 @@ static void bond_miimon_commit(struct bonding *bond)
 	struct slave *slave, *primary;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			/* For 802.3ad mode, check current slave speed and
 			 * duplex again in case its port was disabled after
@@ -2268,8 +2264,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
-				  slave->new_link);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				  slave->link_new_state);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2677,13 +2673,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2708,7 +2704,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2739,8 +2735,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			goto re_arm;
 
 		bond_for_each_slave(bond, slave, iter) {
-			if (slave->new_link != BOND_LINK_NOCHANGE)
-				slave->link = slave->new_link;
+			if (slave->link_new_state != BOND_LINK_NOCHANGE)
+				slave->link = slave->link_new_state;
 		}
 
 		if (slave_state_changed) {
@@ -2763,9 +2759,9 @@ re_arm:
 }
 
 /* Called to inspect slaves for active-backup mode ARP monitor link state
- * changes.  Sets new_link in slaves to specify what action should take
- * place for the slave.  Returns 0 if no changes are found, >0 if changes
- * to link states must be committed.
+ * changes.  Sets proposed link state in slaves to specify what action
+ * should take place for the slave.  Returns 0 if no changes are found, >0
+ * if changes to link states must be committed.
  *
  * Called with rcu_read_lock held.
  */
@@ -2777,12 +2773,12 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 	int commit = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, last_rx, 1)) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 			}
 			continue;
@@ -2810,7 +2806,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (!bond_is_active_slave(slave) &&
 		    !rcu_access_pointer(bond->current_arp_slave) &&
 		    !bond_time_in_interval(bond, last_rx, 3)) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 
@@ -2823,7 +2819,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (bond_is_active_slave(slave) &&
 		    (!bond_time_in_interval(bond, trans_start, 2) ||
 		     !bond_time_in_interval(bond, last_rx, 2))) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 	}
@@ -2843,7 +2839,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
@@ -2893,8 +2889,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			continue;
 
 		default:
-			slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n",
-				  slave->new_link);
+			slave_err(bond->dev, slave->dev,
+				  "impossible: link_new_state %d on slave\n",
+				  slave->link_new_state);
 			continue;
 		}
 
@@ -3442,13 +3439,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
-static int bond_get_nest_level(struct net_device *bond_dev)
-{
-	struct bonding *bond = netdev_priv(bond_dev);
-
-	return bond->nest_level;
-}
-
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3457,7 +3447,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4039,7 +4029,7 @@ out:
 		 * this to-be-skipped slave to send a packet out.
 		 */
 		old_arr = rtnl_dereference(bond->slave_arr);
-		for (idx = 0; idx < old_arr->count; idx++) {
+		for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) {
 			if (skipslave == old_arr->arr[idx]) {
 				old_arr->arr[idx] =
 				    old_arr->arr[old_arr->count-1];
@@ -4268,7 +4258,6 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
-	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4296,7 +4285,6 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
-	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
@@ -4365,6 +4353,7 @@ static void bond_uninit(struct net_device *bond_dev)
 
 	list_del(&bond->bond_list);
 
+	lockdep_unregister_key(&bond->stats_lock_key);
 	bond_debug_unregister(bond);
 }
 
@@ -4768,8 +4757,9 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
-	bond->nest_level = SINGLE_DEPTH_NESTING;
-	netdev_lockdep_set_classes(bond_dev);
+	spin_lock_init(&bond->stats_lock);
+	lockdep_register_key(&bond->stats_lock_key);
+	lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 606b7d8ffe13..8e9f5620c9a2 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -52,6 +52,7 @@
 #define CONTROL_EX_PDR		BIT(8)
 
 /* control register */
+#define CONTROL_SWR		BIT(15)
 #define CONTROL_TEST		BIT(7)
 #define CONTROL_CCE		BIT(6)
 #define CONTROL_DISABLE_AR	BIT(5)
@@ -97,6 +98,9 @@
 #define BTR_TSEG2_SHIFT		12
 #define BTR_TSEG2_MASK		(0x7 << BTR_TSEG2_SHIFT)
 
+/* interrupt register */
+#define INT_STS_PENDING		0x8000
+
 /* brp extension register */
 #define BRP_EXT_BRPE_MASK	0x0f
 #define BRP_EXT_BRPE_SHIFT	0
@@ -569,6 +573,26 @@ static void c_can_configure_msg_objects(struct net_device *dev)
 				   IF_MCONT_RCV_EOB);
 }
 
+static int c_can_software_reset(struct net_device *dev)
+{
+	struct c_can_priv *priv = netdev_priv(dev);
+	int retry = 0;
+
+	if (priv->type != BOSCH_D_CAN)
+		return 0;
+
+	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_SWR | CONTROL_INIT);
+	while (priv->read_reg(priv, C_CAN_CTRL_REG) & CONTROL_SWR) {
+		msleep(20);
+		if (retry++ > 100) {
+			netdev_err(dev, "CCTRL: software reset failed\n");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Configure C_CAN chip:
  * - enable/disable auto-retransmission
@@ -578,6 +602,11 @@ static void c_can_configure_msg_objects(struct net_device *dev)
 static int c_can_chip_config(struct net_device *dev)
 {
 	struct c_can_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = c_can_software_reset(dev);
+	if (err)
+		return err;
 
 	/* enable automatic retransmission */
 	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR);
@@ -886,6 +915,9 @@ static int c_can_handle_state_change(struct net_device *dev,
 	struct can_berr_counter bec;
 
 	switch (error_type) {
+	case C_CAN_NO_ERROR:
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		break;
 	case C_CAN_ERROR_WARNING:
 		/* error warning state */
 		priv->can.can_stats.error_warning++;
@@ -916,6 +948,13 @@ static int c_can_handle_state_change(struct net_device *dev,
 				ERR_CNT_RP_SHIFT;
 
 	switch (error_type) {
+	case C_CAN_NO_ERROR:
+		/* error warning state */
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+		break;
 	case C_CAN_ERROR_WARNING:
 		/* error warning state */
 		cf->can_id |= CAN_ERR_CRTL;
@@ -1029,10 +1068,16 @@ static int c_can_poll(struct napi_struct *napi, int quota)
 	u16 curr, last = priv->last_status;
 	int work_done = 0;
 
-	priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG);
-	/* Ack status on C_CAN. D_CAN is self clearing */
-	if (priv->type != BOSCH_D_CAN)
-		priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
+	/* Only read the status register if a status interrupt was pending */
+	if (atomic_xchg(&priv->sie_pending, 0)) {
+		priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG);
+		/* Ack status on C_CAN. D_CAN is self clearing */
+		if (priv->type != BOSCH_D_CAN)
+			priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
+	} else {
+		/* no change detected ... */
+		curr = last;
+	}
 
 	/* handle state changes */
 	if ((curr & STATUS_EWARN) && (!(last & STATUS_EWARN))) {
@@ -1054,11 +1099,17 @@ static int c_can_poll(struct napi_struct *napi, int quota)
 	/* handle bus recovery events */
 	if ((!(curr & STATUS_BOFF)) && (last & STATUS_BOFF)) {
 		netdev_dbg(dev, "left bus off state\n");
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		work_done += c_can_handle_state_change(dev, C_CAN_ERROR_PASSIVE);
 	}
+
 	if ((!(curr & STATUS_EPASS)) && (last & STATUS_EPASS)) {
 		netdev_dbg(dev, "left error passive state\n");
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		work_done += c_can_handle_state_change(dev, C_CAN_ERROR_WARNING);
+	}
+
+	if ((!(curr & STATUS_EWARN)) && (last & STATUS_EWARN)) {
+		netdev_dbg(dev, "left error warning state\n");
+		work_done += c_can_handle_state_change(dev, C_CAN_NO_ERROR);
 	}
 
 	/* handle lec errors on the bus */
@@ -1083,10 +1134,16 @@ static irqreturn_t c_can_isr(int irq, void *dev_id)
 {
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct c_can_priv *priv = netdev_priv(dev);
+	int reg_int;
 
-	if (!priv->read_reg(priv, C_CAN_INT_REG))
+	reg_int = priv->read_reg(priv, C_CAN_INT_REG);
+	if (!reg_int)
 		return IRQ_NONE;
 
+	/* save for later use */
+	if (reg_int & INT_STS_PENDING)
+		atomic_set(&priv->sie_pending, 1);
+
 	/* disable all interrupts and schedule the NAPI */
 	c_can_irq_control(priv, false);
 	napi_schedule(&priv->napi);
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index 8acdc7fa4792..d5567a7c1c6d 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -198,6 +198,7 @@ struct c_can_priv {
 	struct net_device *dev;
 	struct device *device;
 	atomic_t tx_active;
+	atomic_t sie_pending;
 	unsigned long tx_dir;
 	int last_status;
 	u16 (*read_reg) (const struct c_can_priv *priv, enum reg index);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index ac86be52b461..1c88c361938c 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -848,6 +848,7 @@ void of_can_transceiver(struct net_device *dev)
 		return;
 
 	ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max);
+	of_node_put(dn);
 	if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max))
 		netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n");
 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index dc5695dffc2e..57f9a2f51085 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -677,6 +677,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr)
 	struct can_frame *cf;
 	bool rx_errors = false, tx_errors = false;
 	u32 timestamp;
+	int err;
 
 	timestamp = priv->read(&regs->timer) << 16;
 
@@ -725,7 +726,9 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr)
 	if (tx_errors)
 		dev->stats.tx_errors++;
 
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		dev->stats.rx_fifo_errors++;
 }
 
 static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
@@ -738,6 +741,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
 	int flt;
 	struct can_berr_counter bec;
 	u32 timestamp;
+	int err;
 
 	timestamp = priv->read(&regs->timer) << 16;
 
@@ -769,7 +773,9 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
 	if (unlikely(new_state == CAN_STATE_BUS_OFF))
 		can_bus_off(dev);
 
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		dev->stats.rx_fifo_errors++;
 }
 
 static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *offload)
@@ -1188,6 +1194,7 @@ static int flexcan_chip_start(struct net_device *dev)
 		reg_mecr = priv->read(&regs->mecr);
 		reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS;
 		priv->write(reg_mecr, &regs->mecr);
+		reg_mecr |= FLEXCAN_MECR_ECCDIS;
 		reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK |
 			      FLEXCAN_MECR_FANCEI_MSK);
 		priv->write(reg_mecr, &regs->mecr);
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 6ac4c35f247a..38ea5e600fb8 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -107,7 +107,7 @@ static int m_can_plat_probe(struct platform_device *pdev)
 
 	mcan_class->is_peripheral = false;
 
-	platform_set_drvdata(pdev, mcan_class->dev);
+	platform_set_drvdata(pdev, mcan_class->net);
 
 	m_can_init_ram(mcan_class);
 
@@ -166,8 +166,6 @@ static int __maybe_unused m_can_runtime_resume(struct device *dev)
 	if (err)
 		clk_disable_unprepare(mcan_class->hclk);
 
-	m_can_class_resume(dev);
-
 	return err;
 }
 
diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index e6a668ee7730..84cae167e42f 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -107,37 +107,95 @@ static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b)
 	return cb_b->timestamp - cb_a->timestamp;
 }
 
-static struct sk_buff *can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n)
+/**
+ * can_rx_offload_offload_one() - Read one CAN frame from HW
+ * @offload: pointer to rx_offload context
+ * @n: number of mailbox to read
+ *
+ * The task of this function is to read a CAN frame from mailbox @n
+ * from the device and return the mailbox's content as a struct
+ * sk_buff.
+ *
+ * If the struct can_rx_offload::skb_queue exceeds the maximal queue
+ * length (struct can_rx_offload::skb_queue_len_max) or no skb can be
+ * allocated, the mailbox contents is discarded by reading it into an
+ * overflow buffer. This way the mailbox is marked as free by the
+ * driver.
+ *
+ * Return: A pointer to skb containing the CAN frame on success.
+ *
+ *         NULL if the mailbox @n is empty.
+ *
+ *         ERR_PTR() in case of an error
+ */
+static struct sk_buff *
+can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n)
 {
-	struct sk_buff *skb = NULL;
+	struct sk_buff *skb = NULL, *skb_error = NULL;
 	struct can_rx_offload_cb *cb;
 	struct can_frame *cf;
 	int ret;
 
-	/* If queue is full or skb not available, read to discard mailbox */
-	if (likely(skb_queue_len(&offload->skb_queue) <=
-		   offload->skb_queue_len_max))
+	if (likely(skb_queue_len(&offload->skb_queue) <
+		   offload->skb_queue_len_max)) {
 		skb = alloc_can_skb(offload->dev, &cf);
+		if (unlikely(!skb))
+			skb_error = ERR_PTR(-ENOMEM);	/* skb alloc failed */
+	} else {
+		skb_error = ERR_PTR(-ENOBUFS);		/* skb_queue is full */
+	}
 
-	if (!skb) {
+	/* If queue is full or skb not available, drop by reading into
+	 * overflow buffer.
+	 */
+	if (unlikely(skb_error)) {
 		struct can_frame cf_overflow;
 		u32 timestamp;
 
 		ret = offload->mailbox_read(offload, &cf_overflow,
 					    &timestamp, n);
-		if (ret)
-			offload->dev->stats.rx_dropped++;
 
-		return NULL;
+		/* Mailbox was empty. */
+		if (unlikely(!ret))
+			return NULL;
+
+		/* Mailbox has been read and we're dropping it or
+		 * there was a problem reading the mailbox.
+		 *
+		 * Increment error counters in any case.
+		 */
+		offload->dev->stats.rx_dropped++;
+		offload->dev->stats.rx_fifo_errors++;
+
+		/* There was a problem reading the mailbox, propagate
+		 * error value.
+		 */
+		if (unlikely(ret < 0))
+			return ERR_PTR(ret);
+
+		return skb_error;
 	}
 
 	cb = can_rx_offload_get_cb(skb);
 	ret = offload->mailbox_read(offload, cf, &cb->timestamp, n);
-	if (!ret) {
+
+	/* Mailbox was empty. */
+	if (unlikely(!ret)) {
 		kfree_skb(skb);
 		return NULL;
 	}
 
+	/* There was a problem reading the mailbox, propagate error value. */
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+
+		offload->dev->stats.rx_dropped++;
+		offload->dev->stats.rx_fifo_errors++;
+
+		return ERR_PTR(ret);
+	}
+
+	/* Mailbox was read. */
 	return skb;
 }
 
@@ -157,8 +215,8 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pen
 			continue;
 
 		skb = can_rx_offload_offload_one(offload, i);
-		if (!skb)
-			break;
+		if (IS_ERR_OR_NULL(skb))
+			continue;
 
 		__skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare);
 	}
@@ -188,7 +246,13 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload)
 	struct sk_buff *skb;
 	int received = 0;
 
-	while ((skb = can_rx_offload_offload_one(offload, 0))) {
+	while (1) {
+		skb = can_rx_offload_offload_one(offload, 0);
+		if (IS_ERR(skb))
+			continue;
+		if (!skb)
+			break;
+
 		skb_queue_tail(&offload->skb_queue, skb);
 		received++;
 	}
@@ -207,8 +271,10 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
 	unsigned long flags;
 
 	if (skb_queue_len(&offload->skb_queue) >
-	    offload->skb_queue_len_max)
-		return -ENOMEM;
+	    offload->skb_queue_len_max) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
 
 	cb = can_rx_offload_get_cb(skb);
 	cb->timestamp = timestamp;
@@ -250,8 +316,10 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb)
 {
 	if (skb_queue_len(&offload->skb_queue) >
-	    offload->skb_queue_len_max)
-		return -ENOMEM;
+	    offload->skb_queue_len_max) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
 
 	skb_queue_tail(&offload->skb_queue, skb);
 	can_rx_offload_schedule(offload);
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index bb6032211043..0a9f42e5fedf 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -617,6 +617,7 @@ err_free_chan:
 	sl->tty = NULL;
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
+	free_netdev(sl->dev);
 
 err_exit:
 	rtnl_unlock();
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index bee9f7b8dad6..bb20a9b75cc6 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -717,6 +717,7 @@ static void mcp251x_restart_work_handler(struct work_struct *ws)
 	if (priv->after_suspend) {
 		mcp251x_hw_reset(spi);
 		mcp251x_setup(net, spi);
+		priv->force_quit = 0;
 		if (priv->after_suspend & AFTER_SUSPEND_RESTART) {
 			mcp251x_set_normal_mode(spi);
 		} else if (priv->after_suspend & AFTER_SUSPEND_UP) {
@@ -728,7 +729,6 @@ static void mcp251x_restart_work_handler(struct work_struct *ws)
 			mcp251x_hw_sleep(spi);
 		}
 		priv->after_suspend = 0;
-		priv->force_quit = 0;
 	}
 
 	if (priv->restart_tx) {
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index f8b19eef5d26..31ad364a89bb 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -73,6 +73,7 @@ MODULE_VERSION(HECC_MODULE_VERSION);
  */
 #define HECC_MAX_RX_MBOX	(HECC_MAX_MAILBOXES - HECC_MAX_TX_MBOX)
 #define HECC_RX_FIRST_MBOX	(HECC_MAX_MAILBOXES - 1)
+#define HECC_RX_LAST_MBOX	(HECC_MAX_TX_MBOX)
 
 /* TI HECC module registers */
 #define HECC_CANME		0x0	/* Mailbox enable */
@@ -82,7 +83,7 @@ MODULE_VERSION(HECC_MODULE_VERSION);
 #define HECC_CANTA		0x10	/* Transmission acknowledge */
 #define HECC_CANAA		0x14	/* Abort acknowledge */
 #define HECC_CANRMP		0x18	/* Receive message pending */
-#define HECC_CANRML		0x1C	/* Remote message lost */
+#define HECC_CANRML		0x1C	/* Receive message lost */
 #define HECC_CANRFP		0x20	/* Remote frame pending */
 #define HECC_CANGAM		0x24	/* SECC only:Global acceptance mask */
 #define HECC_CANMC		0x28	/* Master control */
@@ -149,6 +150,8 @@ MODULE_VERSION(HECC_MODULE_VERSION);
 #define HECC_BUS_ERROR		(HECC_CANES_FE | HECC_CANES_BE |\
 				HECC_CANES_CRCE | HECC_CANES_SE |\
 				HECC_CANES_ACKE)
+#define HECC_CANES_FLAGS	(HECC_BUS_ERROR | HECC_CANES_BO |\
+				HECC_CANES_EP | HECC_CANES_EW)
 
 #define HECC_CANMCF_RTR		BIT(4)	/* Remote transmit request */
 
@@ -382,8 +385,18 @@ static void ti_hecc_start(struct net_device *ndev)
 		hecc_set_bit(priv, HECC_CANMIM, mbx_mask);
 	}
 
-	/* Prevent message over-write & Enable interrupts */
-	hecc_write(priv, HECC_CANOPC, HECC_SET_REG);
+	/* Enable tx interrupts */
+	hecc_set_bit(priv, HECC_CANMIM, BIT(HECC_MAX_TX_MBOX) - 1);
+
+	/* Prevent message over-write to create a rx fifo, but not for
+	 * the lowest priority mailbox, since that allows detecting
+	 * overflows instead of the hardware silently dropping the
+	 * messages.
+	 */
+	mbx_mask = ~BIT(HECC_RX_LAST_MBOX);
+	hecc_write(priv, HECC_CANOPC, mbx_mask);
+
+	/* Enable interrupts */
 	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANMIL, HECC_SET_REG);
 		hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK |
@@ -400,6 +413,9 @@ static void ti_hecc_stop(struct net_device *ndev)
 {
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
+	/* Disable the CPK; stop sending, erroring and acking */
+	hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
+
 	/* Disable interrupts and disable mailboxes */
 	hecc_write(priv, HECC_CANGIM, 0);
 	hecc_write(priv, HECC_CANMIM, 0);
@@ -508,8 +524,6 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev)
 	hecc_set_bit(priv, HECC_CANME, mbx_mask);
 	spin_unlock_irqrestore(&priv->mbx_lock, flags);
 
