From 3347fa0928210d96aaa2bd6cd5a8391d5e630873 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 16 Sep 2016 15:49:32 -0400 Subject: workqueue: make workqueue available early during boot Workqueue is currently initialized in an early init call; however, there are cases where early boot code has to be split and reordered to come after workqueue initialization or the same code path which makes use of workqueues is used both before workqueue initailization and after. The latter cases have to gate workqueue usages with keventd_up() tests, which is nasty and easy to get wrong. Workqueue usages have become widespread and it'd be a lot more convenient if it can be used very early from boot. This patch splits workqueue initialization into two steps. workqueue_init_early() which sets up the basic data structures so that workqueues can be created and work items queued, and workqueue_init() which actually brings up workqueues online and starts executing queued work items. The former step can be done very early during boot once memory allocation, cpumasks and idr are initialized. The latter right after kthreads become available. This allows work item queueing and canceling from very early boot which is what most of these use cases want. * As systemd_wq being initialized doesn't indicate that workqueue is fully online anymore, update keventd_up() to test wq_online instead. The follow-up patches will get rid of all its usages and the function itself. * Flushing doesn't make sense before workqueue is fully initialized. The flush functions trigger WARN and return immediately before fully online. * Work items are never in-flight before fully online. Canceling can always succeed by skipping the flush step. * Some code paths can no longer assume to be called with irq enabled as irq is disabled during early boot. Use irqsave/restore operations instead. v2: Watchdog init, which requires timer to be running, moved from workqueue_init_early() to workqueue_init(). Signed-off-by: Tejun Heo Suggested-by: Linus Torvalds Link: http://lkml.kernel.org/r/CA+55aFx0vPuMuxn00rBSM192n-Du5uxy+4AvKa0SBSOVJeuCGg@mail.gmail.com --- include/linux/workqueue.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 26cc1df280d6..91d416f9c0a7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -358,6 +358,8 @@ extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; +extern bool wq_online; + extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6); @@ -594,7 +596,7 @@ static inline bool schedule_delayed_work(struct delayed_work *dwork, */ static inline bool keventd_up(void) { - return system_wq != NULL; + return wq_online; } #ifndef CONFIG_SMP @@ -631,4 +633,7 @@ int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif +int __init workqueue_init_early(void); +int __init workqueue_init(void); + #endif -- cgit From 863b710b664bdcb90c0c682ee24adb368f497a5b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 16 Sep 2016 15:49:34 -0400 Subject: workqueue: remove keventd_up() keventd_up() no longer has in-kernel users. Remove it and make wq_online static. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 91d416f9c0a7..56417133c672 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -358,8 +358,6 @@ extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; -extern bool wq_online; - extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6); @@ -591,14 +589,6 @@ static inline bool schedule_delayed_work(struct delayed_work *dwork, return queue_delayed_work(system_wq, dwork, delay); } -/** - * keventd_up - is workqueue initialized yet? - */ -static inline bool keventd_up(void) -{ - return wq_online; -} - #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { -- cgit From 43ece27e70b2c756e45306791955507f0533e248 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 23 Sep 2016 17:19:41 +0200 Subject: iio:trigger: Add helper function to verify that a trigger belongs to the same device Some triggers can only be attached to the IIO device that corresponds to the same physical device. Currently each driver that requires this implements its own trigger validation function. Introduce a new helper function called iio_trigger_validate_own_device() that can be used to do this check. Having a common implementation avoids code duplication and unnecessary boiler-plate code. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 4f1154f7a33c..ea08302f2d7b 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -170,6 +170,8 @@ void iio_trigger_free(struct iio_trigger *trig); */ bool iio_trigger_using_own(struct iio_dev *indio_dev); +int iio_trigger_validate_own_device(struct iio_trigger *trig, + struct iio_dev *indio_dev); #else struct iio_trigger; -- cgit From 0023e67dd8951737588b8af0469446df3ec52afe Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Fri, 23 Sep 2016 23:04:07 -0700 Subject: iio: inkern: add iio_read_channel_offset helper Allow access to underlying channel IIO_CHAN_INFO_OFFSET from a consumer. Signed-off-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 9edccfba1ffb..638157234357 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -235,6 +235,19 @@ int iio_write_channel_raw(struct iio_channel *chan, int val); int iio_get_channel_type(struct iio_channel *channel, enum iio_chan_type *type); +/** + * iio_read_channel_offset() - read the offset value for a channel + * @chan: The channel being queried. + * @val: First part of value read back. + * @val2: Second part of value read back. + * + * Note returns a description of what is in val and val2, such + * as IIO_VAL_INT_PLUS_MICRO telling us we have a value of val + * + val2/1e6 + */ +int iio_read_channel_offset(struct iio_channel *chan, int *val, + int *val2); + /** * iio_read_channel_scale() - read the scale value for a channel * @chan: The channel being queried. -- cgit From a9a0d64a8b7af406f03b660cbad948cfd34ed2b0 Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Sat, 1 Oct 2016 15:27:18 +0530 Subject: iio: Declare event_attrs field of iio_info structure as const The event_attrs field of iio_info structure is only initialized once whenever an object of iio_info is created. After that this field is never modified again anywhere in the kernel. So, declare event_attrs field of iio_info as a const struct attribute_group. Checked for occurences throughout the kernel using grep and coccinelle. Signed-off-by: Bhumika Goyal Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index b4a0679e4a49..4591d8ea41bd 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -381,7 +381,7 @@ struct iio_dev; **/ struct iio_info { struct module *driver_module; - struct attribute_group *event_attrs; + const struct attribute_group *event_attrs; const struct attribute_group *attrs; int (*read_raw)(struct iio_dev *indio_dev, -- cgit From f3b0deea89039373f0d22eafd1ff65a36e957266 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Mon, 26 Sep 2016 20:20:16 -0400 Subject: include: linux: iio: add IIO_ATTR_{RO, WO, RW} and IIO_DEVICE_ATTR_{RO, WO, RW} macros Add new macros: IIO_ATTR_RO, IIO_ATTR_WO, IIO_ATTR_RW, IIO_DEVICE_ATTR_RO, IIO_DEVICE_ATTR_WO and IIO_DEVICE_ATTR_RW to reduce the amount of boiler plate code that is needed for creating new attributes. This mimics the *_RO, *_WO, and *_RW macros that are found in include/linux/device.h and include/linux/sysfs.h. Signed-off-by: Brian Masney Acked-by: Greg Kroah-Hartman Signed-off-by: Jonathan Cameron --- include/linux/iio/sysfs.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/sysfs.h b/include/linux/iio/sysfs.h index 9cd8f747212f..ce9426c507fd 100644 --- a/include/linux/iio/sysfs.h +++ b/include/linux/iio/sysfs.h @@ -55,10 +55,34 @@ struct iio_const_attr { { .dev_attr = __ATTR(_name, _mode, _show, _store), \ .address = _addr } +#define IIO_ATTR_RO(_name, _addr) \ + { .dev_attr = __ATTR_RO(_name), \ + .address = _addr } + +#define IIO_ATTR_WO(_name, _addr) \ + { .dev_attr = __ATTR_WO(_name), \ + .address = _addr } + +#define IIO_ATTR_RW(_name, _addr) \ + { .dev_attr = __ATTR_RW(_name), \ + .address = _addr } + #define IIO_DEVICE_ATTR(_name, _mode, _show, _store, _addr) \ struct iio_dev_attr iio_dev_attr_##_name \ = IIO_ATTR(_name, _mode, _show, _store, _addr) +#define IIO_DEVICE_ATTR_RO(_name, _addr) \ + struct iio_dev_attr iio_dev_attr_##_name \ + = IIO_ATTR_RO(_name, _addr) + +#define IIO_DEVICE_ATTR_WO(_name, _addr) \ + struct iio_dev_attr iio_dev_attr_##_name \ + = IIO_ATTR_WO(_name, _addr) + +#define IIO_DEVICE_ATTR_RW(_name, _addr) \ + struct iio_dev_attr iio_dev_attr_##_name \ + = IIO_ATTR_RW(_name, _addr) + #define IIO_DEVICE_ATTR_NAMED(_vname, _name, _mode, _show, _store, _addr) \ struct iio_dev_attr iio_dev_attr_##_vname \ = IIO_ATTR(_name, _mode, _show, _store, _addr) -- cgit From 