-	hecc_clear_bit(priv, HECC_CANMD, mbx_mask);
-	hecc_set_bit(priv, HECC_CANMIM, mbx_mask);
 	hecc_write(priv, HECC_CANTRS, mbx_mask);
 
 	return NETDEV_TX_OK;
@@ -526,8 +540,10 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload,
 					 u32 *timestamp, unsigned int mbxno)
 {
 	struct ti_hecc_priv *priv = rx_offload_to_priv(offload);
-	u32 data;
+	u32 data, mbx_mask;
+	int ret = 1;
 
+	mbx_mask = BIT(mbxno);
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMID);
 	if (data & HECC_CANMID_IDE)
 		cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG;
@@ -548,7 +564,25 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload,
 
 	*timestamp = hecc_read_stamp(priv, mbxno);
 
-	return 1;
+	/* Check for FIFO overrun.
+	 *
+	 * All but the last RX mailbox have activated overwrite
+	 * protection. So skip check for overrun, if we're not
+	 * handling the last RX mailbox.
+	 *
+	 * As the overwrite protection for the last RX mailbox is
+	 * disabled, the CAN core might update while we're reading
+	 * it. This means the skb might be inconsistent.
+	 *
+	 * Return an error to let rx-offload discard this CAN frame.
+	 */
+	if (unlikely(mbxno == HECC_RX_LAST_MBOX &&
+		     hecc_read(priv, HECC_CANRML) & mbx_mask))
+		ret = -ENOBUFS;
+
+	hecc_write(priv, HECC_CANRMP, mbx_mask);
+
+	return ret;
 }
 
 static int ti_hecc_error(struct net_device *ndev, int int_status,
@@ -558,92 +592,73 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
 	struct can_frame *cf;
 	struct sk_buff *skb;
 	u32 timestamp;
+	int err;
 
-	/* propagate the error condition to the can stack */
-	skb = alloc_can_err_skb(ndev, &cf);
-	if (!skb) {
-		if (printk_ratelimit())
-			netdev_err(priv->ndev,
-				   "%s: alloc_can_err_skb() failed\n",
-				   __func__);
-		return -ENOMEM;
-	}
-
-	if (int_status & HECC_CANGIF_WLIF) { /* warning level int */
-		if ((int_status & HECC_CANGIF_BOIF) == 0) {
-			priv->can.state = CAN_STATE_ERROR_WARNING;
-			++priv->can.can_stats.error_warning;
-			cf->can_id |= CAN_ERR_CRTL;
-			if (hecc_read(priv, HECC_CANTEC) > 96)
-				cf->data[1] |= CAN_ERR_CRTL_TX_WARNING;
-			if (hecc_read(priv, HECC_CANREC) > 96)
-				cf->data[1] |= CAN_ERR_CRTL_RX_WARNING;
-		}
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_EW);
-		netdev_dbg(priv->ndev, "Error Warning interrupt\n");
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-	}
-
-	if (int_status & HECC_CANGIF_EPIF) { /* error passive int */
-		if ((int_status & HECC_CANGIF_BOIF) == 0) {
-			priv->can.state = CAN_STATE_ERROR_PASSIVE;
-			++priv->can.can_stats.error_passive;
-			cf->can_id |= CAN_ERR_CRTL;
-			if (hecc_read(priv, HECC_CANTEC) > 127)
-				cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE;
-			if (hecc_read(priv, HECC_CANREC) > 127)
-				cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE;
+	if (err_status & HECC_BUS_ERROR) {
+		/* propagate the error condition to the can stack */
+		skb = alloc_can_err_skb(ndev, &cf);
+		if (!skb) {
+			if (net_ratelimit())
+				netdev_err(priv->ndev,
+					   "%s: alloc_can_err_skb() failed\n",
+					   __func__);
+			return -ENOMEM;
 		}
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_EP);
-		netdev_dbg(priv->ndev, "Error passive interrupt\n");
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-	}
-
-	/* Need to check busoff condition in error status register too to
-	 * ensure warning interrupts don't hog the system
-	 */
-	if ((int_status & HECC_CANGIF_BOIF) || (err_status & HECC_CANES_BO)) {
-		priv->can.state = CAN_STATE_BUS_OFF;
-		cf->can_id |= CAN_ERR_BUSOFF;
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_BO);
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-		/* Disable all interrupts in bus-off to avoid int hog */
-		hecc_write(priv, HECC_CANGIM, 0);
-		++priv->can.can_stats.bus_off;
-		can_bus_off(ndev);
-	}
 
-	if (err_status & HECC_BUS_ERROR) {
 		++priv->can.can_stats.bus_error;
 		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-		if (err_status & HECC_CANES_FE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE);
+		if (err_status & HECC_CANES_FE)
 			cf->data[2] |= CAN_ERR_PROT_FORM;
-		}
-		if (err_status & HECC_CANES_BE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_BE);
+		if (err_status & HECC_CANES_BE)
 			cf->data[2] |= CAN_ERR_PROT_BIT;
-		}
-		if (err_status & HECC_CANES_SE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_SE);
+		if (err_status & HECC_CANES_SE)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
-		}
-		if (err_status & HECC_CANES_CRCE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE);
+		if (err_status & HECC_CANES_CRCE)
 			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
-		}
-		if (err_status & HECC_CANES_ACKE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE);
+		if (err_status & HECC_CANES_ACKE)
 			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
-		}
+
+		timestamp = hecc_read(priv, HECC_CANLNT);
+		err = can_rx_offload_queue_sorted(&priv->offload, skb,
+						  timestamp);
+		if (err)
+			ndev->stats.rx_fifo_errors++;
 	}
 
-	timestamp = hecc_read(priv, HECC_CANLNT);
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	hecc_write(priv, HECC_CANES, HECC_CANES_FLAGS);
 
 	return 0;
 }
 
+static void ti_hecc_change_state(struct net_device *ndev,
+				 enum can_state rx_state,
+				 enum can_state tx_state)
+{
+	struct ti_hecc_priv *priv = netdev_priv(ndev);
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 timestamp;
+	int err;
+
+	skb = alloc_can_err_skb(priv->ndev, &cf);
+	if (unlikely(!skb)) {
+		priv->can.state = max(tx_state, rx_state);
+		return;
+	}
+
+	can_change_state(priv->ndev, cf, tx_state, rx_state);
+
+	if (max(tx_state, rx_state) != CAN_STATE_BUS_OFF) {
+		cf->data[6] = hecc_read(priv, HECC_CANTEC);
+		cf->data[7] = hecc_read(priv, HECC_CANREC);
+	}
+
+	timestamp = hecc_read(priv, HECC_CANLNT);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		ndev->stats.rx_fifo_errors++;
+}
+
 static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 {
 	struct net_device *ndev = (struct net_device *)dev_id;
@@ -651,6 +666,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	struct net_device_stats *stats = &ndev->stats;
 	u32 mbxno, mbx_mask, int_status, err_status, stamp;
 	unsigned long flags, rx_pending;
+	u32 handled = 0;
 
 	int_status = hecc_read(priv,
 			       priv->use_hecc1int ?
@@ -660,17 +676,66 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	err_status = hecc_read(priv, HECC_CANES);
-	if (err_status & (HECC_BUS_ERROR | HECC_CANES_BO |
-			  HECC_CANES_EP | HECC_CANES_EW))
+	if (unlikely(err_status & HECC_CANES_FLAGS))
 		ti_hecc_error(ndev, int_status, err_status);
 
+	if (unlikely(int_status & HECC_CANGIM_DEF_MASK)) {
+		enum can_state rx_state, tx_state;
+		u32 rec = hecc_read(priv, HECC_CANREC);
+		u32 tec = hecc_read(priv, HECC_CANTEC);
+
+		if (int_status & HECC_CANGIF_WLIF) {
+			handled |= HECC_CANGIF_WLIF;
+			rx_state = rec >= tec ? CAN_STATE_ERROR_WARNING : 0;
+			tx_state = rec <= tec ? CAN_STATE_ERROR_WARNING : 0;
+			netdev_dbg(priv->ndev, "Error Warning interrupt\n");
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+
+		if (int_status & HECC_CANGIF_EPIF) {
+			handled |= HECC_CANGIF_EPIF;
+			rx_state = rec >= tec ? CAN_STATE_ERROR_PASSIVE : 0;
+			tx_state = rec <= tec ? CAN_STATE_ERROR_PASSIVE : 0;
+			netdev_dbg(priv->ndev, "Error passive interrupt\n");
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+
+		if (int_status & HECC_CANGIF_BOIF) {
+			handled |= HECC_CANGIF_BOIF;
+			rx_state = CAN_STATE_BUS_OFF;
+			tx_state = CAN_STATE_BUS_OFF;
+			netdev_dbg(priv->ndev, "Bus off interrupt\n");
+
+			/* Disable all interrupts */
+			hecc_write(priv, HECC_CANGIM, 0);
+			can_bus_off(ndev);
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+	} else if (unlikely(priv->can.state != CAN_STATE_ERROR_ACTIVE)) {
+		enum can_state new_state, tx_state, rx_state;
+		u32 rec = hecc_read(priv, HECC_CANREC);
+		u32 tec = hecc_read(priv, HECC_CANTEC);
+
+		if (rec >= 128 || tec >= 128)
+			new_state = CAN_STATE_ERROR_PASSIVE;
+		else if (rec >= 96 || tec >= 96)
+			new_state = CAN_STATE_ERROR_WARNING;
+		else
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (new_state < priv->can.state) {
+			rx_state = rec >= tec ? new_state : 0;
+			tx_state = rec <= tec ? new_state : 0;
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+	}
+
 	if (int_status & HECC_CANGIF_GMIF) {
 		while (priv->tx_tail - priv->tx_head > 0) {
 			mbxno = get_tx_tail_mb(priv);
 			mbx_mask = BIT(mbxno);
 			if (!(mbx_mask & hecc_read(priv, HECC_CANTA)))
 				break;
-			hecc_clear_bit(priv, HECC_CANMIM, mbx_mask);
 			hecc_write(priv, HECC_CANTA, mbx_mask);
 			spin_lock_irqsave(&priv->mbx_lock, flags);
 			hecc_clear_bit(priv, HECC_CANME, mbx_mask);
@@ -695,16 +760,15 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 		while ((rx_pending = hecc_read(priv, HECC_CANRMP))) {
 			can_rx_offload_irq_offload_timestamp(&priv->offload,
 							     rx_pending);
-			hecc_write(priv, HECC_CANRMP, rx_pending);
 		}
 	}
 
 	/* clear all interrupt conditions - read back to avoid spurious ints */
 	if (priv->use_hecc1int) {
-		hecc_write(priv, HECC_CANGIF1, HECC_SET_REG);
+		hecc_write(priv, HECC_CANGIF1, handled);
 		int_status = hecc_read(priv, HECC_CANGIF1);
 	} else {
-		hecc_write(priv, HECC_CANGIF0, HECC_SET_REG);
+		hecc_write(priv, HECC_CANGIF0, handled);
 		int_status = hecc_read(priv, HECC_CANGIF0);
 	}
 
@@ -877,7 +941,7 @@ static int ti_hecc_probe(struct platform_device *pdev)
 
 	priv->offload.mailbox_read = ti_hecc_mailbox_read;
 	priv->offload.mb_first = HECC_RX_FIRST_MBOX;
-	priv->offload.mb_last = HECC_MAX_TX_MBOX;
+	priv->offload.mb_last = HECC_RX_LAST_MBOX;
 	err = can_rx_offload_add_timestamp(ndev, &priv->offload);
 	if (err) {
 		dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n");
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index bd6eb9967630..2f74f6704c12 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -623,6 +623,7 @@ static int gs_can_open(struct net_device *netdev)
 					   rc);
 
 				usb_unanchor_urb(urb);
+				usb_free_urb(urb);
 				break;
 			}
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 19a702ac49e4..21faa2ec4632 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -876,9 +876,8 @@ static void mcba_usb_disconnect(struct usb_interface *intf)
 	netdev_info(priv->netdev, "device disconnected\n");
 
 	unregister_candev(priv->netdev);
-	free_candev(priv->netdev);
-
 	mcba_urb_unlink(priv);
+	free_candev(priv->netdev);
 }
 
 static struct usb_driver mcba_usb_driver = {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 617da295b6c1..d2539c95adb6 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -100,7 +100,7 @@ struct pcan_usb_msg_context {
 	u8 *end;
 	u8 rec_cnt;
 	u8 rec_idx;
-	u8 rec_data_idx;
+	u8 rec_ts_idx;
 	struct net_device *netdev;
 	struct pcan_usb *pdev;
 };
@@ -436,8 +436,8 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		}
 		if ((n & PCAN_USB_ERROR_BUS_LIGHT) == 0) {
 			/* no error (back to active state) */
-			mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE;
-			return 0;
+			new_state = CAN_STATE_ERROR_ACTIVE;
+			break;
 		}
 		break;
 
@@ -460,9 +460,9 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		}
 
 		if ((n & PCAN_USB_ERROR_BUS_HEAVY) == 0) {
-			/* no error (back to active state) */
-			mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE;
-			return 0;
+			/* no error (back to warning state) */
+			new_state = CAN_STATE_ERROR_WARNING;
+			break;
 		}
 		break;
 
@@ -501,6 +501,11 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		mc->pdev->dev.can.can_stats.error_warning++;
 		break;
 
+	case CAN_STATE_ERROR_ACTIVE:
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		break;
+
 	default:
 		/* CAN_STATE_MAX (trick to handle other errors) */
 		cf->can_id |= CAN_ERR_CRTL;
@@ -547,10 +552,15 @@ static int pcan_usb_decode_status(struct pcan_usb_msg_context *mc,
 	mc->ptr += PCAN_USB_CMD_ARGS;
 
 	if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) {
-		int err = pcan_usb_decode_ts(mc, !mc->rec_idx);
+		int err = pcan_usb_decode_ts(mc, !mc->rec_ts_idx);
 
 		if (err)
 			return err;
+
+		/* Next packet in the buffer will have a timestamp on a single
+		 * byte
+		 */
+		mc->rec_ts_idx++;
 	}
 
 	switch (f) {
@@ -632,10 +642,13 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 
 	cf->can_dlc = get_can_dlc(rec_len);
 
-	/* first data packet timestamp is a word */
-	if (pcan_usb_decode_ts(mc, !mc->rec_data_idx))
+	/* Only first packet timestamp is a word */
+	if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx))
 		goto decode_failed;
 
+	/* Next packet in the buffer will have a timestamp on a single byte */
+	mc->rec_ts_idx++;
+
 	/* read data */
 	memset(cf->data, 0x0, sizeof(cf->data));
 	if (status_len & PCAN_USB_STATUSLEN_RTR) {
@@ -688,7 +701,6 @@ static int pcan_usb_decode_msg(struct peak_usb_device *dev, u8 *ibuf, u32 lbuf)
 		/* handle normal can frames here */
 		} else {
 			err = pcan_usb_decode_data(&mc, sl);
-			mc.rec_data_idx++;
 		}
 	}
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 65dce642b86b..0b7766b715fd 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -750,7 +750,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 	dev = netdev_priv(netdev);
 
 	/* allocate a buffer large enough to send commands */
-	dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
+	dev->cmd_buf = kzalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
 	if (!dev->cmd_buf) {
 		err = -ENOMEM;
 		goto lbl_free_candev;
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index d596a2ad7f78..8fa224b28218 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -996,9 +996,8 @@ static void usb_8dev_disconnect(struct usb_interface *intf)
 		netdev_info(priv->netdev, "device disconnected\n");
 
 		unregister_netdev(priv->netdev);
-		free_candev(priv->netdev);
-
 		unlink_all_urbs(priv);
+		free_candev(priv->netdev);
 	}
 
 }
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 911b34316c9d..7c482b2d78d2 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -1599,7 +1599,6 @@ static const struct xcan_devtype_data xcan_zynq_data = {
 
 static const struct xcan_devtype_data xcan_axi_data = {
 	.cantype = XAXI_CAN,
-	.flags = XCAN_FLAG_TXFEMP,
 	.bittiming_const = &xcan_bittiming_const,
 	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
 	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 526ba2ab66f1..cc3536315eff 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1845,7 +1845,6 @@ int b53_mirror_add(struct dsa_switch *ds, int port,
 		loc = B53_EG_MIR_CTL;
 
 	b53_read16(dev, B53_MGMT_PAGE, loc, &reg);
-	reg &= ~MIRROR_MASK;
 	reg |= BIT(port);
 	b53_write16(dev, B53_MGMT_PAGE, loc, reg);
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 26509fa37a50..69fc13046ac7 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -37,22 +37,11 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 	unsigned int i;
 	u32 reg, offset;
 
-	if (priv->type == BCM7445_DEVICE_ID)
-		offset = CORE_STS_OVERRIDE_IMP;
-	else
-		offset = CORE_STS_OVERRIDE_IMP2;
-
 	/* Enable the port memories */
 	reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL);
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
-	/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-	reg = core_readl(priv, CORE_IMP_CTL);
-	reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
-	reg &= ~(RX_DIS | TX_DIS);
-	core_writel(priv, reg, CORE_IMP_CTL);
-
 	/* Enable forwarding */
 	core_writel(priv, SW_FWDG_EN, CORE_SWMODE);
 
@@ -71,10 +60,27 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 	b53_brcm_hdr_setup(ds, port);
 
-	/* Force link status for IMP port */
-	reg = core_readl(priv, offset);
-	reg |= (MII_SW_OR | LINK_STS);
-	core_writel(priv, reg, offset);
+	if (port == 8) {
+		if (priv->type == BCM7445_DEVICE_ID)
+			offset = CORE_STS_OVERRIDE_IMP;
+		else
+			offset = CORE_STS_OVERRIDE_IMP2;
+
+		/* Force link status for IMP port */
+		reg = core_readl(priv, offset);
+		reg |= (MII_SW_OR | LINK_STS);
+		core_writel(priv, reg, offset);
+
+		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
+		reg = core_readl(priv, CORE_IMP_CTL);
+		reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_IMP_CTL);
+	} else {
+		reg = core_readl(priv, CORE_G_PCTL_PORT(port));
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_G_PCTL_PORT(port));
+	}
 }
 
 static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
@@ -1209,10 +1215,10 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 	struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
 
 	priv->wol_ports_mask = 0;
+	/* Disable interrupts */
+	bcm_sf2_intr_disable(priv);
 	dsa_unregister_switch(priv->dev->ds);
 	bcm_sf2_cfp_exit(priv->dev->ds);
-	/* Disable all ports and interrupts */
-	bcm_sf2_sw_suspend(priv->dev->ds);
 	bcm_sf2_mdio_unregister(priv);
 
 	return 0;
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index a23d3ffdf0c4..24a5e99f7fd5 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1224,10 +1224,6 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 {
 	int i;
 
-	mutex_init(&dev->stats_mutex);
-	mutex_init(&dev->alu_mutex);
-	mutex_init(&dev->vlan_mutex);
-
 	dev->ds->ops = &ksz8795_switch_ops;
 
 	for (i = 0; i < ARRAY_SIZE(ksz8795_switch_chips); i++) {
diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c
index d0f8153e86b7..8b00f8e6c02f 100644
--- a/drivers/net/dsa/microchip/ksz8795_spi.c
+++ b/drivers/net/dsa/microchip/ksz8795_spi.c
@@ -25,6 +25,7 @@ KSZ_REGMAP_TABLE(ksz8795, 16, SPI_ADDR_SHIFT,
 
 static int ksz8795_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -33,9 +34,9 @@ static int ksz8795_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz8795_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_spi(spi,
-						      &ksz8795_regmap_config
-						      [i]);
+		rc = ksz8795_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_spi(spi, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&spi->dev,
diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c
index 0b1e01f0873d..fdffd9e0c518 100644
--- a/drivers/net/dsa/microchip/ksz9477_i2c.c
+++ b/drivers/net/dsa/microchip/ksz9477_i2c.c
@@ -17,6 +17,7 @@ KSZ_REGMAP_TABLE(ksz9477, not_used, 16, 0, 0);
 static int ksz9477_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *i2c_id)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -25,8 +26,9 @@ static int ksz9477_i2c_probe(struct i2c_client *i2c,
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_i2c(i2c,
-					&ksz9477_regmap_config[i]);
+		rc = ksz9477_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_i2c(i2c, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&i2c->dev,
diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
index 2938e892b631..16939f29faa5 100644
--- a/drivers/net/dsa/microchip/ksz9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Microchip KSZ9477 register definitions
  *
  * Copyright (C) 2017-2018 Microchip Technology Inc.
diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index f4198d6f72be..c5f64959a184 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -24,6 +24,7 @@ KSZ_REGMAP_TABLE(ksz9477, 32, SPI_ADDR_SHIFT,
 
 static int ksz9477_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -32,8 +33,9 @@ static int ksz9477_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_spi(spi,
-					&ksz9477_regmap_config[i]);
+		rc = ksz9477_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_spi(spi, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&spi->dev,
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index b0b870f0c252..fe47180c908b 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -436,7 +436,7 @@ int ksz_switch_register(struct ksz_device *dev,
 	}
 
 	mutex_init(&dev->dev_mutex);
-	mutex_init(&dev->stats_mutex);
+	mutex_init(&dev->regmap_mutex);
 	mutex_init(&dev->alu_mutex);
 	mutex_init(&dev->vlan_mutex);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index dd60d0837fc6..a20ebb749377 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Microchip switch driver common header
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Microchip switch driver common header
  *
  * Copyright (C) 2017-2019 Microchip Technology Inc.
  */
@@ -47,7 +47,7 @@ struct ksz_device {
 	const char *name;
 
 	struct mutex dev_mutex;		/* device access */
-	struct mutex stats_mutex;	/* status access */
+	struct mutex regmap_mutex;	/* regmap access */
 	struct mutex alu_mutex;		/* ALU access */
 	struct mutex vlan_mutex;	/* vlan access */
 	const struct ksz_dev_ops *dev_ops;
@@ -290,6 +290,18 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
 	ksz_write32(dev, dev->dev_ops->get_port_addr(port, offset), data);
 }
 
+static inline void ksz_regmap_lock(void *__mtx)
+{
+	struct mutex *mtx = __mtx;
+	mutex_lock(mtx);
+}
+
+static inline void ksz_regmap_unlock(void *__mtx)
+{
+	struct mutex *mtx = __mtx;
+	mutex_unlock(mtx);
+}
+
 /* Regmap tables generation */
 #define KSZ_SPI_OP_RD		3
 #define KSZ_SPI_OP_WR		2
@@ -314,6 +326,8 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
 		.write_flag_mask =					\
 			KSZ_SPI_OP_FLAG_MASK(KSZ_SPI_OP_WR, swp,	\
 					     regbits, regpad),		\
+		.lock = ksz_regmap_lock,				\
+		.unlock = ksz_regmap_unlock,				\
 		.reg_format_endian = REGMAP_ENDIAN_BIG,			\
 		.val_format_endian = REGMAP_ENDIAN_BIG			\
 	}
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index 073cbd0bb91b..d838c174dc0d 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -273,6 +273,19 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 	int pin;
 	int err;
 
+	/* Reject requests with unsupported flags */
+	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
+				PTP_RISING_EDGE |
+				PTP_FALLING_EDGE |
+				PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
+	/* Reject requests to enable time stamping on both edges. */
+	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
+	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+	    (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES)
+		return -EOPNOTSUPP;
+
 	pin = ptp_find_pin(chip->ptp_clock, PTP_PF_EXTTS, rq->extts.index);
 
 	if (pin < 0)
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index f40b248f0b23..ffac0ea4e8d5 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -26,8 +26,8 @@ config NET_DSA_SJA1105_PTP
 
 config NET_DSA_SJA1105_TAS
 	bool "Support for the Time-Aware Scheduler on NXP SJA1105"
-	depends on NET_DSA_SJA1105
-	depends on NET_SCH_TAPRIO
+	depends on NET_DSA_SJA1105 && NET_SCH_TAPRIO
+	depends on NET_SCH_TAPRIO=y || NET_DSA_SJA1105=m
 	help
 	  This enables support for the TTEthernet-based egress scheduling
 	  engine in the SJA1105 DSA driver, which is controlled using a
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index e53e494c22e0..fbb564c3beb8 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
  * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_H
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
index 740dadf43f01..1fc0d13dc623 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_DYNAMIC_CONFIG_H
 #define _SJA1105_DYNAMIC_CONFIG_H
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h
index af456b0a4d27..394e12a6ad59 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.h
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_PTP_H
 #define _SJA1105_PTP_H
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h
index 7f87022a2d61..f4a5c5c04311 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright (c) 2016-2018, NXP Semiconductors
+/* SPDX-License-Identifier: BSD-3-Clause */
+/* Copyright (c) 2016-2018, NXP Semiconductors
  * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_STATIC_CONFIG_H
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.h b/drivers/net/dsa/sja1105/sja1105_tas.h
index 0b803c30e640..0aad212d88b2 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.h
+++ b/drivers/net/dsa/sja1105/sja1105_tas.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_TAS_H
 #define _SJA1105_TAS_H
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index b4a0fb281e69..bb65dd39f847 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -194,9 +194,7 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 
-	aq_nic_set_packet_filter(aq_nic, ndev->flags);
-
-	aq_nic_set_multicast_list(aq_nic, ndev);
+	(void)aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 8f66e7817811..137c1de4c6ec 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -631,9 +631,12 @@ err_exit:
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
-	unsigned int packet_filter = self->packet_filter;
+	const struct aq_hw_ops *hw_ops = self->aq_hw_ops;
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	unsigned int packet_filter = ndev->flags;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
+	int err = 0;
 
 	self->mc_list.count = 0;
 	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
@@ -641,29 +644,28 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 	} else {
 		netdev_for_each_uc_addr(ha, ndev) {
 			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
 		}
 	}
 
-	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_ALLMULTI;
-	} else {
-		netdev_for_each_mc_addr(ha, ndev) {
-			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
+	cfg->is_mc_list_enabled = !!(packet_filter & IFF_MULTICAST);
+	if (cfg->is_mc_list_enabled) {
+		if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+			packet_filter |= IFF_ALLMULTI;
+		} else {
+			netdev_for_each_mc_addr(ha, ndev) {
+				ether_addr_copy(self->mc_list.ar[i++],
+						ha->addr);
+			}
 		}
 	}
 
 	if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_MULTICAST;
 		self->mc_list.count = i;
-		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						       self->mc_list.ar,
-						       self->mc_list.count);
+		err = hw_ops->hw_multicast_list_set(self->aq_hw,
+						    self->mc_list.ar,
+						    self->mc_list.count);
+		if (err < 0)
+			return err;
 	}
 	return aq_nic_set_packet_filter(self, packet_filter);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 3901d7994ca1..76bdbe1596d6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -313,6 +313,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 					break;
 
 				buff->is_error |= buff_->is_error;
+				buff->is_cso_err |= buff_->is_cso_err;
 
 			} while (!buff_->is_eop);
 
@@ -320,7 +321,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error) {
+			if (buff->is_error || buff->is_cso_err) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 30f7fc4c97ff..2ad3fa6316ce 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -818,14 +818,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 				     cfg->is_vlan_force_promisc);
 
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
-					       IS_FILTER_ENABLED(IFF_ALLMULTI));
+					      IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					      IS_FILTER_ENABLED(IFF_MULTICAST));
 
 	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
 
-	cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
 
 	for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i)
 		hw_atl_rpfl2_uc_flr_en_set(self,
@@ -968,14 +969,26 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 
 static int hw_atl_b0_hw_stop(struct aq_hw_s *self)
 {
+	int err;
+	u32 val;
+
 	hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK);
 
 	/* Invalidate Descriptor Cache to prevent writing to the cached
 	 * descriptors and to the data pointer of those descriptors
 	 */
-	hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1);
+	hw_atl_rdm_rx_dma_desc_cache_init_tgl(self);
 
-	return aq_hw_err_from_flags(self);
+	err = aq_hw_err_from_flags(self);
+
+	if (err)
+		goto err_exit;
+
+	readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get,
+				  self, val, val == 1, 1000U, 10000U);
+
+err_exit:
+	return err;
 }
 
 static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 1149812ae463..6f340695e6bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -606,12 +606,25 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode
 			    HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode);
 }
 
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init)
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw)
 {
+	u32 val;
+
+	val = aq_hw_read_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT);
+
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT,
-			    init);
+			    val ^ 1);
+}
+
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT);
 }
 
 void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 0c37abbabca5..c3ee278c3747 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -313,8 +313,11 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
 					    u32 rx_pkt_buff_size_per_tc,
 					    u32 buffer);
 
-/* set rdm rx dma descriptor cache init */
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init);
+/* toggle rdm rx dma descriptor cache init */
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw);
+
+/* get rdm rx dma descriptor cache init done */
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw);
 
 /* set rx xoff enable (per tc) */
 void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index c3febcdfa92e..35887ad89025 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -318,6 +318,25 @@
 /* default value of bitfield rdm_desc_init_i */
 #define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0
 
+/* rdm_desc_init_done_i bitfield definitions
+ * preprocessor definitions for the bitfield rdm_desc_init_done_i.
+ * port="pif_rdm_desc_init_done_i"
+ */
+
+/* register address for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR 0x00005a10
+/* bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK 0x00000001U
+/* inverted bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSKN 0xfffffffe
+/* lower bit position of bitfield  rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT 0U
+/* width of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_WIDTH 1
+/* default value of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_DEFAULT 0x0
+
+
 /* rx int_desc_wrb_en bitfield definitions
  * preprocessor definitions for the bitfield "int_desc_wrb_en".
  * port="pif_rdm_int_desc_wrb_en_i"
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index da726489e3c8..7bc51f8d6f2f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -337,7 +337,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp)
 	/* Convert PHY temperature from 1/256 degree Celsius
 	 * to 1/1000 degree Celsius.
 	 */
-	*temp = temp_res  * 1000 / 256;
+	*temp = (temp_res & 0xFFFF) * 1000 / 256;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index 42d2e1b02c44..664d664e0925 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -256,6 +256,9 @@ static int emac_rockchip_remove(struct platform_device *pdev)
 	if (priv->regulator)
 		regulator_disable(priv->regulator);
 
+	if (priv->soc_data->need_div_macclk)
+		clk_disable_unprepare(priv->macclk);
+
 	free_netdev(ndev);
 	return err;
 }
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index e24f5d2b6afe..53055ce5dfd6 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -8,7 +8,6 @@ config NET_VENDOR_BROADCOM
 	default y
 	depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \
 		   SIBYTE_SB1xxx_SOC
-	select DIMLIB
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
@@ -69,6 +68,7 @@ config BCMGENET
 	select FIXED_PHY
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
@@ -188,6 +188,7 @@ config SYSTEMPORT
 	select MII
 	select PHYLIB
 	select FIXED_PHY
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset using an internal
@@ -200,6 +201,7 @@ config BNXT
 	select LIBCRC32C
 	select NET_DEVLINK
 	select PAGE_POOL
+	select DIMLIB
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b4a8cf620a0c..04ec909e06df 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10382,7 +10382,8 @@ static void bnxt_cleanup_pci(struct bnxt *bp)
 {
 	bnxt_unmap_bars(bp, bp->pdev);
 	pci_release_regions(bp->pdev);
-	pci_disable_device(bp->pdev);
+	if (pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
 }
 
 static void bnxt_init_dflt_coal(struct bnxt *bp)
@@ -10669,14 +10670,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW;
 	}
 	/* fall through */
-	case BNXT_FW_RESET_STATE_RESET_FW: {
-		u32 wait_dsecs = bp->fw_health->post_reset_wait_dsecs;
-
+	case BNXT_FW_RESET_STATE_RESET_FW:
 		bnxt_reset_all(bp);
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
-		bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10);
+		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
 		return;
-	}
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
 		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
 		    bp->fw_health) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index e664392dccc0..7151244f8c7d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -29,25 +29,20 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
 	health_status = val & 0xffff;
 
-	if (health_status == BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Healthy;");
-		if (rc)
-			return rc;
-	} else if (health_status < BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Not yet completed initialization;");
+	if (health_status < BNXT_FW_STATUS_HEALTHY) {
+		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
+						  "Not yet completed initialization");
 		if (rc)
 			return rc;
 	} else if (health_status > BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Encountered fatal error and cannot recover;");
+		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
+						  "Encountered fatal error and cannot recover");
 		if (rc)
 			return rc;
 	}
 
 	if (val >> 16) {
-		rc = devlink_fmsg_u32_pair_put(fmsg, "Error", val >> 16);
+		rc = devlink_fmsg_u32_pair_put(fmsg, "Error code", val >> 16);
 		if (rc)
 			return rc;
 	}
@@ -215,25 +210,68 @@ enum bnxt_dl_param_id {
 
 static const struct bnxt_dl_nvm_param nvm_params[] = {
 	{DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 	{DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, NVM_OFF_IGNORE_ARI,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
-	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10},
+	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
-	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7},
+	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4},
 	{BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 };
 
+union bnxt_nvm_data {
+	u8	val8;
+	__le32	val32;
+};
+
+static void bnxt_copy_to_nvm_data(union bnxt_nvm_data *dst,
+				  union devlink_param_value *src,
+				  int nvm_num_bits, int dl_num_bytes)
+{
+	u32 val32 = 0;
+
+	if (nvm_num_bits == 1) {
+		dst->val8 = src->vbool;
+		return;
+	}
+	if (dl_num_bytes == 4)
+		val32 = src->vu32;
+	else if (dl_num_bytes == 2)
+		val32 = (u32)src->vu16;
+	else if (dl_num_bytes == 1)
+		val32 = (u32)src->vu8;
+	dst->val32 = cpu_to_le32(val32);
+}
+
+static void bnxt_copy_from_nvm_data(union devlink_param_value *dst,
+				    union bnxt_nvm_data *src,
+				    int nvm_num_bits, int dl_num_bytes)
+{
+	u32 val32;
+
+	if (nvm_num_bits == 1) {
+		dst->vbool = src->val8;
+		return;
+	}
+	val32 = le32_to_cpu(src->val32);
+	if (dl_num_bytes == 4)
+		dst->vu32 = val32;
+	else if (dl_num_bytes == 2)
+		dst->vu16 = (u16)val32;
+	else if (dl_num_bytes == 1)
+		dst->vu8 = (u8)val32;
+}
+
 static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 			     int msg_len, union devlink_param_value *val)
 {
 	struct hwrm_nvm_get_variable_input *req = msg;
-	void *data_addr = NULL, *buf = NULL;
 	struct bnxt_dl_nvm_param nvm_param;
-	int bytesize, idx = 0, rc, i;
+	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
+	int idx = 0, rc, i;
 
 	/* Get/Set NVM CFG parameter is supported only on PFs */
 	if (BNXT_VF(bp))
@@ -254,47 +292,31 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
-	bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE;
-	switch (bytesize) {
-	case 1:
-		if (nvm_param.num_bits == 1)
-			buf = &val->vbool;
-		else
-			buf = &val->vu8;
-		break;
-	case 2:
-		buf = &val->vu16;
-		break;
-	case 4:
-		buf = &val->vu32;
-		break;
-	default:
-		return -EFAULT;
-	}
-
-	data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize,
-				       &data_dma_addr, GFP_KERNEL);
-	if (!data_addr)
+	data = dma_alloc_coherent(&bp->pdev->dev, sizeof(*data),
+				  &data_dma_addr, GFP_KERNEL);
+	if (!data)
 		return -ENOMEM;
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
-	req->data_len = cpu_to_le16(nvm_param.num_bits);
+	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
 	req->option_num = cpu_to_le16(nvm_param.offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
 	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
-		memcpy(data_addr, buf, bytesize);
+		bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits,
+				      nvm_param.dl_num_bytes);
 		rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
 	} else {
 		rc = hwrm_send_message_silent(bp, msg, msg_len,
 					      HWRM_CMD_TIMEOUT);
+		if (!rc)
+			bnxt_copy_from_nvm_data(val, data,
+						nvm_param.nvm_num_bits,
+						nvm_param.dl_num_bytes);
 	}
-	if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
-		memcpy(buf, data_addr, bytesize);
-
-	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
+	dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr);
 	if (rc == -EACCES)
 		netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n");
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index b97e0baeb42d..2f4fd0a7d04b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -52,7 +52,8 @@ struct bnxt_dl_nvm_param {
 	u16 id;
 	u16 offset;
 	u16 dir_type;
-	u16 num_bits;
+	u16 nvm_num_bits;
+	u8 dl_num_bytes;
 };
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 12cb77ef1081..1de51811fcb4 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1996,8 +1996,6 @@ static void reset_umac(struct bcmgenet_priv *priv)
 
 	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
 	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
-	udelay(2);
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
@@ -2018,6 +2016,8 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	 */
 	if (priv->internal_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			int0_enable |= UMAC_IRQ_PHY_DET_R;
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
@@ -2611,11 +2611,16 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	priv->irq0_stat = 0;
 	spin_unlock_irq(&priv->lock);
 
+	if (status & UMAC_IRQ_PHY_DET_R &&
+	    priv->dev->phydev->autoneg != AUTONEG_ENABLE) {
+		phy_init_hw(priv->dev->phydev);
+		genphy_config_aneg(priv->dev->phydev);
+	}
+
 	/* Link UP/DOWN event */
-	if (status & UMAC_IRQ_LINK_EVENT) {
-		priv->dev->phydev->link = !!(status & UMAC_IRQ_LINK_UP);
+	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->dev->phydev);
-	}
+
 }
 
 /* bcmgenet_isr1: handle Rx and Tx priority queues */
@@ -2710,7 +2715,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	}
 
 	/* all other interested interrupts handled in bottom half */
-	status &= UMAC_IRQ_LINK_EVENT;
+	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R);
 	if (status) {
 		/* Save irq status for bottom-half processing. */
 		spin_lock_irqsave(&priv->lock, flags);
@@ -3631,6 +3636,7 @@ static int bcmgenet_resume(struct device *d)
 	phy_init_hw(dev->phydev);
 
 	/* Speed settings must be restored */
+	genphy_config_aneg(dev->phydev);
 	bcmgenet_mii_config(priv->dev, false);
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 4a8fc03d82fd..dbc69d8fa05f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -366,6 +366,7 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
+#define  RGMII_MODE_EN_V123		(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
 #define  RGMII_MODE_EN			(1 << 6)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 970e478a9017..dbe18cdf6c1b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -181,8 +181,38 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
 	u32 port_ctrl;
+	int bmcr = -1;
+	int ret;
 	u32 reg;
 
+	/* MAC clocking workaround during reset of umac state machines */
+	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+	if (reg & CMD_SW_RESET) {
+		/* An MII PHY must be isolated to prevent TXC contention */
+		if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
+			ret = phy_read(phydev, MII_BMCR);
+			if (ret >= 0) {
+				bmcr = ret;
+				ret = phy_write(phydev, MII_BMCR,
+						bmcr | BMCR_ISOLATE);
+			}
+			if (ret) {
+				netdev_err(dev, "failed to isolate PHY\n");
+				return ret;
+			}
+		}
+		/* Switch MAC clocking to RGMII generated clock */
+		bcmgenet_sys_writel(priv, PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
+		/* Ensure 5 clks with Rx disabled
+		 * followed by 5 clks with Reset asserted
+		 */
+		udelay(4);
+		reg &= ~(CMD_SW_RESET | CMD_LCL_LOOP_EN);
+		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+		/* Ensure 5 more clocks before Rx is enabled */
+		udelay(2);
+	}
+
 	priv->ext_phy = !priv->internal_phy &&
 			(priv->phy_interface != PHY_INTERFACE_MODE_MOCA);
 