3d42de25d290fdfe604835d1b389845b8cba5bff Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 4 Oct 2016 20:34:35 -0400 Subject: x86/fpu, kvm: Remove KVM vcpu->fpu_counter With the removal of the lazy FPU code, this field is no longer used. Get rid of it. Signed-off-by: Rik van Riel Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Thomas Gleixner Cc: pbonzini@redhat.com Link: http://lkml.kernel.org/r/1475627678-20788-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9c28b4d4c90b..4e6905cd1e8e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -224,7 +224,6 @@ struct kvm_vcpu { int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; - unsigned char fpu_counter; struct swait_queue_head wq; struct pid *pid; int sigset_active; -- cgit From a13e831fcaa7e8af0387aef629d1835cf39c59f0 Mon Sep 17 00:00:00 2001 From: Eva Rachel Retuya Date: Wed, 5 Oct 2016 11:06:21 +0800 Subject: staging: iio: ad7192: implement IIO_CHAN_INFO_SAMP_FREQ This driver predates the availability of IIO_CHAN_INFO_SAMP_FREQ attribute wherein usage has some advantages like it can be accessed by in-kernel consumers as well as reduces the code size. Therefore, use IIO_CHAN_INFO_SAMP_FREQ to implement the sampling_frequency attribute instead of using IIO_DEV_ATTR_SAMP_FREQ() macro. Move code from the functions associated with IIO_DEV_ATTR_SAMP_FREQ() into respective read and write hooks with the mask set to IIO_CHAN_INFO_SAMP_FREQ. Signed-off-by: Eva Rachel Retuya Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index e7fdec4db9da..5ba430cc9a87 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -136,6 +136,7 @@ int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_OFFSET), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ + .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), \ .scan_index = (_si), \ .scan_type = { \ .sign = 'u', \ -- cgit From 4be0542073a33cc063b6a8f8fb367536e234e7aa Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 29 Aug 2016 08:08:29 +0100 Subject: dma-buf: Introduce fence_get_rcu_safe() This variant of fence_get_rcu() takes an RCU protected pointer to a fence and carefully returns a reference to the fence ensuring that it is not reallocated as it does. This is required when mixing fences and SLAB_DESTROY_BY_RCU - although it serves a more pedagogical function atm Signed-off-by: Chris Wilson Cc: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Reviewed-by: Daniel Vetter Signed-off-by: Sumit Semwal Link: http://patchwork.freedesktop.org/patch/msgid/20160829070834.22296-6-chris@chris-wilson.co.uk --- include/linux/fence.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index 0d763053f97a..c9c5ba98c302 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -182,6 +182,16 @@ void fence_init(struct fence *fence, const struct fence_ops *ops, void fence_release(struct kref *kref); void fence_free(struct fence *fence); +/** + * fence_put - decreases refcount of the fence + * @fence: [in] fence to reduce refcount of + */ +static inline void fence_put(struct fence *fence) +{ + if (fence) + kref_put(&fence->refcount, fence_release); +} + /** * fence_get - increases refcount of the fence * @fence: [in] fence to increase refcount of @@ -210,13 +220,49 @@ static inline struct fence *fence_get_rcu(struct fence *fence) } /** - * fence_put - decreases refcount of the fence - * @fence: [in] fence to reduce refcount of + * fence_get_rcu_safe - acquire a reference to an RCU tracked fence + * @fence: [in] pointer to fence to increase refcount of + * + * Function returns NULL if no refcount could be obtained, or the fence. + * This function handles acquiring a reference to a fence that may be + * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU), + * so long as the caller is using RCU on the pointer to the fence. + * + * An alternative mechanism is to employ a seqlock to protect a bunch of + * fences, such as used by struct reservation_object. When using a seqlock, + * the seqlock must be taken before and checked after a reference to the + * fence is acquired (as shown here). + * + * The caller is required to hold the RCU read lock. */ -static inline void fence_put(struct fence *fence) +static inline struct fence *fence_get_rcu_safe(struct fence * __rcu *fencep) { - if (fence) - kref_put(&fence->refcount, fence_release); + do { + struct fence *fence; + + fence = rcu_dereference(*fencep); + if (!fence || !fence_get_rcu(fence)) + return NULL; + + /* The atomic_inc_not_zero() inside fence_get_rcu() + * provides a full memory barrier upon success (such as now). + * This is paired with the write barrier from assigning + * to the __rcu protected fence pointer so that if that + * pointer still matches the current fence, we know we + * have successfully acquire a reference to it. If it no + * longer matches, we are holding a reference to some other + * reallocated pointer. This is possible if the allocator + * is using a freelist like SLAB_DESTROY_BY_RCU where the + * fence remains valid for the RCU grace period, but it + * may be reallocated. When using such allocators, we are + * responsible for ensuring the reference we get is to + * the right fence, as below. + */ + if (fence == rcu_access_pointer(*fencep)) + return rcu_pointer_handoff(fence); + + fence_put(fence); + } while (1); } int fence_signal(struct fence *fence); -- cgit From 61e84623ace35ce48975e8f90bbbac7557c43d61 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Fri, 7 Oct 2016 22:04:33 -0400 Subject: net: centralize net_device min/max MTU checking While looking into an MTU issue with sfc, I started noticing that almost every NIC driver with an ndo_change_mtu function implemented almost exactly the same range checks, and in many cases, that was the only practical thing their ndo_change_mtu function was doing. Quite a few drivers have either 68, 64, 60 or 46 as their minimum MTU value checked, and then various sizes from 1500 to 65535 for their maximum MTU value. We can remove a whole lot of redundant code here if we simple store min_mtu and max_mtu in net_device, and check against those in net/core/dev.c's dev_set_mtu(). In theory, there should be zero functional change with this patch, it just puts the infrastructure in place. Subsequent patches will attempt to start using said infrastructure, with theoretically zero change in functionality. CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 136ae6bbe81e..fbdf923af4d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1506,6 +1506,8 @@ enum netdev_priv_flags { * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value + * @min_mtu: Interface Minimum MTU value + * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. * @@ -1726,6 +1728,8 @@ struct net_device { unsigned char dma; unsigned int mtu; + unsigned int min_mtu; + unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; -- cgit From cf53b1da73bdf940f1523ec5a7d375d7056c759c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Tue, 11 Oct 2016 13:04:09 -0700 Subject: Revert "net: Add driver helper functions to determine checksum offloadability" This reverts commit 6ae23ad36253a8033c5714c52b691b84456487c5. The code has been in kernel since 4.4 but there are no in tree code that uses. Unused code is broken code, remove it. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 78 ----------------------------------------------- 1 file changed, 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fbdf923af4d3..bf341b65ca5e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2653,71 +2653,6 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } -struct skb_csum_offl_spec { - __u16 ipv4_okay:1, - ipv6_okay:1, - encap_okay:1, - ip_options_okay:1, - ext_hdrs_okay:1, - tcp_okay:1, - udp_okay:1, - sctp_okay:1, - vlan_okay:1, - no_encapped_ipv6:1, - no_not_encapped:1; -}; - -bool __skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help); - -static inline bool skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help) -{ - if (skb->ip_summed != CHECKSUM_PARTIAL) - return false; - - return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); -} - -static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec) -{ - bool csum_encapped; - - return skb_csum_offload_chk(skb, spec, &csum_encapped, true); -} - -static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) -{ - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .ipv6_okay = 1, - .vlan_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); -} - -static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) -{ - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - .vlan_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); -} - static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3961,19 +3896,6 @@ static inline bool