@@ -214,6 +244,9 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		phy_set_max_speed(phydev, SPEED_100);
 		bcmgenet_sys_writel(priv,
 				    PORT_MODE_EXT_EPHY, SYS_PORT_CTRL);
+		/* Restore the MII PHY after isolation */
+		if (bmcr >= 0)
+			phy_write(phydev, MII_BMCR, bmcr);
 		break;
 
 	case PHY_INTERFACE_MODE_REVMII:
@@ -258,7 +291,11 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	 */
 	if (priv->ext_phy) {
 		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
-		reg |= RGMII_MODE_EN | id_mode_dis;
+		reg |= id_mode_dis;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			reg |= RGMII_MODE_EN_V123;
+		else
+			reg |= RGMII_MODE_EN;
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
@@ -273,11 +310,12 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
-	u32 phy_flags;
+	u32 phy_flags = 0;
 	int ret;
 
 	/* Communicate the integrated PHY revision */
-	phy_flags = priv->gphy_rev;
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
 
 	/* Initialize link state variables that bcmgenet_mii_setup() uses */
 	priv->old_link = -1;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 77f3511b97de..ca3aa1250dd1 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6280,6 +6280,10 @@ static int tg3_ptp_enable(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_PEROUT:
+		/* Reject requests with unsupported flags */
+		if (rq->perout.flags)
+			return -EOPNOTSUPP;
+
 		if (rq->perout.index != 0)
 			return -EINVAL;
 
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 8e8d557901a9..1e1b774e1953 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3405,17 +3405,17 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		return err;
 	}
 
-	*tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
+	*tx_clk = devm_clk_get_optional(&pdev->dev, "tx_clk");
 	if (IS_ERR(*tx_clk))
-		*tx_clk = NULL;
+		return PTR_ERR(*tx_clk);
 
-	*rx_clk = devm_clk_get(&pdev->dev, "rx_clk");
+	*rx_clk = devm_clk_get_optional(&pdev->dev, "rx_clk");
 	if (IS_ERR(*rx_clk))
-		*rx_clk = NULL;
+		return PTR_ERR(*rx_clk);
 
-	*tsu_clk = devm_clk_get(&pdev->dev, "tsu_clk");
+	*tsu_clk = devm_clk_get_optional(&pdev->dev, "tsu_clk");
 	if (IS_ERR(*tsu_clk))
-		*tsu_clk = NULL;
+		return PTR_ERR(*tsu_clk);
 
 	err = clk_prepare_enable(*pclk);
 	if (err) {
diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.h b/drivers/net/ethernet/cavium/common/cavium_ptp.h
index be2bafc7beeb..a04eccbc78e8 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.h
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /* cavium_ptp.h - PTP 1588 clock on Cavium hardware
  * Copyright (c) 2003-2015, 2017 Cavium, Inc.
  */
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 0e5de88fd6e8..cdd7e5da4a74 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1499,7 +1499,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 	netdev->ethtool_ops = &octeon_mgmt_ethtool_ops;
 
 	netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM;
-	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM;
+	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN;
 
 	mac = of_get_mac_address(pdev->dev.of_node);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index a4dead4ab0ed..86b528d8364c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -695,10 +695,10 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->write_cmpl_support = adap->params.write_cmpl_support;
 }
 
-static void uld_attach(struct adapter *adap, unsigned int uld)
+static int uld_attach(struct adapter *adap, unsigned int uld)
 {
-	void *handle;
 	struct cxgb4_lld_info lli;
+	void *handle;
 
 	uld_init(adap, &lli);
 	uld_queue_init(adap, uld, &lli);
@@ -708,7 +708,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 		dev_warn(adap->pdev_dev,
 			 "could not attach to the %s driver, error %ld\n",
 			 adap->uld[uld].name, PTR_ERR(handle));
-		return;
+		return PTR_ERR(handle);
 	}
 
 	adap->uld[uld].handle = handle;
@@ -716,22 +716,22 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 
 	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		adap->uld[uld].state_change(handle, CXGB4_STATE_UP);
+
+	return 0;
 }
 
-/**
- *	cxgb4_register_uld - register an upper-layer driver
- *	@type: the ULD type
- *	@p: the ULD methods
+/* cxgb4_register_uld - register an upper-layer driver
+ * @type: the ULD type
+ * @p: the ULD methods
  *
- *	Registers an upper-layer driver with this driver and notifies the ULD
- *	about any presently available devices that support its type.  Returns
- *	%-EBUSY if a ULD of the same type is already registered.
+ * Registers an upper-layer driver with this driver and notifies the ULD
+ * about any presently available devices that support its type.
  */
 void cxgb4_register_uld(enum cxgb4_uld type,
 			const struct cxgb4_uld_info *p)
 {
-	int ret = 0;
 	struct adapter *adap;
+	int ret = 0;
 
 	if (type >= CXGB4_ULD_MAX)
 		return;
@@ -763,8 +763,12 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		if (ret)
 			goto free_irq;
 		adap->uld[type] = *p;
-		uld_attach(adap, type);
+		ret = uld_attach(adap, type);
+		if (ret)
+			goto free_txq;
 		continue;
+free_txq:
+		release_sge_txq_uld(adap, type);
 free_irq:
 		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index b3da81e90132..928bfea5457b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -3791,15 +3791,11 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	 * write the CIDX Updates into the Status Page at the end of the
 	 * TX Queue.
 	 */
-	c.autoequiqe_to_viid = htonl((dbqt
-				      ? FW_EQ_ETH_CMD_AUTOEQUIQE_F
-				      : FW_EQ_ETH_CMD_AUTOEQUEQE_F) |
+	c.autoequiqe_to_viid = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
 				     FW_EQ_ETH_CMD_VIID_V(pi->viid));
 
 	c.fetchszm_to_iqid =
-		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt
-						 ? HOSTFCMODE_INGRESS_QUEUE_X
-						 : HOSTFCMODE_STATUS_PAGE_X) |
+		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
 		      FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid));
 
diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index f1a0c4dceda0..f37c9a08c4cf 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -763,6 +763,7 @@ static int ep93xx_eth_remove(struct platform_device *pdev)
 {
 	struct net_device *dev;
 	struct ep93xx_priv *ep;
+	struct resource *mem;
 
 	dev = platform_get_drvdata(pdev);
 	if (dev == NULL)
@@ -778,8 +779,8 @@ static int ep93xx_eth_remove(struct platform_device *pdev)
 		iounmap(ep->base_addr);
 
 	if (ep->res != NULL) {
-		release_resource(ep->res);
-		kfree(ep->res);
+		mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		release_mem_region(mem->start, resource_size(mem));
 	}
 
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index e736ce2c58ca..a8f4c69252ff 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2524,6 +2524,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev)
 	struct gemini_ethernet_port *port = platform_get_drvdata(pdev);
 
 	gemini_port_remove(port);
+	free_netdev(port->netdev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h
index 0b12f89bf89a..9fdf77d5eb37 100644
--- a/drivers/net/ethernet/cortina/gemini.h
+++ b/drivers/net/ethernet/cortina/gemini.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Register definitions for Gemini GMAC Ethernet device driver
  *
  * Copyright (C) 2006 Storlink, Corp.
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 9b7af94a40bb..96e9565f1e08 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -727,6 +727,18 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	 */
 	nfrags = skb_shinfo(skb)->nr_frags;
 
+	/* Setup HW checksumming */
+	csum_vlan = 0;
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
+		goto drop;
+
+	/* Add VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
+		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
+	}
+
 	/* Get header len */
 	len = skb_headlen(skb);
 
@@ -753,19 +765,6 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	if (nfrags == 0)
 		f_ctl_stat |= FTGMAC100_TXDES0_LTS;
 	txdes->txdes3 = cpu_to_le32(map);
-
-	/* Setup HW checksumming */
-	csum_vlan = 0;
-	if (skb->ip_summed == CHECKSUM_PARTIAL &&
-	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
-		goto drop;
-
-	/* Add VLAN tag */
-	if (skb_vlan_tag_present(skb)) {
-		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
-		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
-	}
-
 	txdes->txdes1 = cpu_to_le32(csum_vlan);
 
 	/* Next descriptor */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 162d7d8fb295..bf5add954181 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1235,6 +1235,8 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
 	priv->rx_td_enabled = enable;
 }
 
+static void update_tx_fqids(struct dpaa2_eth_priv *priv);
+
 static int link_state_update(struct dpaa2_eth_priv *priv)
 {
 	struct dpni_link_state state = {0};
@@ -1261,6 +1263,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv)
 		goto out;
 
 	if (state.up) {
+		update_tx_fqids(priv);
 		netif_carrier_on(priv->net_dev);
 		netif_tx_start_all_queues(priv->net_dev);
 	} else {
@@ -2229,8 +2232,16 @@ err_set_cdan:
 err_service_reg:
 	free_channel(priv, channel);
 err_alloc_ch:
-	if (err == -EPROBE_DEFER)
+	if (err == -EPROBE_DEFER) {
+		for (i = 0; i < priv->num_channels; i++) {
+			channel = priv->channel[i];
+			nctx = &channel->nctx;
+			dpaa2_io_service_deregister(channel->dpio, nctx, dev);
+			free_channel(priv, channel);
+		}
+		priv->num_channels = 0;
 		return err;
+	}
 
 	if (cpumask_empty(&priv->dpio_cpumask)) {
 		dev_err(dev, "No cpu with an affine DPIO/DPCON\n");
@@ -2533,6 +2544,47 @@ static int set_pause(struct dpaa2_eth_priv *priv)
 	return 0;
 }
 
+static void update_tx_fqids(struct dpaa2_eth_priv *priv)
+{
+	struct dpni_queue_id qid = {0};
+	struct dpaa2_eth_fq *fq;
+	struct dpni_queue queue;
+	int i, j, err;
+
+	/* We only use Tx FQIDs for FQID-based enqueue, so check
+	 * if DPNI version supports it before updating FQIDs
+	 */
+	if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR,
+				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
+		return;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		if (fq->type != DPAA2_TX_CONF_FQ)
+			continue;
+		for (j = 0; j < dpaa2_eth_tc_count(priv); j++) {
+			err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
+					     DPNI_QUEUE_TX, j, fq->flowid,
+					     &queue, &qid);
+			if (err)
+				goto out_err;
+
+			fq->tx_fqid[j] = qid.fqid;
+			if (fq->tx_fqid[j] == 0)
+				goto out_err;
+		}
+	}
+
+	priv->enqueue = dpaa2_eth_enqueue_fq;
+
+	return;
+
+out_err:
+	netdev_info(priv->net_dev,
+		    "Error reading Tx FQID, fallback to QDID-based enqueue\n");
+	priv->enqueue = dpaa2_eth_enqueue_qd;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
@@ -3306,6 +3358,9 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg)
 	if (status & DPNI_IRQ_EVENT_LINK_CHANGED)
 		link_state_update(netdev_priv(net_dev));
 
+	if (status & DPNI_IRQ_EVENT_ENDPOINT_CHANGED)
+		set_mac_addr(netdev_priv(net_dev));
+
 	return IRQ_HANDLED;
 }
 
@@ -3331,7 +3386,8 @@ static int setup_irqs(struct fsl_mc_device *ls_dev)
 	}
 
 	err = dpni_set_irq_mask(ls_dev->mc_io, 0, ls_dev->mc_handle,
-				DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED);
+				DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED |
+				DPNI_IRQ_EVENT_ENDPOINT_CHANGED);
 	if (err < 0) {
 		dev_err(&ls_dev->dev, "dpni_set_irq_mask(): %d\n", err);
 		goto free_irq;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
index ff2e177395d4..df2458a5e9ef 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2018 NXP
  */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index fd583911b6c0..ee0711d06b3a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -133,9 +133,12 @@ int dpni_reset(struct fsl_mc_io	*mc_io,
  */
 #define DPNI_IRQ_INDEX				0
 /**
- * IRQ event - indicates a change in link state
+ * IRQ events:
+ *       indicates a change in link state
+ *       indicates a change in endpoint
  */
 #define DPNI_IRQ_EVENT_LINK_CHANGED		0x00000001
+#define DPNI_IRQ_EVENT_ENDPOINT_CHANGED		0x00000002
 
 int dpni_set_irq_enable(struct fsl_mc_io	*mc_io,
 			u32			cmd_flags,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
index 720cd50f5895..4ac05bfef338 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2013-2016 Freescale Semiconductor Inc.
  * Copyright 2016-2018 NXP
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.h b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
index be7914c1634d..311c184e1aef 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2013-2016 Freescale Semiconductor Inc.
  * Copyright 2016-2018 NXP
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4d4c72adf49..4bb30761abfc 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3558,7 +3558,7 @@ fec_probe(struct platform_device *pdev)
 
 	for (i = 0; i < irq_cnt; i++) {
 		snprintf(irq_name, sizeof(irq_name), "int%d", i);
-		irq = platform_get_irq_byname(pdev, irq_name);
+		irq = platform_get_irq_byname_optional(pdev, irq_name);
 		if (irq < 0)
 			irq = platform_get_irq(pdev, i);
 		if (irq < 0) {
@@ -3636,6 +3636,11 @@ fec_drv_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct device_node *np = pdev->dev.of_node;
+	int ret;
+
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0)
+		return ret;
 
 	cancel_work_sync(&fep->tx_timeout_work);
 	fec_ptp_stop(pdev);
@@ -3643,13 +3648,17 @@ fec_drv_remove(struct platform_device *pdev)
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
+
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
 	free_netdev(ndev);
 
+	clk_disable_unprepare(fep->clk_ahb);
+	clk_disable_unprepare(fep->clk_ipg);
+	pm_runtime_put_noidle(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 19e2365be7d8..945643c02615 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -600,9 +600,9 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 
 	INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
 
-	irq = platform_get_irq_byname(pdev, "pps");
+	irq = platform_get_irq_byname_optional(pdev, "pps");
 	if (irq < 0)
-		irq = platform_get_irq(pdev, irq_idx);
+		irq = platform_get_irq_optional(pdev, irq_idx);
 	/* Failure to get an irq is not fatal,
 	 * only the PTP_CLOCK_PPS clock events should stop
 	 */
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 59564ac99d2a..edec61dfc868 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -289,6 +289,8 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 
 	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
 	page_info = &rx->data.page_info[idx];
+	dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx],
+				PAGE_SIZE, DMA_FROM_DEVICE);
 
 	/* gvnic can only receive into registered segments. If the buffer
 	 * can't be recycled, our only choice is to copy the data out of
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 778b87b5a06c..f4889431f9b7 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -390,7 +390,22 @@ static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc,
 	seg_desc->seg.seg_addr = cpu_to_be64(addr);
 }
 
-static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
+static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses,
+				    u64 iov_offset, u64 iov_len)
+{
+	u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE;
+	u64 first_page = iov_offset / PAGE_SIZE;
+	dma_addr_t dma;
+	u64 page;
+
+	for (page = first_page; page <= last_page; page++) {
+		dma = page_buses[page];
+		dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE);
+	}
+}
+
+static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb,
+			  struct device *dev)
 {
 	int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset;
 	union gve_tx_desc *pkt_desc, *seg_desc;
@@ -432,6 +447,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
 	skb_copy_bits(skb, 0,
 		      tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset,
 		      hlen);
+	gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+				info->iov[hdr_nfrags - 1].iov_offset,
+				info->iov[hdr_nfrags - 1].iov_len);
 	copy_offset = hlen;
 
 	for (i = payload_iov; i < payload_nfrags + payload_iov; i++) {
@@ -445,6 +463,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
 		skb_copy_bits(skb, copy_offset,
 			      tx->tx_fifo.base + info->iov[i].iov_offset,
 			      info->iov[i].iov_len);
+		gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+					info->iov[i].iov_offset,
+					info->iov[i].iov_len);
 		copy_offset += info->iov[i].iov_len;
 	}
 
@@ -473,7 +494,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
 		gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
 		return NETDEV_TX_BUSY;
 	}
-	nsegs = gve_tx_add_skb(tx, skb);
+	nsegs = gve_tx_add_skb(tx, skb, &priv->pdev->dev);
 
 	netdev_tx_sent_queue(tx->netdev_txq, skb->len);
 	skb_tx_timestamp(skb);
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index c84167447abe..4606a7e4a6d1 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -237,6 +237,7 @@ struct hip04_priv {
 	dma_addr_t rx_phys[RX_DESC_NUM];
 	unsigned int rx_head;
 	unsigned int rx_buf_size;
+	unsigned int rx_cnt_remaining;
 
 	struct device_node *phy_node;
 	struct phy_device *phy;
@@ -575,7 +576,6 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 	struct hip04_priv *priv = container_of(napi, struct hip04_priv, napi);
 	struct net_device *ndev = priv->ndev;
 	struct net_device_stats *stats = &ndev->stats;
-	unsigned int cnt = hip04_recv_cnt(priv);
 	struct rx_desc *desc;
 	struct sk_buff *skb;
 	unsigned char *buf;
@@ -588,8 +588,8 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 
 	/* clean up tx descriptors */
 	tx_remaining = hip04_tx_reclaim(ndev, false);
-
-	while (cnt && !last) {
+	priv->rx_cnt_remaining += hip04_recv_cnt(priv);
+	while (priv->rx_cnt_remaining && !last) {
 		buf = priv->rx_buf[priv->rx_head];
 		skb = build_skb(buf, priv->rx_buf_size);
 		if (unlikely(!skb)) {
@@ -635,11 +635,13 @@ refill:
 		hip04_set_recv_desc(priv, phys);
 
 		priv->rx_head = RX_NEXT(priv->rx_head);
-		if (rx >= budget)
+		if (rx >= budget) {
+			--priv->rx_cnt_remaining;
 			goto done;
+		}
 
-		if (--cnt == 0)
-			cnt = hip04_recv_cnt(priv);
+		if (--priv->rx_cnt_remaining == 0)
+			priv->rx_cnt_remaining += hip04_recv_cnt(priv);
 	}
 
 	if (!(priv->reg_inten & RCV_INT)) {
@@ -724,6 +726,7 @@ static int hip04_mac_open(struct net_device *ndev)
 	int i;
 
 	priv->rx_head = 0;
+	priv->rx_cnt_remaining = 0;
 	priv->tx_head = 0;
 	priv->tx_tail = 0;
 	hip04_reset_ppe(priv);
@@ -1038,7 +1041,6 @@ static int hip04_remove(struct platform_device *pdev)
 
 	hip04_free_ring(ndev, d);
 	unregister_netdev(ndev);
-	free_irq(ndev->irq, ndev);
 	of_node_put(priv->phy_node);
 	cancel_work_sync(&priv->tx_timeout_task);
 	free_netdev(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 6d0457eb4faa..08339278c722 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -199,7 +199,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
-	spin_lock_init(&ring->lock);
 	ring->coal_param = q->handle->coal_param;
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index e9c67c06bfd2..6ab9458302e1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -274,9 +274,6 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
-	/* ring lock for poll one */
-	spinlock_t lock;
-
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index a48396dd4ebb..14ab20491fd0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -943,15 +943,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 	return u > c ? (h > c && h <= u) : (h > c || h <= u);
 }
 
-/* netif_tx_lock will turn down the performance, set only when necessary */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
-#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
-#else
-#define NETIF_TX_LOCK(ring)
-#define NETIF_TX_UNLOCK(ring)
-#endif
-
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -965,21 +956,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
-	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ring);
+	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return 0; /* no data to poll */
-	}
 
 	if (!is_valid_clean_head(ring, head)) {
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -994,8 +980,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	ring->stats.tx_pkts += pkts;
 	ring->stats.tx_bytes += bytes;
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
 
@@ -1055,16 +1039,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
 	pkts = 0;
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index c4b7bf851a28..a0998937727d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNAE3_H
@@ -32,6 +32,8 @@
 
 #define HNAE3_MOD_VERSION "1.0"
 
+#define HNAE3_MIN_VECTOR_NUM	2 /* first one for misc, another for IO */
+
 /* Device IDs */
 #define HNAE3_DEV_ID_GE				0xA220
 #define HNAE3_DEV_ID_25GE			0xA221
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 2110fa3b4479..5d468ed404a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNS3_ENET_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 680c3508876d..52c9d204fe3d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -70,11 +70,6 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 #define HNS3_NIC_LB_TEST_TX_CNT_ERR	2
 #define HNS3_NIC_LB_TEST_RX_CNT_ERR	3
 
-struct hns3_link_mode_mapping {
-	u32 hns3_link_mode;
-	u32 ethtool_link_mode;
-};
-
 static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 4821fe08b5e4..1426eb5ddf3d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_CMD_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index c063301d6060..a1790af73096 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -124,7 +124,7 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 	if (ret)
 		return ret;
 
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
+	for (i = 0; i < hdev->tc_max; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
@@ -318,6 +318,7 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 	struct net_device *netdev = h->kinfo.netdev;
 	struct hclge_dev *hdev = vport->back;
 	u8 i, j, pfc_map, *prio_tc;
+	int ret;
 
 	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
 	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
@@ -347,7 +348,21 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 
 	hclge_tm_pfc_info_update(hdev);
 
-	return hclge_pause_setup_hw(hdev, false);
+	ret = hclge_pause_setup_hw(hdev, false);
+	if (ret)
+		return ret;
+
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
+
+	ret = hclge_buffer_alloc(hdev);
+	if (ret) {
+		hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+		return ret;
+	}
+
+	return hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 }
 
 /* DCBX configuration */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
index 278f21e02736..b04702e65689 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_DCB_H__
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fd7f94372ff0..c052bb33b3d3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -906,6 +906,9 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 
+		/* nic's msix numbers is always equals to the roce's. */
+		hdev->num_nic_msi = hdev->num_roce_msi;
+
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
 		 */
@@ -915,6 +918,15 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		hdev->num_msi =
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+
+		hdev->num_nic_msi = hdev->num_msi;
+	}
+
+	if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) {
+		dev_err(&hdev->pdev->dev,
+			"Just %u msi resources, not enough for pf(min:2).\n",
+			hdev->num_nic_msi);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -1507,6 +1519,10 @@ static int  hclge_assign_tqp(struct hclge_vport *vport, u16 num_tqps)
 	kinfo->rss_size = min_t(u16, hdev->rss_size_max,
 				vport->alloc_tqps / hdev->tm_info.num_tc);
 
+	/* ensure one to one mapping between irq and queue at default */
+	kinfo->rss_size = min_t(u16, kinfo->rss_size,
+				(hdev->num_nic_msi - 1) / hdev->tm_info.num_tc);
+
 	return 0;
 }
 
@@ -2285,7 +2301,8 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 	int vectors;
 	int i;
 
-	vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+	vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM,
+					hdev->num_msi,
 					PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (vectors < 0) {
 		dev_err(&pdev->dev,
@@ -2300,6 +2317,7 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
+
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = hdev->base_msi_vector +
 				hdev->roce_base_msix_offset;
@@ -3569,12 +3587,28 @@ static int hclge_set_rst_done(struct hclge_dev *hdev)
 {
 	struct hclge_pf_rst_done_cmd *req;
 	struct hclge_desc desc;
+	int ret;
 
 	req = (struct hclge_pf_rst_done_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false);
 	req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT;
 
-	return hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	/* To be compatible with the old firmware, which does not support
+	 * command HCLGE_OPC_PF_RST_DONE, just print a warning and
+	 * return success
+	 */
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&hdev->pdev->dev,
+			 "current firmware does not support command(0x%x)!\n",
+			 HCLGE_OPC_PF_RST_DONE);
+		return 0;
+	} else if (ret) {
+		dev_err(&hdev->pdev->dev, "assert PF reset done fail %d!\n",
+			ret);
+	}
+
+	return ret;
 }
 
 static int hclge_reset_prepare_up(struct hclge_dev *hdev)
@@ -3903,6 +3937,7 @@ static int hclge_get_vector(struct hnae3_handle *handle, u16 vector_num,
 	int alloc = 0;
 	int i, j;
 
+	vector_num = min_t(u16, hdev->num_nic_msi - 1, vector_num);
 	vector_num = min(hdev->num_msi_left, vector_num);
 
 	for (j = 0; j < vector_num; j++) {
@@ -6228,11 +6263,23 @@ static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid,
 
 	func_id = hclge_get_port_number(HOST_PORT, 0, vfid, 0);
 	req = (struct hclge_mac_vlan_switch_cmd *)desc.data;
+
+	/* read current config parameter */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_SWITCH_PARAM,
-				   false);
+				   true);
 	req->roce_sel = HCLGE_MAC_VLAN_NIC_SEL;
 	req->func_id = cpu_to_le32(func_id);
-	req->switch_param = switch_param;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"read mac vlan switch parameter fail, ret = %d\n", ret);
+		return ret;
+	}
+
+	/* modify and write new config parameter */
+	hclge_cmd_reuse_desc(&desc, false);
+	req->switch_param = (req->switch_param & param_mask) | switch_param;
 	req->param_mask = param_mask;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 3e9574a9e22d..615cde1cbf0b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MAIN_H
@@ -166,7 +166,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_GLOBAL_RESET_BIT		0
 #define HCLGE_CORE_RESET_BIT		1
 #define HCLGE_IMP_RESET_BIT		2
-#define HCLGE_RESET_INT_M		GENMASK(2, 0)
+#define HCLGE_RESET_INT_M		GENMASK(7, 5)
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
@@ -763,6 +763,7 @@ struct hclge_dev {
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
+	u16 num_nic_msi;	/* Num of nic vectors for this PF */
 	u16 num_roce_msi;	/* Num of roce vectors for this PF */
 	int roce_base_vector;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index ef095d9c566f..dd9a1218a7b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MDIO_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 9f0e35f27789..62399cc1c5a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -537,9 +537,16 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 		kinfo->rss_size = kinfo->req_rss_size;
 	} else if (kinfo->rss_size > max_rss_size ||
 		   (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) {
+		/* if user not set rss, the rss_size should compare with the
+		 * valid msi numbers to ensure one to one map between tqp and
+		 * irq as default.
+		 */
+		if (!kinfo->req_rss_size)
+			max_rss_size = min_t(u16, max_rss_size,
+					     (hdev->num_nic_msi - 1) /
+					     kinfo->num_tc);
+
 		/* Set to the maximum specification value (max_rss_size). */
-		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
-			 kinfo->rss_size, max_rss_size);
 		kinfo->rss_size = max_rss_size;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 818610988d34..260f22d19d81 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_TM_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index e3090b3dab1d..7d7e712691b9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -411,6 +411,13 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 		kinfo->tqp[i] = &hdev->htqp[i].q;
 	}
 
+	/* after init the max rss_size and tqps, adjust the default tqp numbers
+	 * and rss size with the actual vector numbers
+	 */
+	kinfo->num_tqps = min_t(u16, hdev->num_nic_msix - 1, kinfo->num_tqps);
+	kinfo->rss_size = min_t(u16, kinfo->num_tqps / kinfo->num_tc,
+				kinfo->rss_size);
+
 	return 0;
 }
 
@@ -502,6 +509,7 @@ static int hclgevf_get_vector(struct hnae3_handle *handle, u16 vector_num,
 	int alloc = 0;
 	int i, j;
 
+	vector_num = min_t(u16, hdev->num_nic_msix - 1, vector_num);
 	vector_num = min(hdev->num_msi_left, vector_num);
 
 	for (j = 0; j < vector_num; j++) {
@@ -2246,13 +2254,14 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	int vectors;
 	int i;
 
-	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
+	if (hnae3_dev_roce_supported(hdev))
 		vectors = pci_alloc_irq_vectors(pdev,
 						hdev->roce_base_msix_offset + 1,
 						hdev->num_msi,
 						PCI_IRQ_MSIX);
 	else
-		vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+		vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM,
+						hdev->num_msi,
 						PCI_IRQ_MSI | PCI_IRQ_MSIX);
 
 	if (vectors < 0) {
@@ -2268,6 +2277,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
+
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset;
 
@@ -2533,7 +2543,7 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 
 	req = (struct hclgevf_query_res_cmd *)desc.data;
 
-	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) {
+	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->roce_base_msix_offset =
 		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
 				HCLGEVF_MSIX_OFT_ROCEE_M,
@@ -2542,6 +2552,9 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
 				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
 
+		/* nic's msix numbers is always equals to the roce's. */
+		hdev->num_nic_msix = hdev->num_roce_msix;
+
 		/* VF should have NIC vectors and Roce vectors, NIC vectors
 		 * are queued before Roce vectors. The offset is fixed to 64.
 		 */
@@ -2551,6 +2564,15 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 		hdev->num_msi =
 		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
 				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+
+		hdev->num_nic_msix = hdev->num_msi;
+	}
+
+	if (hdev->num_nic_msix < HNAE3_MIN_VECTOR_NUM) {
+		dev_err(&hdev->pdev->dev,
+			"Just %u msi resources, not enough for vf(min:2).\n",
+			hdev->num_nic_msix);
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index bdde3afc286b..2b8d6bc6d224 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -270,6 +270,7 @@ struct hclgevf_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 num_nic_msix;	/* Num of nic vectors for this VF */
 	u16 num_roce_msix;	/* Num of roce vectors for this VF */
 	u16 roce_base_msix_offset;
 	int roce_base_vector;
diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index 211c5f74b4c8..aec7e98bcc85 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -96,6 +96,8 @@
 
 #define OPT_SWAP_PORT	0x0001	/* Need to wordswp on the MPU port */
 
+#define LIB82596_DMA_ATTR	DMA_ATTR_NON_CONSISTENT
+
 #define DMA_WBACK(ndev, addr, len) \
 	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0)
 
@@ -200,7 +202,7 @@ static int __exit lan_remove_chip(struct parisc_device *pdev)
 
 	unregister_netdev (dev);
 	dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	free_netdev (dev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 1274ad24d6af..f9742af7f142 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1065,7 +1065,7 @@ static int i82596_probe(struct net_device *dev)
 
 	dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma),
 			      &lp->dma_addr, GFP_KERNEL,
-			      DMA_ATTR_NON_CONSISTENT);
+			      LIB82596_DMA_ATTR);
 	if (!dma) {
 		printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__);
 		return -ENOMEM;
@@ -1087,7 +1087,7 @@ static int i82596_probe(struct net_device *dev)
 	i = register_netdev(dev);
 	if (i) {
 		dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			       dma, lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+			       dma, lp->dma_addr, LIB82596_DMA_ATTR);
 		return i;
 	}
 
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index 6eb6c2ff7f09..6436a98c5953 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -24,6 +24,8 @@
 
 static const char sni_82596_string[] = "snirm_82596";
 
+#define LIB82596_DMA_ATTR	0
+
 #define DMA_WBACK(priv, addr, len)     do { } while (0)
 #define DMA_INV(priv, addr, len)       do { } while (0)
 #define DMA_WBACK_INV(priv, addr, len) do { } while (0)
@@ -152,7 +154,7 @@ static int sni_82596_driver_remove(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	iounmap(lp->ca);
 	iounmap(lp->mpu_port);
 	free_netdev (dev);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2b073a3c0b84..0686ded7ad3a 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2881,7 +2881,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 		u64 val = (0xff000000) | scrq->hw_irq;
 
 		rc = plpar_hcall_norets(H_EOI, val);
-		if (rc)
+		/* H_EOI would fail with rc = H_FUNCTION when running
+		 * in XIVE mode which is expected, but not an error.
+		 */
+		if (rc && (rc != H_FUNCTION))
 			dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
 				val, rc);
 	}
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 71d3d8854d8f..be56e631d693 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -607,6 +607,7 @@ static int e1000_set_ringparam(struct net_device *netdev,
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		rxdr[i].count = rxdr->count;
 
+	err = 0;
 	if (netif_running(adapter->netdev)) {
 		/* Try to get new resources before deleting old */
 		err = e1000_setup_all_rx_resources(adapter);
@@ -627,14 +628,13 @@ static int e1000_set_ringparam(struct net_device *netdev,
 		adapter->rx_ring = rxdr;
 		adapter->tx_ring = txdr;
 		err = e1000_up(adapter);
-		if (err)
-			goto err_setup;
 	}
 	kfree(tx_old);
 	kfree(rx_old);
 
 	clear_bit(__E1000_RESETTING, &adapter->flags);
-	return 0;
+	return err;
+
 err_setup_tx:
 	e1000_free_all_rx_resources(adapter);
 err_setup_rx:
@@ -646,7 +646,6 @@ err_alloc_rx:
 err_alloc_tx:
 	if (netif_running(adapter->netdev))
 		e1000_up(adapter);
-err_setup:
 	clear_bit(__E1000_RESETTING, &adapter->flags);
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 530613f31527..69a2daaca5c5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -20,6 +20,8 @@
 
 /* API version 1.7 implements additional link and PHY-specific APIs  */
 #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+/* API version 1.9 for X722 implements additional link and PHY-specific APIs */
+#define I40E_MINOR_VER_GET_LINK_INFO_X722 0x0009
 /* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */
 #define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d37c6e0e5f08..7560f06768e0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1876,7 +1876,8 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	     hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
 		hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE &&
+	    hw->mac.type != I40E_MAC_X722) {
 		__le32 tmp;
 
 		memcpy(&tmp, resp->link_type, sizeof(tmp));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index b1c3227ae4ab..d07e1a890428 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -157,11 +157,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
-
-		/* Kick start the NAPI context so that receiving will start */
-		err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX);
-		if (err)
-			return err;
 	}
 
 	return 0;
@@ -694,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 		i40e_xdp_ring_update_tail(xdp_ring);
 
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
-		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
-			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -774,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 	i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
 
 out_xmit:
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
-		if (tx_ring->next_to_clean == tx_ring->next_to_use)
-			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
-		else
-			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
-	}
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
 
 	xmit_done = i40e_xmit_zc(tx_ring, budget);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 8f310e520b06..821987da5698 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -314,7 +314,7 @@ iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx)
 	q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
 	q_vector->ring_mask |= BIT(r_idx);
 	wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx),
-	     q_vector->rx.current_itr);
+	     q_vector->rx.current_itr >> 1);
 	q_vector->rx.current_itr = q_vector->rx.target_itr;
 }
 
@@ -340,7 +340,7 @@ iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx)
 	q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
 	q_vector->num_ringpairs++;
 	wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx),
-	     q_vector->tx.target_itr);
+	     q_vector->tx.target_itr >> 1);
 	q_vector->tx.current_itr = q_vector->tx.target_itr;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index fc624b73d05d..2fde9653a608 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1036,7 +1036,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw)
 	struct ice_aqc_query_txsched_res_resp *buf;
 	enum ice_status status = 0;
 	__le16 max_sibl;
-	u8 i;
+	u16 i;
 
 	if (hw->layer_info)
 		return status;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 3ec2ce0725d5..8a6ef3514129 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -466,7 +466,7 @@ static s32 igb_init_mac_params_82575(struct e1000_hw *hw)
 			? igb_setup_copper_link_82575
 			: igb_setup_serdes_link_82575;
 
-	if (mac->type == e1000_82580) {
+	if (mac->type == e1000_82580 || mac->type == e1000_i350) {
 		switch (hw->device_id) {
 		/* feature not supported on these id's */
 		case E1000_DEV_ID_DH89XXCC_SGMII:
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 105b0624081a..ed7e667d7eb2 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -753,7 +753,8 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg)
 		struct net_device *netdev = igb->netdev;
 		hw->hw_addr = NULL;
 		netdev_err(netdev, "PCIe link lost\n");
-		WARN(1, "igb: Failed to read reg 0x%x!\n", reg);
+		WARN(pci_device_is_present(igb->pdev),
+		     "igb: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
@@ -2064,7 +2065,8 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 	if ((hw->phy.media_type == e1000_media_type_copper) &&
 	    (!(connsw & E1000_CONNSW_AUTOSENSE_EN))) {
 		swap_now = true;
-	} else if (!(connsw & E1000_CONNSW_SERDESD)) {
+	} else if ((hw->phy.media_type != e1000_media_type_copper) &&
+		   !(connsw & E1000_CONNSW_SERDESD)) {
 		/* copper signal takes time to appear */
 		if (adapter->copper_tries < 4) {
 			adapter->copper_tries++;
@@ -2370,7 +2372,7 @@ void igb_reset(struct igb_adapter *adapter)
 		adapter->ei.get_invariants(hw);
 		adapter->flags &= ~IGB_FLAG_MEDIA_RESET;
 	}
-	if ((mac->type == e1000_82575) &&
+	if ((mac->type == e1000_82575 || mac->type == e1000_i350) &&
 	    (adapter->flags & IGB_FLAG_MAS_ENABLE)) {
 		igb_enable_mas(adapter);
 	}
@@ -5673,8 +5675,8 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
 	 * should have been handled by the upper layers.
 	 */
 	if (tx_ring->launchtime_enable) {
-		ts = ns_to_timespec64(first->skb->tstamp);
-		first->skb->tstamp = 0;
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		first->skb->tstamp = ktime_set(0, 0);
 		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
 	} else {
 		context_desc->seqnum_seed = 0;
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index fd3071f55bd3..c39e921757ba 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -521,6 +521,19 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
+		/* Reject requests with unsupported flags */
+		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
+					PTP_RISING_EDGE |
+					PTP_FALLING_EDGE |
+					PTP_STRICT_FLAGS))
+			return -EOPNOTSUPP;
+
+		/* Reject requests failing to enable both edges. */
+		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
+		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+		    (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
+			return -EOPNOTSUPP;
+
 		if (on) {
 			pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS,
 					   rq->extts.index);
@@ -551,6 +564,10 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
+		/* Reject requests with unsupported flags */
+		if (rq->perout.flags)
+			return -EOPNOTSUPP;
+
 		if (on) {
 			pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT,
 					   rq->perout.index);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 63b62d74f961..24888676f69b 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -824,8 +824,8 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
 	 * should have been handled by the upper layers.
 	 */
 	if (tx_ring->launchtime_enable) {
-		ts = ns_to_timespec64(first->skb->tstamp);
-		first->skb->tstamp = 0;
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		first->skb->tstamp = ktime_set(0, 0);
 		context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32);
 	} else {
 		context_desc->launch_time = 0;
@@ -4047,7 +4047,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 		hw->hw_addr = NULL;
 		netif_device_detach(netdev);
 		netdev_err(netdev, "PCIe link lost, device now detached\n");
-		WARN(1, "igc: Failed to read reg 0x%x!\n", reg);
+		WARN(pci_device_is_present(igc->pdev),
+		     "igc: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1ce2397306b9..91b3780ddb04 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4310,7 +4310,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 
-		clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
 		if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
 			continue;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 100ac89b345d..d6feaacfbf89 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -622,8 +622,6 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	if (tx_desc) {
 		ixgbe_xdp_ring_update_tail(xdp_ring);
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
-		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
-			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -691,12 +689,8 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (xsk_frames)
 		xsk_umem_complete_tx(umem, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
-		if (tx_ring->next_to_clean == tx_ring->next_to_use)
-			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
-		else
-			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
-	}
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
 
 	return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
 }
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index c8425d35c049..e47783ce77e0 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -160,16 +160,23 @@ static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 			     (bm_pool->id << MVNETA_BM_POOL_ACCESS_OFFS));
 }
 #else
-void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
-			    struct mvneta_bm_pool *bm_pool, u8 port_map) {}
-void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
-			 u8 port_map) {}
-int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf) { return 0; }
-int mvneta_bm_pool_refill(struct mvneta_bm *priv,
-			  struct mvneta_bm_pool *bm_pool) {return 0; }
-struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
-					  enum mvneta_bm_type type, u8 port_id,
-					  int pkt_size) { return NULL; }
+static inline void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
+					  struct mvneta_bm_pool *bm_pool,
+					  u8 port_map) {}
+static inline void mvneta_bm_bufs_free(struct mvneta_bm *priv,
+				       struct mvneta_bm_pool *bm_pool,
+				       u8 port_map) {}
+static inline int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf)
+{ return 0; }
+static inline int mvneta_bm_pool_refill(struct mvneta_bm *priv,
+					struct mvneta_bm_pool *bm_pool)
+{ return 0; }
+static inline struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv,
+							u8 pool_id,
+							enum mvneta_bm_type type,
+							u8 port_id,
+							int pkt_size)
+{ return NULL; }
 
 static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 					 struct mvneta_bm_pool *bm_pool,
@@ -178,7 +185,8 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 					struct mvneta_bm_pool *bm_pool)
 { return 0; }
-struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; }
-void mvneta_bm_put(struct mvneta_bm *priv) {}
+static inline struct mvneta_bm *mvneta_bm_get(struct device_node *node)
+{ return NULL; }
+static inline void mvneta_bm_put(struct mvneta_bm *priv) {}
 #endif /* CONFIG_MVNETA_BM */
 #endif
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 206dc5dc1df8..5c1f389e3320 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 CGX driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 CGX driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index fb3ba4968a9b..473d9751601f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 CGX driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 CGX driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index e332e82fc066..413c3f254cf8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 76a4575d18ff..75439fce0505 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 8d6d90fdfb73..5d4df315a0e1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
index b2ce957605bb..da649f6a5573 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c9d60b0554c0..5222e4228905 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 09a8d61f3144..1ea92a2e7cfe 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index f920dac74e6c..84a39063a8bb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Marvell OcteonTx2 RVU Admin Function driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/*  Marvell OcteonTx2 RVU Admin Function driver
  *
  * Copyright (C) 2018 Marvell International Ltd.
  *
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c61069340f4f..703adb96429e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -261,6 +261,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 		ge_mode = 0;
 		switch (state->interface) {
 		case PHY_INTERFACE_MODE_MII:
+		case PHY_INTERFACE_MODE_GMII:
 			ge_mode = 1;
 			break;
 		case PHY_INTERFACE_MODE_REVMII:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d8313e2ee600..a1202e53710c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		err = mlx4_en_get_flow(dev, cmd, cmd->fs.location);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
+		cmd->data = MAX_NUM_OF_FS_RULES;
 		while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) {
 			err = mlx4_en_get_flow(dev, cmd, i);
 			if (!err)
@@ -1811,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_tx_count;
 	int port_up = 0;
 	int xdp_count;
 	int err = 0;
@@ -1825,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	mutex_lock(&mdev->state_lock);
 	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
-	if (channel->tx_count * priv->prof->num_up + xdp_count >
-	    priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) {
+	total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count;
+	if (total_tx_count > MAX_TX_RINGS) {
 		err = -EINVAL;
 		en_err(priv,
 		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
-		       channel->tx_count * priv->prof->num_up  + xdp_count,
-		       MAX_TX_RINGS);
+		       total_tx_count, MAX_TX_RINGS);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 40ec5acf79c0..70fd246840e2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -91,6 +91,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_count;
 	int port_up = 0;
 	int err = 0;
 