can_checksum_protocol(netdev_features_t features, } } -/* Map an ethertype into IP protocol if possible */ -static inline int eproto_to_ipproto(int eproto) -{ - switch (eproto) { - case htons(ETH_P_IP): - return IPPROTO_IP; - case htons(ETH_P_IPV6): - return IPPROTO_IPV6; - default: - return -1; - } -} - #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev); #else -- cgit From c3aaa403840a5ccd305fb5e73f3cbfac6453b5e5 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 14 Oct 2016 05:19:17 -0400 Subject: qed: Pass MAC hints to VFs Some hypervisors can support MAC hints to their VFs. Even though we don't have such a hypervisor API in linux, we add sufficient logic for the VF to be able to receive such hints and set the mac accordingly - as long as the VF has not been set with a MAC already. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 33c24ebc9b7f..1c779486c30d 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -129,7 +129,7 @@ struct qed_tunn_params { struct qed_eth_cb_ops { struct qed_common_cb_ops common; - void (*force_mac) (void *dev, u8 *mac); + void (*force_mac) (void *dev, u8 *mac, bool forced); }; #ifdef CONFIG_DCB -- cgit From 7b7e70f979e34ed84d725eab8ea42921ab6f42e3 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 14 Oct 2016 05:19:20 -0400 Subject: qed*: Allow unicast filtering Apparently qede fails to set IFF_UNICAST_FLT, and as a result is not actually performing unicast MAC filtering. While we're at it - relax a hard-coded limitation that limits each interface into using at most 15 unicast MAC addresses before turning promiscuous. Instead utilize the HW resources to their limit. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 1c779486c30d..15130805d792 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -23,6 +23,7 @@ struct qed_dev_eth_info { u8 port_mac[ETH_ALEN]; u8 num_vlan_filters; + u16 num_mac_filters; /* Legacy VF - this affects the datapath, so qede has to know */ bool is_legacy; -- cgit From a6e78b3e1406575323b30b65890ee3c29930fb27 Mon Sep 17 00:00:00 2001 From: Shashank Sharma Date: Mon, 17 Oct 2016 17:34:39 +0530 Subject: video: Add new aspect ratios for HDMI 2.0 HDMI 2.0/CEA-861-F introduces two new aspect ratios: - 64:27 - 256:135 This patch adds enumeration for the new aspect ratios in the existing aspect ratio list. V2: rebase V3: rebase V4: Added r-b from Jose, Ack by Tomi Signed-off-by: Shashank Sharma Reviewed-by: Sean Paul Reviewed-by: Jose Abreu Acked-by: Tomi Valkeinen Cc: Daniel Vetter Cc: Emil Velikov Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1476705880-15600-4-git-send-email-shashank.sharma@intel.com --- include/linux/hdmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index e9744202fa29..edbb4fc674ed 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -78,6 +78,8 @@ enum hdmi_picture_aspect { HDMI_PICTURE_ASPECT_NONE, HDMI_PICTURE_ASPECT_4_3, HDMI_PICTURE_ASPECT_16_9, + HDMI_PICTURE_ASPECT_64_27, + HDMI_PICTURE_ASPECT_256_135, HDMI_PICTURE_ASPECT_RESERVED, }; -- cgit From 664fcf123a30edf16b47d2ce1f610d654ba917b2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 16 Oct 2016 19:56:51 +0200 Subject: net: phy: Threaded interrupts allow some simplification The PHY interrupts are now handled in a threaded interrupt handler, which can sleep. The work queue is no longer needed, phy_change() can be called directly. phy_mac_interrupt() still needs to be safe to call in interrupt context, so keep the work queue, and use a helper to call phy_change(). Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e25f1830fbcf..c47378c93607 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -343,7 +343,7 @@ struct phy_c45_device_ids { * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine - * phy_queue: A work_queue for the interrupt + * phy_queue: A work_queue for the phy_mac_interrupt * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -802,7 +802,8 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); -void phy_change(struct work_struct *work); +void phy_change(struct phy_device *phydev); +void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -- cgit From bb6869b2147817385e0261f928b942f466f74a63 Mon Sep 17 00:00:00 2001 From: Peter Griffin Date: Tue, 18 Oct 2016 10:39:06 +0100 Subject: remoteproc: st_slim_rproc: add a slimcore rproc driver slim core is used as a basis for many IPs in the STi chipsets