@@ -104,6 +105,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 				      MLX4_EN_NUM_UP_HIGH;
 	new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up *
 				   new_prof.num_up;
+	total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP];
+	if (total_count > MAX_TX_RINGS) {
+		err = -EINVAL;
+		en_err(priv,
+		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+		       total_count, MAX_TX_RINGS);
+		goto out;
+	}
 	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index fce9b3a24347..d44ac666e730 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -514,8 +514,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rq_desc_sz     = dev_cap->max_rq_desc_sz;
 	/*
 	 * Subtract 1 from the limit because we need to allocate a
-	 * spare CQE so the HCA HW can tell the difference between an
-	 * empty CQ and a full CQ.
+	 * spare CQE to enable resizing the CQ.
 	 */
 	dev->caps.max_cqes	     = dev_cap->max_cq_sz - 1;
 	dev->caps.reserved_cqs	     = dev_cap->reserved_cqs;
@@ -4011,6 +4010,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_params_unregister;
 
 	devlink_params_publish(devlink);
+	devlink_reload_enable(devlink);
 	pci_save_state(pdev);
 	return 0;
 
@@ -4122,6 +4122,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
+	devlink_reload_disable(devlink);
+
 	if (mlx4_is_slave(dev))
 		persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 4356f3a58002..1187ef1375e2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -471,12 +471,31 @@ void mlx4_init_quotas(struct mlx4_dev *dev)
 		priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf];
 }
 
-static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev)
+static int
+mlx4_calc_res_counter_guaranteed(struct mlx4_dev *dev,
+				 struct resource_allocator *res_alloc,
+				 int vf)
 {
-	/* reduce the sink counter */
-	return (dev->caps.max_counters - 1 -
-		(MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS))
-		/ MLX4_MAX_PORTS;
+	struct mlx4_active_ports actv_ports;
+	int ports, counters_guaranteed;
+
+	/* For master, only allocate according to the number of phys ports */
+	if (vf == mlx4_master_func_num(dev))
+		return MLX4_PF_COUNTERS_PER_PORT * dev->caps.num_ports;
+
+	/* calculate real number of ports for the VF */
+	actv_ports = mlx4_get_active_ports(dev, vf);
+	ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+	counters_guaranteed = ports * MLX4_VF_COUNTERS_PER_PORT;
+
+	/* If we do not have enough counters for this VF, do not
+	 * allocate any for it. '-1' to reduce the sink counter.
+	 */
+	if ((res_alloc->res_reserved + counters_guaranteed) >
+	    (dev->caps.max_counters - 1))
+		return 0;
+
+	return counters_guaranteed;
 }
 
 int mlx4_init_resource_tracker(struct mlx4_dev *dev)
@@ -484,7 +503,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, j;
 	int t;
-	int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev);
 
 	priv->mfunc.master.res_tracker.slave_list =
 		kcalloc(dev->num_slaves, sizeof(struct slave_list),
@@ -603,16 +621,8 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			case RES_COUNTER:
 				res_alloc->quota[t] = dev->caps.max_counters;
-				if (t == mlx4_master_func_num(dev))
-					res_alloc->guaranteed[t] =
-						MLX4_PF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else if (t <= max_vfs_guarantee_counter)
-					res_alloc->guaranteed[t] =
-						MLX4_VF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else
-					res_alloc->guaranteed[t] = 0;
+				res_alloc->guaranteed[t] =
+					mlx4_calc_res_counter_guaranteed(dev, res_alloc, t);
 				break;
 			default:
 				break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8d76452cacdc..f1a7bc46f1c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -345,7 +345,7 @@ struct mlx5e_tx_wqe_info {
 	u8  num_wqebbs;
 	u8  num_dma;
 #ifdef CONFIG_MLX5_EN_TLS
-	skb_frag_t *resync_dump_frag;
+	struct page *resync_dump_frag_page;
 #endif
 };
 
@@ -410,6 +410,7 @@ struct mlx5e_txqsq {
 	struct device             *pdev;
 	__be32                     mkey_be;
 	unsigned long              state;
+	unsigned int               hw_mtu;
 	struct hwtstamp_config    *tstamp;
 	struct mlx5_clock         *clock;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
index b3a249b2a482..ac44bbe95c5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
@@ -141,7 +141,7 @@ int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
 				    "Failed to create hv vhca stats agent, err = %ld\n",
 				    PTR_ERR(agent));
 
-		kfree(priv->stats_agent.buf);
+		kvfree(priv->stats_agent.buf);
 		return IS_ERR_OR_NULL(agent);
 	}
 
@@ -157,5 +157,5 @@ void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
 		return;
 
 	mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
-	kfree(priv->stats_agent.buf);
+	kvfree(priv->stats_agent.buf);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f8ee18b4da6f..745ab6cd7c30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -97,15 +97,19 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET)
+	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) {
+		ip_rt_put(rt);
 		return -ENETUNREACH;
+	}
 #else
 	return -EOPNOTSUPP;
 #endif
 
 	ret = get_route_and_out_devs(priv, rt->dst.dev, route_dev, out_dev);
-	if (ret < 0)
+	if (ret < 0) {
+		ip_rt_put(rt);
 		return ret;
+	}
 
 	if (!(*out_ttl))
 		*out_ttl = ip4_dst_hoplimit(&rt->dst);
@@ -149,8 +153,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 		*out_ttl = ip6_dst_hoplimit(dst);
 
 	ret = get_route_and_out_devs(priv, dst->dev, route_dev, out_dev);
-	if (ret < 0)
+	if (ret < 0) {
+		dst_release(dst);
 		return ret;
+	}
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -233,12 +239,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv4_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		goto out;
 	}
 
 	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
+	if (!encap_header) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -349,12 +358,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv6_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		goto out;
 	}
 
 	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
+	if (!encap_header) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 87be96747902..7c8796d9743f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -15,15 +15,14 @@
 #else
 /* TLS offload requires additional stop_room for:
  *  - a resync SKB.
- * kTLS offload requires additional stop_room for:
- * - static params WQE,
- * - progress params WQE, and
- * - resync DUMP per frag.
+ * kTLS offload requires fixed additional stop_room for:
+ * - a static params WQE, and a progress params WQE.
+ * The additional MTU-depending room for the resync DUMP WQEs
+ * will be calculated and added in runtime.
  */
 #define MLX5E_SQ_TLS_ROOM  \
 	(MLX5_SEND_WQE_MAX_WQEBBS + \
-	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS + \
-	 MAX_SKB_FRAGS * MLX5E_KTLS_MAX_DUMP_WQEBBS)
+	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS)
 #endif
 
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
@@ -92,7 +91,7 @@ mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
 
 	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
-		wi->skb        = NULL;
+		memset(wi, 0, sizeof(*wi));
 		wi->num_wqebbs = 1;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index d2ff74d52720..46725cd743a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -38,7 +38,7 @@ static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk,
 		return -ENOMEM;
 
 	tx_priv->expected_seq = start_offload_tcp_sn;
-	tx_priv->crypto_info  = crypto_info;
+	tx_priv->crypto_info  = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	mlx5e_set_ktls_tx_priv_ctx(tls_ctx, tx_priv);
 
 	/* tc and underlay_qpn values are not in use for tls tis */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index b7298f9ee3d3..a3efa29a4629 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -21,7 +21,14 @@
 	 MLX5_ST_SZ_BYTES(tls_progress_params))
 #define MLX5E_KTLS_PROGRESS_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
-#define MLX5E_KTLS_MAX_DUMP_WQEBBS 2
+
+struct mlx5e_dump_wqe {
+	struct mlx5_wqe_ctrl_seg ctrl;
+	struct mlx5_wqe_data_seg data;
+};
+
+#define MLX5E_KTLS_DUMP_WQEBBS \
+	(DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB))
 
 enum {
 	MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD     = 0,
@@ -37,7 +44,7 @@ enum {
 
 struct mlx5e_ktls_offload_context_tx {
 	struct tls_offload_context_tx *tx_ctx;
-	struct tls_crypto_info *crypto_info;
+	struct tls12_crypto_info_aes_gcm_128 crypto_info;
 	u32 expected_seq;
 	u32 tisn;
 	u32 key_id;
@@ -86,14 +93,28 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 					 struct mlx5e_tx_wqe **wqe, u16 *pi);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
-					   struct mlx5e_sq_dma *dma);
-
+					   u32 *dma_fifo_cc);
+static inline u8
+mlx5e_ktls_dumps_num_wqebbs(struct mlx5e_txqsq *sq, unsigned int nfrags,
+			    unsigned int sync_len)
+{
+	/* Given the MTU and sync_len, calculates an upper bound for the
+	 * number of WQEBBs needed for the TX resync DUMP WQEs of a record.
+	 */
+	return MLX5E_KTLS_DUMP_WQEBBS *
+		(nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu));
+}
 #else
 
 static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
 {
 }
 
+static inline void
+mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+				      struct mlx5e_tx_wqe_info *wi,
+				      u32 *dma_fifo_cc) {}
+
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index d195366461c9..778dab1af8fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -24,17 +24,12 @@ enum {
 static void
 fill_static_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
 {
-	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
-	struct tls12_crypto_info_aes_gcm_128 *info;
+	struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info;
 	char *initial_rn, *gcm_iv;
 	u16 salt_sz, rec_seq_sz;
 	char *salt, *rec_seq;
 	u8 tls_version;
 
-	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
-		return;
-
-	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	EXTRACT_INFO_FIELDS;
 
 	gcm_iv      = MLX5_ADDR_OF(tls_static_params, ctx, gcm_iv);
@@ -108,16 +103,15 @@ build_progress_params(struct mlx5e_tx_wqe *wqe, u16 pc, u32 sqn,
 }
 
 static void tx_fill_wi(struct mlx5e_txqsq *sq,
-		       u16 pi, u8 num_wqebbs,
-		       skb_frag_t *resync_dump_frag,
-		       u32 num_bytes)
+		       u16 pi, u8 num_wqebbs, u32 num_bytes,
+		       struct page *page)
 {
 	struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
 
-	wi->skb              = NULL;
-	wi->num_wqebbs       = num_wqebbs;
-	wi->resync_dump_frag = resync_dump_frag;
-	wi->num_bytes        = num_bytes;
+	memset(wi, 0, sizeof(*wi));
+	wi->num_wqebbs = num_wqebbs;
+	wi->num_bytes  = num_bytes;
+	wi->resync_dump_frag_page = page;
 }
 
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
@@ -145,7 +139,7 @@ post_static_params(struct mlx5e_txqsq *sq,
 
 	umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi);
 	build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL, 0);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
 }
 
@@ -159,7 +153,7 @@ post_progress_params(struct mlx5e_txqsq *sq,
 
 	wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi);
 	build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL, 0);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
 }
 
@@ -169,6 +163,14 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 			      bool skip_static_post, bool fence_first_post)
 {
 	bool progress_fence = skip_static_post || !fence_first_post;
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 contig_wqebbs_room, pi;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room <
+		     MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS))
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
 	if (!skip_static_post)
 		post_static_params(sq, priv_tx, fence_first_post);
@@ -180,29 +182,36 @@ struct tx_sync_info {
 	u64 rcd_sn;
 	s32 sync_len;
 	int nr_frags;
-	skb_frag_t *frags[MAX_SKB_FRAGS];
+	skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+enum mlx5e_ktls_sync_retval {
+	MLX5E_KTLS_SYNC_DONE,
+	MLX5E_KTLS_SYNC_FAIL,
+	MLX5E_KTLS_SYNC_SKIP_NO_DATA,
 };
 
-static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
-			     u32 tcp_seq, struct tx_sync_info *info)
+static enum mlx5e_ktls_sync_retval
+tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
+		 u32 tcp_seq, struct tx_sync_info *info)
 {
 	struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
+	enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE;
 	struct tls_record_info *record;
 	int remaining, i = 0;
 	unsigned long flags;
-	bool ret = true;
 
 	spin_lock_irqsave(&tx_ctx->lock, flags);
 	record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
 
 	if (unlikely(!record)) {
-		ret = false;
+		ret = MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
 	if (unlikely(tcp_seq < tls_record_start_seq(record))) {
-		if (!tls_record_is_start_marker(record))
-			ret = false;
+		ret = tls_record_is_start_marker(record) ?
+			MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
@@ -211,13 +220,13 @@ static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	while (remaining > 0) {
 		skb_frag_t *frag = &record->frags[i];
 
-		__skb_frag_ref(frag);
+		get_page(skb_frag_page(frag));
 		remaining -= skb_frag_size(frag);
-		info->frags[i++] = frag;
+		info->frags[i++] = *frag;
 	}
 	/* reduce the part which will be sent with the original SKB */
 	if (remaining < 0)
-		skb_frag_size_add(info->frags[i - 1], remaining);
+		skb_frag_size_add(&info->frags[i - 1], remaining);
 	info->nr_frags = i;
 out:
 	spin_unlock_irqrestore(&tx_ctx->lock, flags);
@@ -229,17 +238,12 @@ tx_post_resync_params(struct mlx5e_txqsq *sq,
 		      struct mlx5e_ktls_offload_context_tx *priv_tx,
 		      u64 rcd_sn)
 {
-	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
-	struct tls12_crypto_info_aes_gcm_128 *info;
+	struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info;
 	__be64 rn_be = cpu_to_be64(rcd_sn);
 	bool skip_static_post;
 	u16 rec_seq_sz;
 	char *rec_seq;
 
-	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
-		return;
-
-	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	rec_seq = info->rec_seq;
 	rec_seq_sz = sizeof(info->rec_seq);
 
@@ -250,11 +254,6 @@ tx_post_resync_params(struct mlx5e_txqsq *sq,
 	mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, skip_static_post, true);
 }
 
-struct mlx5e_dump_wqe {
-	struct mlx5_wqe_ctrl_seg ctrl;
-	struct mlx5_wqe_data_seg data;
-};
-
 static int
 tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool first)
 {
@@ -262,7 +261,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	struct mlx5_wqe_data_seg *dseg;
 	struct mlx5e_dump_wqe *wqe;
 	dma_addr_t dma_addr = 0;
-	u8  num_wqebbs;
 	u16 ds_cnt;
 	int fsz;
 	u16 pi;
@@ -270,7 +268,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 
 	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
-	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 
 	cseg = &wqe->ctrl;
 	dseg = &wqe->data;
@@ -291,24 +288,27 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	dseg->byte_count = cpu_to_be32(fsz);
 	mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
 
-	tx_fill_wi(sq, pi, num_wqebbs, frag, fsz);
-	sq->pc += num_wqebbs;
-
-	WARN(num_wqebbs > MLX5E_KTLS_MAX_DUMP_WQEBBS,
-	     "unexpected DUMP num_wqebbs, %d > %d",
-	     num_wqebbs, MLX5E_KTLS_MAX_DUMP_WQEBBS);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_DUMP_WQEBBS, fsz, skb_frag_page(frag));
+	sq->pc += MLX5E_KTLS_DUMP_WQEBBS;
 
 	return 0;
 }
 
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
-					   struct mlx5e_sq_dma *dma)
+					   u32 *dma_fifo_cc)
 {
-	struct mlx5e_sq_stats *stats = sq->stats;
+	struct mlx5e_sq_stats *stats;
+	struct mlx5e_sq_dma *dma;
+
+	if (!wi->resync_dump_frag_page)
+		return;
+
+	dma = mlx5e_dma_get(sq, (*dma_fifo_cc)++);
+	stats = sq->stats;
 
 	mlx5e_tx_dma_unmap(sq->pdev, dma);
-	__skb_frag_unref(wi->resync_dump_frag);
+	put_page(wi->resync_dump_frag_page);
 	stats->tls_dump_packets++;
 	stats->tls_dump_bytes += wi->num_bytes;
 }
@@ -318,25 +318,31 @@ static void tx_post_fence_nop(struct mlx5e_txqsq *sq)
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
-	tx_fill_wi(sq, pi, 1, NULL, 0);
+	tx_fill_wi(sq, pi, 1, 0, NULL);
 
 	mlx5e_post_nop_fence(wq, sq->sqn, &sq->pc);
 }
 
-static struct sk_buff *
+static enum mlx5e_ktls_sync_retval
 mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 			 struct mlx5e_txqsq *sq,
-			 struct sk_buff *skb,
+			 int datalen,
 			 u32 seq)
 {
 	struct mlx5e_sq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
+	enum mlx5e_ktls_sync_retval ret;
 	struct tx_sync_info info = {};
 	u16 contig_wqebbs_room, pi;
 	u8 num_wqebbs;
-	int i;
-
-	if (!tx_sync_info_get(priv_tx, seq, &info)) {
+	int i = 0;
+
+	ret = tx_sync_info_get(priv_tx, seq, &info);
+	if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) {
+		if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) {
+			stats->tls_skip_no_sync_data++;
+			return MLX5E_KTLS_SYNC_SKIP_NO_DATA;
+		}
 		/* We might get here if a retransmission reaches the driver
 		 * after the relevant record is acked.
 		 * It should be safe to drop the packet in this case
@@ -346,13 +352,8 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	}
 
 	if (unlikely(info.sync_len < 0)) {
-		u32 payload;
-		int headln;
-
-		headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
-		payload = skb->len - headln;
-		if (likely(payload <= -info.sync_len))
-			return skb;
+		if (likely(datalen <= -info.sync_len))
+			return MLX5E_KTLS_SYNC_DONE;
 
 		stats->tls_drop_bypass_req++;
 		goto err_out;
@@ -360,30 +361,62 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 
 	stats->tls_ooo++;
 
-	num_wqebbs = MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS +
-		(info.nr_frags ? info.nr_frags * MLX5E_KTLS_MAX_DUMP_WQEBBS : 1);
+	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
+
+	/* If no dump WQE was sent, we need to have a fence NOP WQE before the
+	 * actual data xmit.
+	 */
+	if (!info.nr_frags) {
+		tx_post_fence_nop(sq);
+		return MLX5E_KTLS_SYNC_DONE;
+	}
+
+	num_wqebbs = mlx5e_ktls_dumps_num_wqebbs(sq, info.nr_frags, info.sync_len);
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+
 	if (unlikely(contig_wqebbs_room < num_wqebbs))
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
 	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
 
-	for (i = 0; i < info.nr_frags; i++)
-		if (tx_post_resync_dump(sq, info.frags[i], priv_tx->tisn, !i))
-			goto err_out;
+	for (; i < info.nr_frags; i++) {
+		unsigned int orig_fsz, frag_offset = 0, n = 0;
+		skb_frag_t *f = &info.frags[i];
 
-	/* If no dump WQE was sent, we need to have a fence NOP WQE before the
-	 * actual data xmit.
-	 */
-	if (!info.nr_frags)
-		tx_post_fence_nop(sq);
+		orig_fsz = skb_frag_size(f);
 
-	return skb;
+		do {
+			bool fence = !(i || frag_offset);
+			unsigned int fsz;
+
+			n++;
+			fsz = min_t(unsigned int, sq->hw_mtu, orig_fsz - frag_offset);
+			skb_frag_size_set(f, fsz);
+			if (tx_post_resync_dump(sq, f, priv_tx->tisn, fence)) {
+				page_ref_add(skb_frag_page(f), n - 1);
+				goto err_out;
+			}
+
+			skb_frag_off_add(f, fsz);
+			frag_offset += fsz;
+		} while (frag_offset < orig_fsz);
+
+		page_ref_add(skb_frag_page(f), n - 1);
+	}
+
+	return MLX5E_KTLS_SYNC_DONE;
 
 err_out:
-	dev_kfree_skb_any(skb);
-	return NULL;
+	for (; i < info.nr_frags; i++)
+		/* The put_page() here undoes the page ref obtained in tx_sync_info_get().
+		 * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be
+		 * released only upon their completions (or in mlx5e_free_txqsq_descs,
+		 * if channel closes).
+		 */
+		put_page(skb_frag_page(&info.frags[i]));
+
+	return MLX5E_KTLS_SYNC_FAIL;
 }
 
 struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
@@ -419,10 +452,15 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 
 	seq = ntohl(tcp_hdr(skb)->seq);
 	if (unlikely(priv_tx->expected_seq != seq)) {
-		skb = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, skb, seq);
-		if (unlikely(!skb))
+		enum mlx5e_ktls_sync_retval ret =
+			mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq);
+
+		if (likely(ret == MLX5E_KTLS_SYNC_DONE))
+			*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+		else if (ret == MLX5E_KTLS_SYNC_FAIL)
+			goto err_out;
+		else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */
 			goto out;
-		*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
 	}
 
 	priv_tx->expected_seq = seq + datalen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c5a9c20d7f00..95601269fa2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -708,9 +708,9 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev,
 
 static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings,
 						   u32 eth_proto_cap,
-						   u8 connector_type)
+						   u8 connector_type, bool ext)
 {
-	if (!connector_type || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
+	if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
 		if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
 				   | MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
 				   | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
@@ -842,9 +842,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = {
 		[MLX5E_PORT_OTHER]              = PORT_OTHER,
 	};
 
-static u8 get_connector_port(u32 eth_proto, u8 connector_type)
+static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext)
 {
-	if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
+	if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
 		return ptys2connector_type[connector_type];
 
 	if (eth_proto &
@@ -945,9 +945,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
 	link_ksettings->base.port = get_connector_port(eth_proto_oper,
-						       connector_type);
+						       connector_type, ext);
 	ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
-					       connector_type);
+					       connector_type, ext);
 	get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
 
 	if (an_status == MLX5_AN_COMPLETE)
@@ -1021,7 +1021,7 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 {
 #define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT
 	int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT;
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = {0,};
 
 	bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size);
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7569287f8f3c..2a56e66f58d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1128,6 +1128,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->txq_ix    = txq_ix;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
 	sq->stop_room = MLX5E_SQ_STOP_ROOM;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
@@ -1135,10 +1136,14 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
+#ifdef CONFIG_MLX5_EN_TLS
 	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
-		sq->stop_room += MLX5E_SQ_TLS_ROOM;
+		sq->stop_room += MLX5E_SQ_TLS_ROOM +
+			mlx5e_ktls_dumps_num_wqebbs(sq, MAX_SKB_FRAGS,
+						    TLS_MAX_PAYLOAD_SIZE);
 	}
+#endif
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1349,9 +1354,13 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
 		u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+		struct mlx5e_tx_wqe_info *wi;
 		struct mlx5e_tx_wqe *nop;
 
-		sq->db.wqe_info[pi].skb = NULL;
+		wi = &sq->db.wqe_info[pi];
+
+		memset(wi, 0, sizeof(*wi));
+		wi->num_wqebbs = 1;
 		nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
@@ -4243,9 +4252,12 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 
 	switch (proto) {
 	case IPPROTO_GRE:
+		return features;
 	case IPPROTO_IPIP:
 	case IPPROTO_IPV6:
-		return features;
+		if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP))
+			return features;
+		break;
 	case IPPROTO_UDP:
 		udph = udp_hdr(skb);
 		port = be16_to_cpu(udph->dest);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 95892a3b63a1..cd9bb7c7b341 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -611,8 +611,8 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 
 	mutex_lock(&esw->offloads.encap_tbl_lock);
 	encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
-	if (e->compl_result || (encap_connected == neigh_connected &&
-				ether_addr_equal(e->h_dest, ha)))
+	if (e->compl_result < 0 || (encap_connected == neigh_connected &&
+				    ether_addr_equal(e->h_dest, ha)))
 		goto unlock;
 
 	mlx5e_take_all_encap_flows(e, &flow_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d6a547238de0..82cffb3a9964 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1386,8 +1386,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
-	if (rq->cqd.left)
+	if (rq->cqd.left) {
 		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
+		if (rq->cqd.left || work_done >= budget)
+			goto out;
+	}
 
 	cqe = mlx5_cqwq_get_cqe(cqwq);
 	if (!cqe) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 840ec945ccba..bbff8d8ded76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -35,6 +35,7 @@
 #include <linux/udp.h>
 #include <net/udp.h>
 #include "en.h"
+#include "en/port.h"
 
 enum {
 	MLX5E_ST_LINK_STATE,
@@ -80,22 +81,12 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv)
 
 static int mlx5e_test_link_speed(struct mlx5e_priv *priv)
 {
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	u32 eth_proto_oper;
-	int i;
+	u32 speed;
 
 	if (!netif_carrier_ok(priv->netdev))
 		return 1;
 
-	if (mlx5_query_port_ptys(priv->mdev, out, sizeof(out), MLX5_PTYS_EN, 1))
-		return 1;
-
-	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; i++) {
-		if (eth_proto_oper & MLX5E_PROT_MASK(i))
-			return 0;
-	}
-	return 1;
+	return mlx5e_port_linkspeed(priv->mdev, &speed);
 }
 
 struct mlx5ehdr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index ac6fdcda7019..7e6ebd0505cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -52,11 +52,12 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_skip_no_sync_data) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_no_sync_data) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_bypass_req) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
 #endif
 
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
@@ -288,11 +289,12 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_encrypted_bytes   += sq_stats->tls_encrypted_bytes;
 			s->tx_tls_ctx               += sq_stats->tls_ctx;
 			s->tx_tls_ooo               += sq_stats->tls_ooo;
+			s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
+			s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
 			s->tx_tls_resync_bytes      += sq_stats->tls_resync_bytes;
+			s->tx_tls_skip_no_sync_data += sq_stats->tls_skip_no_sync_data;
 			s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data;
 			s->tx_tls_drop_bypass_req   += sq_stats->tls_drop_bypass_req;
-			s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
-			s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
 #endif
 			s->tx_cqes		+= sq_stats->cqes;
 		}
@@ -1472,10 +1474,12 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_resync_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_skip_no_sync_data) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) },
 #endif
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 79f261bf86ac..869f3502f631 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -129,11 +129,12 @@ struct mlx5e_sw_stats {
 	u64 tx_tls_encrypted_bytes;
 	u64 tx_tls_ctx;
 	u64 tx_tls_ooo;
+	u64 tx_tls_dump_packets;
+	u64 tx_tls_dump_bytes;
 	u64 tx_tls_resync_bytes;
+	u64 tx_tls_skip_no_sync_data;
 	u64 tx_tls_drop_no_sync_data;
 	u64 tx_tls_drop_bypass_req;
-	u64 tx_tls_dump_packets;
-	u64 tx_tls_dump_bytes;
 #endif
 
 	u64 rx_xsk_packets;
@@ -273,11 +274,12 @@ struct mlx5e_sq_stats {
 	u64 tls_encrypted_bytes;
 	u64 tls_ctx;
 	u64 tls_ooo;
+	u64 tls_dump_packets;
+	u64 tls_dump_bytes;
 	u64 tls_resync_bytes;
+	u64 tls_skip_no_sync_data;
 	u64 tls_drop_no_sync_data;
 	u64 tls_drop_bypass_req;
-	u64 tls_dump_packets;
-	u64 tls_dump_bytes;
 #endif
 	/* less likely accessed in data path */
 	u64 csum_none;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3e78a727f3e6..f90a9f8e0fc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1278,8 +1278,10 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
 			mlx5e_detach_encap(priv, flow, out_index);
+			kfree(attr->parse_attr->tun_info[out_index]);
+		}
 	kvfree(attr->parse_attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -1559,6 +1561,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr
 			mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
 	}
 
+	kfree(e->tun_info);
 	kfree(e->encap_header);
 	kfree_rcu(e, rcu);
 }
@@ -2972,6 +2975,13 @@ mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
 	return NULL;
 }
 
+static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info)
+{
+	size_t tun_size = sizeof(*tun_info) + tun_info->options_len;
+
+	return kmemdup(tun_info, tun_size, GFP_KERNEL);
+}
+
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow,
 			      struct net_device *mirred_dev,
@@ -3028,13 +3038,15 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	refcount_set(&e->refcnt, 1);
 	init_completion(&e->res_ready);
 
+	tun_info = dup_tun_info(tun_info);
+	if (!tun_info) {
+		err = -ENOMEM;
+		goto out_err_init;
+	}
 	e->tun_info = tun_info;
 	err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
-	if (err) {
-		kfree(e);
-		e = NULL;
-		goto out_err;
-	}
+	if (err)
+		goto out_err_init;
 
 	INIT_LIST_HEAD(&e->flows);
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
@@ -3075,6 +3087,12 @@ out_err:
 	if (e)
 		mlx5e_encap_put(priv, e);
 	return err;
+
+out_err_init:
+	mutex_unlock(&esw->offloads.encap_tbl_lock);
+	kfree(tun_info);
+	kfree(e);
+	return err;
 }
 
 static int parse_tc_vlan_action(struct mlx5e_priv *priv,
@@ -3160,7 +3178,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 			       struct mlx5_esw_flow_attr *attr,
 			       u32 *action)
 {
-	int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev);
+	int nest_level = attr->parse_attr->filter_dev->lower_level;
 	struct flow_action_entry vlan_act = {
 		.id = FLOW_ACTION_VLAN_POP,
 	};
@@ -3250,7 +3268,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			if (netdev_port_same_parent_id(priv->netdev, out_dev)) {
+			if (encap) {
+				parse_attr->mirred_ifindex[attr->out_count] =
+					out_dev->ifindex;
+				parse_attr->tun_info[attr->out_count] = dup_tun_info(info);
+				if (!parse_attr->tun_info[attr->out_count])
+					return -ENOMEM;
+				encap = false;
+				attr->dests[attr->out_count].flags |=
+					MLX5_ESW_DEST_ENCAP;
+				attr->out_count++;
+				/* attr->dests[].rep is resolved when we
+				 * handle encap
+				 */
+			} else if (netdev_port_same_parent_id(priv->netdev, out_dev)) {
 				struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 				struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 				struct net_device *uplink_upper;
@@ -3292,17 +3323,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				attr->dests[attr->out_count].rep = rpriv->rep;
 				attr->dests[attr->out_count].mdev = out_priv->mdev;
 				attr->out_count++;
-			} else if (encap) {
-				parse_attr->mirred_ifindex[attr->out_count] =
-					out_dev->ifindex;
-				parse_attr->tun_info[attr->out_count] = info;
-				encap = false;
-				attr->dests[attr->out_count].flags |=
-					MLX5_ESW_DEST_ENCAP;
-				attr->out_count++;
-				/* attr->dests[].rep is resolved when we
-				 * handle encap
-				 */
 			} else if (parse_attr->filter_dev != priv->netdev) {
 				/* All mlx5 devices are called to configure
 				 * high level device filters. Therefore, the
@@ -3980,9 +4000,8 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
 				struct tc_cls_matchall_offload *ma)
 {
 	struct netlink_ext_ack *extack = ma->common.extack;
-	int prio = TC_H_MAJ(ma->common.prio) >> 16;
 
-	if (prio != 1) {
+	if (ma->common.prio != 1) {
 		NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d3a67a9b4eba..67dc4f0921b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -403,7 +403,10 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 				 struct mlx5_err_cqe *err_cqe)
 {
-	u32 ci = mlx5_cqwq_get_ci(&sq->cq.wq);
+	struct mlx5_cqwq *wq = &sq->cq.wq;
+	u32 ci;
+
+	ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1);
 
 	netdev_err(sq->channel->netdev,
 		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
@@ -479,14 +482,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			skb = wi->skb;
 
 			if (unlikely(!skb)) {
-#ifdef CONFIG_MLX5_EN_TLS
-				if (wi->resync_dump_frag) {
-					struct mlx5e_sq_dma *dma =
-						mlx5e_dma_get(sq, dma_fifo_cc++);
-
-					mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma);
-				}
-#endif
+				mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
 				sqcc += wi->num_wqebbs;
 				continue;
 			}
@@ -542,29 +538,38 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	struct sk_buff *skb;
+	u32 dma_fifo_cc;
+	u16 sqcc;
 	u16 ci;
 	int i;
 
-	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+	sqcc = sq->cc;
+	dma_fifo_cc = sq->dma_fifo_cc;
+
+	while (sqcc != sq->pc) {
+		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 		wi = &sq->db.wqe_info[ci];
 		skb = wi->skb;
 
-		if (!skb) { /* nop */
-			sq->cc++;
+		if (!skb) {
+			mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
+			sqcc += wi->num_wqebbs;
 			continue;
 		}
 
 		for (i = 0; i < wi->num_dma; i++) {
 			struct mlx5e_sq_dma *dma =
-				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+				mlx5e_dma_get(sq, dma_fifo_cc++);
 
 			mlx5e_tx_dma_unmap(sq->pdev, dma);
 		}
 
 		dev_kfree_skb_any(skb);
-		sq->cc += wi->num_wqebbs;
+		sqcc += wi->num_wqebbs;
 	}
+
+	sq->dma_fifo_cc = dma_fifo_cc;
+	sq->cc = sqcc;
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 30aae76b6a1d..60fddf8afc99 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2117,7 +2117,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 
 unlock:
 	mutex_unlock(&esw->state_lock);
-	return 0;
+	return err;
 }
 
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 00d71db15f22..9004a07e457a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -285,7 +285,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 
 	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 	if (attr->outer_match_level != MLX5_MATCH_NONE)
 		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 
@@ -1080,7 +1079,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
 	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
 
-	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(2^%d))\n",
+	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n",
 		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size),
 		  max_flow_counter, ESW_OFFLOADS_NUM_GROUPS,
 		  fdb_max);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index 1d55a324a17e..366bda1bb1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -177,22 +177,33 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src,
 	memset(&src->vlan[1], 0, sizeof(src->vlan[1]));
 }
 
+static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw,
+						const struct mlx5_flow_spec *spec)
+{
+	u32 port_mask, port_value;
+
+	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+		return spec->flow_context.flow_source ==
+					MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	port_mask = MLX5_GET(fte_match_param, spec->match_criteria,
+			     misc_parameters.source_port);
+	port_value = MLX5_GET(fte_match_param, spec->match_value,
+			      misc_parameters.source_port);
+	return (port_mask & port_value & 0xffff) == MLX5_VPORT_UPLINK;
+}
+
 bool
 mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 			      struct mlx5_flow_act *flow_act,
 			      struct mlx5_flow_spec *spec)
 {
-	u32 port_mask = MLX5_GET(fte_match_param, spec->match_criteria,
-				 misc_parameters.source_port);
-	u32 port_value = MLX5_GET(fte_match_param, spec->match_value,
-				  misc_parameters.source_port);
-
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table))
 		return false;
 
 	/* push vlan on RX */
 	return (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) &&
-		((port_mask & port_value) == MLX5_VPORT_UPLINK);
+		mlx5_eswitch_offload_is_uplink_port(esw, spec);
 }
 
 struct mlx5_flow_handle *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 4c50efe4e7f1..61021133029e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -464,8 +464,10 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	}
 
 	err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
-	if (err)
+	if (err) {
+		kvfree(in);
 		goto err_cqwq;
+	}
 
 	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 579c306caa7b..3c816e81f8d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -507,7 +507,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
-				if (extended_dest) {
+				if (extended_dest &&
+				    dst->dest_attr.vport.pkt_reformat) {
 					MLX5_SET(dest_format_struct, in_dests,
 						 packet_reformat,
 						 !!(dst->dest_attr.vport.flags &
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 3bbb49354829..791e14ac26f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -579,7 +579,7 @@ static void del_sw_flow_group(struct fs_node *node)
 
 	rhashtable_destroy(&fg->ftes_hash);
 	ida_destroy(&fg->fte_allocator);
-	if (ft->autogroup.active)
+	if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size)
 		ft->autogroup.num_groups--;
 	err = rhltable_remove(&ft->fgs_hash,
 			      &fg->hash,
@@ -1126,6 +1126,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 
 	ft->autogroup.active = true;
 	ft->autogroup.required_groups = max_num_groups;
+	/* We save place for flow groups in addition to max types */
+	ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1);
 
 	return ft;
 }
@@ -1328,8 +1330,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 		return ERR_PTR(-ENOENT);
 
 	if (ft->autogroup.num_groups < ft->autogroup.required_groups)
-		/* We save place for flow groups in addition to max types */
-		group_size = ft->max_fte / (ft->autogroup.required_groups + 1);
+		group_size = ft->autogroup.group_size;
 
 	/*  ft->max_fte == ft->autogroup.max_types */
 	if (group_size == 0)
@@ -1356,7 +1357,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 	if (IS_ERR(fg))
 		goto out;
 
-	ft->autogroup.num_groups++;
+	if (group_size == ft->autogroup.group_size)
+		ft->autogroup.num_groups++;
 
 out:
 	return fg;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 00717eba2256..c2621b911563 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -162,6 +162,7 @@ struct mlx5_flow_table {
 	struct {
 		bool			active;
 		unsigned int		required_groups;
+		unsigned int		group_size;
 		unsigned int		num_groups;
 	} autogroup;
 	/* Protect fwd_rules */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d685122d9ff7..c07f3154437c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -572,7 +572,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
 		return -ENOMEM;
 	err = mlx5_crdump_collect(dev, cr_data);
 	if (err)
-		return err;
+		goto free_data;
 
 	if (priv_ctx) {
 		struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 0059b290e095..43f97601b500 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -236,6 +236,19 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 	if (!MLX5_PPS_CAP(mdev))
 		return -EOPNOTSUPP;
 
+	/* Reject requests with unsupported flags */
+	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
+				PTP_RISING_EDGE |
+				PTP_FALLING_EDGE |
+				PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
+	/* Reject requests to enable time stamping on both edges. */
+	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
+	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+	    (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES)
+		return -EOPNOTSUPP;
+
 	if (rq->extts.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
@@ -290,6 +303,10 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	if (!MLX5_PPS_CAP(mdev))
 		return -EOPNOTSUPP;
 
+	/* Reject requests with unsupported flags */
+	if (rq->perout.flags)
+		return -EOPNOTSUPP;
+
 	if (rq->perout.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index e47dd7c1b909..50ab88d80033 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1566,6 +1566,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF},	/* ConnectX-6 VF */
 	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
+	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index b74b7d0f6590..004c56c2fc0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -1577,6 +1577,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action)
 		break;
 	case DR_ACTION_TYP_MODIFY_HDR:
 		mlx5dr_icm_free_chunk(action->rewrite.chunk);
+		kfree(action->rewrite.data);
 		refcount_dec(&action->rewrite.dmn->refcount);
 		break;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 4187f2b112b8..bd1699e62142 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -595,6 +595,18 @@ static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule,
 	}
 }
 
+static u16 dr_get_bits_per_mask(u16 byte_mask)
+{
+	u16 bits = 0;
+
+	while (byte_mask) {
+		byte_mask = byte_mask & (byte_mask - 1);
+		bits++;
+	}
+
+	return bits;
+}
+
 static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl,
 				      struct mlx5dr_domain *dmn,
 				      struct mlx5dr_domain_rx_tx *nic_dmn)
@@ -607,6 +619,9 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl,
 	if (!ctrl->may_grow)
 		return false;
 
+	if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size)
+		return false;
+
 	if (ctrl->num_of_collisions >= ctrl->increase_threshold &&
 	    (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold)
 		return true;
@@ -788,12 +803,10 @@ again:
 			 * it means that all the previous stes are the same,
 			 * if so, this rule is duplicated.
 			 */
-			if (mlx5dr_ste_is_last_in_rule(nic_matcher,
-						       matched_ste->ste_chain_location)) {
-				mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n");
-				return NULL;
-			}
-			return matched_ste;
+			if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste_location))
+				return matched_ste;
+
+			mlx5dr_dbg(dmn, "Duplicate rule inserted\n");
 		}
 
 		if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) {
@@ -1098,6 +1111,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 	if (htbl)
 		mlx5dr_htbl_put(htbl);
 
+	kfree(hw_ste_arr);
+
 	return 0;
 
 free_ste:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 5df8436b2ae3..51803eef13dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -700,6 +700,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	unsigned int irqn;
 	void *cqc, *in;
 	__be64 *pas;
+	int vector;
 	u32 i;
 
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -728,7 +729,8 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	if (!in)
 		goto err_cqwq;
 
-	err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
+	vector = smp_processor_id() % mlx5_comp_vectors_count(mdev);
+	err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn);
 	if (err) {
 		kvfree(in);
 		goto err_cqwq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 4efe1b0be4a8..3cbf74b44d1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -560,18 +560,6 @@ bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
 	return !refcount_read(&ste->refcount);
 }
 
-static u16 get_bits_per_mask(u16 byte_mask)
-{
-	u16 bits = 0;
-
-	while (byte_mask) {
-		byte_mask = byte_mask & (byte_mask - 1);
-		bits++;
-	}
-
-	return bits;
-}
-
 /* Init one ste as a pattern for ste data array */
 void mlx5dr_ste_set_formatted_ste(u16 gvmi,
 				  struct mlx5dr_domain_rx_tx *nic_dmn,
@@ -620,20 +608,12 @@ int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher,
 	struct mlx5dr_ste_htbl *next_htbl;
 
 	if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) {
-		u32 bits_in_mask;
 		u8 next_lu_type;
 		u16 byte_mask;
 
 		next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type);
 		byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask);
 
-		/* Don't allocate table more than required,
-		 * the size of the table defined via the byte_mask, so no need
-		 * to allocate more than that.
-		 */
-		bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE;
-		log_table_size = min(log_table_size, bits_in_mask);
-
 		next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
 						  log_table_size,
 						  next_lu_type,
@@ -671,7 +651,7 @@ static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl)
 
 	htbl->ctrl.may_grow = true;
 
-	if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1)
+	if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask)
 		htbl->ctrl.may_grow = false;
 
 	/* Threshold is 50%, one is added to table of size 1 */
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 67990406cba2..29e95d0a6ad1 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -66,6 +66,8 @@ retry:
 		return err;
 
 	if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) {
+		fsm_state_err = min_t(enum mlxfw_fsm_state_err,
+				      fsm_state_err, MLXFW_FSM_STATE_ERR_MAX);
 		pr_err("Firmware flash failed: %s\n",
 		       mlxfw_fsm_state_err_str[fsm_state_err]);
 		NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 14dcc786926d..0a0884d86d44 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1186,9 +1186,12 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
-	if (mlxsw_driver->params_register && !reload)
+	if (mlxsw_driver->params_register)
 		devlink_params_publish(devlink);
 
+	if (!reload)
+		devlink_reload_enable(devlink);
+
 	return 0;
 
 err_thermal_init:
@@ -1249,6 +1252,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
+	if (!reload)
+		devlink_reload_disable(devlink);
 	if (devlink_is_reload_failed(devlink)) {
 		if (!reload)
 			/* Only the parts that were not de-initialized in the
@@ -1259,7 +1264,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 			return;
 	}
 
-	if (mlxsw_core->driver->params_unregister && !reload)
+	if (mlxsw_core->driver->params_unregister)
 		devlink_params_unpublish(devlink);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index a330b369e899..39d600c8b92d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -994,7 +994,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
 	if (d)
 		return l3mdev_fib_table(d) ? : RT_TABLE_MAIN;
 	else
-		return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN;
+		return RT_TABLE_MAIN;
 }
 
 static struct mlxsw_sp_rif *
@@ -1598,27 +1598,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_ipip_entry *ipip_entry =
 		mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
-	enum mlxsw_sp_l3proto ul_proto;
-	union mlxsw_sp_l3addr saddr;
-	u32 ul_tb_id;
 
 	if (!ipip_entry)
 		return 0;
 
-	/* For flat configuration cases, moving overlay to a different VRF might
-	 * cause local address conflict, and the conflicting tunnels need to be
-	 * demoted.
-	 */
-	ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
-	ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto;
-	saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
-	if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto,
-						 saddr, ul_tb_id,
-						 ipip_entry)) {
-		mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
-		return 0;
-	}
-
 	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
 						   true, false, false, extack);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 899450b28621..7c03b661ae7e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -99,6 +99,7 @@ static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port,
 	devlink = priv_to_devlink(mlxsw_sp->core);
 	in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core,
 							   local_port);
+	skb_push(skb, ETH_HLEN);
 	devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port);
 	consume_skb(skb);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 57b26c2acf87..e8fe9a90fe4f 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -429,6 +429,10 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
 	int pulse_width = 0;
 	int perout_bit = 0;
 
+	/* Reject requests with unsupported flags */
+	if (perout->flags)
+		return -EOPNOTSUPP;
+
 	if (!on) {
 		lan743x_ptp_perout_off(adapter);
 		return 0;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 4d1bce4389c7..672ea1342add 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -261,8 +261,15 @@ static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
 		port->pvid = vid;
 
 	/* Untagged egress vlan clasification */
-	if (untagged)
+	if (untagged && port->vid != vid) {
+		if (port->vid) {
+			dev_err(ocelot->dev,
+				"Port already has a native VLAN: %d\n",
+				port->vid);
+			return -EBUSY;
+		}
 		port->vid = vid;
+	}
 
 	ocelot_vlan_port_apply(ocelot, port);
 
@@ -934,7 +941,7 @@ end:
 static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 				  u16 vid)
 {
-	return ocelot_vlan_vid_add(dev, vid, false, true);
+	return ocelot_vlan_vid_add(dev, vid, false, false);
 }
 
 static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
@@ -1673,9 +1680,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 	struct ocelot_port *ocelot_port = netdev_priv(dev);
 	int err = 0;
 
-	if (!ocelot_netdevice_dev_check(dev))
-		return 0;
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		if (netif_is_bridge_master(info->upper_dev)) {
@@ -1712,12 +1716,16 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (!ocelot_netdevice_dev_check(dev))
+		return 0;
+
 	if (event == NETDEV_PRECHANGEUPPER &&
 	    netif_is_lag_master(info->upper_dev)) {
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
 		struct netlink_ext_ack *extack;
 
-		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		if (lag_upper_info &&
+		    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
 			extack = netdev_notifier_info_to_extack(&info->info);
 			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
 
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index e40773c01a44..06ac806052bc 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -523,7 +523,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
 #define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri))
 #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0)
 
-void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 mask,
+void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 		     u32 offset);
 #define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
 #define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi))
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 1eef446036d6..79d72c88bbef 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -299,22 +299,6 @@ static void nfp_repr_clean(struct nfp_repr *repr)
 	nfp_port_free(repr->port);
 }
 
-static struct lock_class_key nfp_repr_netdev_xmit_lock_key;
-static struct lock_class_key nfp_repr_netdev_addr_lock_key;
-
-static void nfp_repr_set_lockdep_class_one(struct net_device *dev,
-					   struct netdev_queue *txq,
-					   void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &nfp_repr_netdev_xmit_lock_key);
-}
-
-static void nfp_repr_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &nfp_repr_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, nfp_repr_set_lockdep_class_one, NULL);
-}
-
 int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  u32 cmsg_port_id, struct nfp_port *port,
 		  struct net_device *pf_netdev)
@@ -324,8 +308,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	u32 repr_cap = nn->tlv_caps.repr_cap;
 	int err;
 
-	nfp_repr_set_lockdep_class(netdev);
-
 	repr->port = port;
 	repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL);
 	if (!repr->dst)
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 141571e2ec11..544012a67221 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1356,9 +1356,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	if (!is_valid_ether_addr(ndev->dev_addr))
 		eth_hw_addr_random(ndev);
 
-	/* Reset the ethernet controller */
-	__lpc_eth_reset(pldat);
-
 	/* then shut everything down to save power */
 	__lpc_eth_shutdown(pldat);
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 72107a0627a9..20faa8d24c9f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/printk.h>
+#include <linux/dynamic_debug.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 812190e729c2..6a95b42a8d8c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -182,6 +182,8 @@ struct ionic_lif {
 
 #define lif_to_txqcq(lif, i)	((lif)->txqcqs[i].qcq)
 #define lif_to_rxqcq(lif, i)	((lif)->rxqcqs[i].qcq)
+#define lif_to_txstats(lif, i)	((lif)->txqcqs[i].stats->tx)
+#define lif_to_rxstats(lif, i)	((lif)->rxqcqs[i].stats->rx)
 #define lif_to_txq(lif, i)	(&lif_to_txqcq((lif), i)->q)
 #define lif_to_rxq(lif, i)	(&lif_to_txqcq((lif), i)->q)
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 15e432386b35..aab311413412 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/printk.h>
+#include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/utsname.h>
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index e2907884f843..03916b6d47f2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -117,7 +117,8 @@ static u64 ionic_sw_stats_get_count(struct ionic_lif *lif)
 	/* rx stats */
 	total += MAX_Q(lif) * IONIC_NUM_RX_STATS;
 
-	if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+	if (test_bit(IONIC_LIF_UP, lif->state) &&
+	    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 		/* tx debug stats */
 		total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS +
 				      IONIC_NUM_TX_Q_STATS +
@@ -149,7 +150,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 			*buf += ETH_GSTRING_LEN;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 			for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) {
 				snprintf(*buf, ETH_GSTRING_LEN,
 					 "txq_%d_%s",
@@ -187,7 +189,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 			*buf += ETH_GSTRING_LEN;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 			for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) {
 				snprintf(*buf, ETH_GSTRING_LEN,
 					 "rxq_%d_cq_%s",
@@ -223,6 +226,8 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 {
 	struct ionic_lif_sw_stats lif_stats;
 	struct ionic_qcq *txqcq, *rxqcq;
+	struct ionic_tx_stats *txstats;
+	struct ionic_rx_stats *rxstats;
 	int i, q_num;
 
 	ionic_get_lif_stats(lif, &lif_stats);
@@ -233,15 +238,17 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 	}
 
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
-		txqcq = lif_to_txqcq(lif, q_num);
+		txstats = &lif_to_txstats(lif, q_num);
 
 		for (i = 0; i < IONIC_NUM_TX_STATS; i++) {
-			**buf = IONIC_READ_STAT64(&txqcq->stats->tx,
+			**buf = IONIC_READ_STAT64(txstats,
 						  &ionic_tx_stats_desc[i]);
 			(*buf)++;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+			txqcq = lif_to_txqcq(lif, q_num);
 			for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) {
 				**buf = IONIC_READ_STAT64(&txqcq->q,
 						      &ionic_txq_stats_desc[i]);
@@ -258,22 +265,24 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 				(*buf)++;
 			}
 			for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) {
-				**buf = txqcq->stats->tx.sg_cntr[i];
+				**buf = txstats->sg_cntr[i];
 				(*buf)++;
 			}
 		}
 	}
 
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
-		rxqcq = lif_to_rxqcq(lif, q_num);
+		rxstats = &lif_to_rxstats(lif, q_num);
 
 		for (i = 0; i < IONIC_NUM_RX_STATS; i++) {
-			**buf = IONIC_READ_STAT64(&rxqcq->stats->rx,
+			**buf = IONIC_READ_STAT64(rxstats,
 						  &ionic_rx_stats_desc[i]);
 			(*buf)++;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+			rxqcq = lif_to_rxqcq(lif, q_num);
 			for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) {
 				**buf = IONIC_READ_STAT64(&rxqcq->cq,
 						   &ionic_dbg_cq_stats_desc[i]);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 2ce70097d018..38f7f40b3a4d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -67,10 +67,9 @@
 #define QED_ROCE_QPS			(8192)
 #define QED_ROCE_DPIS			(8)
 #define QED_RDMA_SRQS                   QED_ROCE_QPS
-#define QED_NVM_CFG_SET_FLAGS		0xE
-#define QED_NVM_CFG_SET_PF_FLAGS	0x1E
 #define QED_NVM_CFG_GET_FLAGS		0xA
 #define QED_NVM_CFG_GET_PF_FLAGS	0x1A
+#define QED_NVM_CFG_MAX_ATTRS		50
 
 static char version[] =
 	"QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n";
@@ -2255,6 +2254,7 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	u8 entity_id, len, buf[32];
+	bool need_nvm_init = true;
 	struct qed_ptt *ptt;
 	u16 cfg_id, count;
 	int rc = 0, i;
@@ -2271,8 +2271,10 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 
 	DP_VERBOSE(cdev, NETIF_MSG_DRV,
 		   "Read config ids: num_attrs = %0d\n", count);
-	/* NVM CFG ID attributes */
-	for (i = 0; i < count; i++) {
+	/* NVM CFG ID attributes. Start loop index from 1 to avoid additional
+	 * arithmetic operations in the implementation.
+	 */
+	for (i = 1; i <= count; i++) {
 		cfg_id = *((u16 *)*data);
 		*data += 2;
 		entity_id = **data;
@@ -2282,8 +2284,21 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 		memcpy(buf, *data, len);
 		*data += len;
 
-		flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS :
-			QED_NVM_CFG_SET_FLAGS;
+		flags = 0;
+		if (need_nvm_init) {
+			flags |= QED_NVM_CFG_OPTION_INIT;
+			need_nvm_init = false;
+		}
+
+		/* Commit to flash and free the resources */
+		if (!(i % QED_NVM_CFG_MAX_ATTRS) || i == count) {
+			flags |= QED_NVM_CFG_OPTION_COMMIT |
+				 QED_NVM_CFG_OPTION_FREE;
+			need_nvm_init = true;
+		}
+
+		if (entity_id)
+			flags |= QED_NVM_CFG_OPTION_ENTITY_SEL;
 
 		DP_VERBOSE(cdev, NETIF_MSG_DRV,
 			   "cfg_id = %d entity = %d len = %d\n", cfg_id,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 78f77b712b10..dcb5c917f373 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -2005,7 +2005,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	    (qed_iov_validate_active_txq(p_hwfn, vf))) {
 		vf->b_malicious = true;
 		DP_NOTICE(p_hwfn,
-			  "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n",
+			  "VF [%02x] - considered malicious; Unable to stop RX/TX queues\n",
 			  vf->abs_vf_id);
 		status = PFVF_STATUS_MALICIOUS;
 		goto out;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8d1c208f778f..a220cc7c947a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1208,8 +1208,16 @@ enum qede_remove_mode {
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 {
 	struct net_device *ndev = pci_get_drvdata(pdev);
-	struct qede_dev *edev = netdev_priv(ndev);
-	struct qed_dev *cdev = edev->cdev;
+	struct qede_dev *edev;
+	struct qed_dev *cdev;
+
+	if (!ndev) {
+		dev_info(&pdev->dev, "Device has already been removed\n");
+		return;
+	}
+
+	edev = netdev_priv(ndev);
+	cdev = edev->cdev;
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 5ecf61df78bd..baac016f3ec0 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -363,7 +363,7 @@ qcaspi_receive(struct qcaspi *qca)
 	netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n",
 		   available);
 
-	if (available > QCASPI_HW_BUF_LEN) {
+	if (available > QCASPI_HW_BUF_LEN + QCASPI_HW_PKT_LEN) {
 		/* This could only happen by interferences on the SPI line.
 		 * So retry later ...
 		 */
@@ -496,7 +496,6 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event)
 	u16 signature = 0;
 	u16 spi_config;
 	u16 wrbuf_space = 0;
-	static u16 reset_count;
 
 	if (event == QCASPI_EVENT_CPUON) {
 		/* Read signature twice, if not valid
@@ -549,13 +548,13 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event)
 
 		qca->sync = QCASPI_SYNC_RESET;
 		qca->stats.trig_reset++;
-		reset_count = 0;
+		qca->reset_count = 0;
 		break;
 	case QCASPI_SYNC_RESET:
-		reset_count++;
+		qca->reset_count++;
 		netdev_dbg(qca->net_dev, "sync: waiting for CPU on, count %u.\n",
-			   reset_count);
-		if (reset_count >= QCASPI_RESET_TIMEOUT) {
+			   qca->reset_count);
+		if (qca->reset_count >= QCASPI_RESET_TIMEOUT) {
 			/* reset did not seem to take place, try again */
 			qca->sync = QCASPI_SYNC_UNKNOWN;
 			qca->stats.reset_timeout++;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index eb9af45fcc5e..d13a67e20d65 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -94,6 +94,7 @@ struct qcaspi {
 
 	unsigned int intr_req;
 	unsigned int intr_svc;
+	u16 reset_count;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *device_root;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 9c54b715228e..06de59521fc4 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -57,10 +57,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 	if (port->nr_rmnet_devs)
 		return -EINVAL;
 
-	kfree(port);
-
 	netdev_rx_handler_unregister(real_dev);
 
+	kfree(port);
+
 	/* release reference on real_dev */
 	dev_put(real_dev);
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 74f81fe03810..c33c438850cc 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
author	Ricardo B. Marliere <ricardo@marliere.net>	2024-03-02 13:47:24 -0300
committer	Martin K. Petersen <martin.petersen@oracle.com>	2024-03-10 18:15:48 -0400
commit	a08f0eb02981ebeccc6c62833e673cc06a29393b (patch)
tree	bc2148af4d4cea3f3ca8054e321f36a7cd08388c /scripts/patch-kernel
parent	ee8dda6a7e9d28260e30ecaf8b5f27d176c8ade0 (diff)