such as fdma and demux. To avoid duplicating the elf loading code in each device driver a slim rproc driver has been created. This driver is designed to be used by other device drivers such as fdma, or demux whose IP is based around a slim core. The device driver can call slim_rproc_alloc() to allocate a slim rproc and slim_rproc_put() when finished. This driver takes care of ioremapping the slim registers (dmem, imem, slimcore, peripherals), whose offsets and sizes can change between IP's. It also obtains and enables any clocks used by the device. This approach avoids having a double mapping of the registers as slim_rproc does not register its own platform device. It also maps well to device tree abstraction as it allows us to have one dt node for the whole device. All of the generic rproc elf loading code can be reused, and we provide start() stop() hooks to start and stop the slim core once the firmware has been loaded. This has been tested successfully with fdma driver. Signed-off-by: Peter Griffin Signed-off-by: Vinod Koul --- include/linux/remoteproc/st_slim_rproc.h | 58 ++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) create mode 100644 include/linux/remoteproc/st_slim_rproc.h (limited to 'include/linux') diff --git a/include/linux/remoteproc/st_slim_rproc.h b/include/linux/remoteproc/st_slim_rproc.h new file mode 100644 index 000000000000..4155556fa4b2 --- /dev/null +++ b/include/linux/remoteproc/st_slim_rproc.h @@ -0,0 +1,58 @@ +/* + * SLIM core rproc driver header + * + * Copyright (C) 2016 STMicroelectronics + * + * Author: Peter Griffin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _ST_REMOTEPROC_SLIM_H +#define _ST_REMOTEPROC_SLIM_H + +#define ST_SLIM_MEM_MAX 2 +#define ST_SLIM_MAX_CLK 4 + +enum { + ST_SLIM_DMEM, + ST_SLIM_IMEM, +}; + +/** + * struct st_slim_mem - slim internal memory structure + * @cpu_addr: MPU virtual address of the memory region + * @bus_addr: Bus address used to access the memory region + * @size: Size of the memory region + */ +struct st_slim_mem { + void __iomem *cpu_addr; + phys_addr_t bus_addr; + size_t size; +}; + +/** + * struct st_slim_rproc - SLIM slim core + * @rproc: rproc handle + * @mem: slim memory information + * @slimcore: slim slimcore regs + * @peri: slim peripheral regs + * @clks: slim clocks + */ +struct st_slim_rproc { + struct rproc *rproc; + struct st_slim_mem mem[ST_SLIM_MEM_MAX]; + void __iomem *slimcore; + void __iomem *peri; + + /* st_slim_rproc private */ + struct clk *clks[ST_SLIM_MAX_CLK]; +}; + +struct st_slim_rproc *st_slim_rproc_alloc(struct platform_device *pdev, + char *fw_name); +void st_slim_rproc_put(struct st_slim_rproc *slim_rproc); + +#endif -- cgit From 1a3f060c1a47dba4e12ac21ce62b57666b9c4e95 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 17 Oct 2016 19:15:44 -0700 Subject: net: Introduce new api for walking upper and lower devices This patch introduces netdev_walk_all_upper_dev_rcu, netdev_walk_all_lower_dev and netdev_walk_all_lower_dev_rcu. These functions recursively walk the adj_list of devices to determine all upper and lower devices. The functions take a callback function that is invoked for each device in the list. If the callback returns non-0, the walk is terminated and the functions return that code back to callers. v3 - simplified netdev_has_upper_dev_all_rcu and __netdev_has_upper_dev and removed typecast as suggested by Stephen v2 - fixed definition of netdev_next_lower_dev_rcu to mirror the upper_dev version. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf341b65ca5e..a5902d995907 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3778,6 +3778,14 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, updev; \ updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) +int netdev_walk_all_upper_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *upper_dev, + void *data), + void *data); + +bool netdev_has_upper_dev_all_rcu(struct net_device *dev, + struct net_device *upper_dev); + void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, @@ -3821,6 +3829,15 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, ldev; \ ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) +int netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); + void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); -- cgit From f1170fd462c67c4ae2f20734566d94e0f8f62f69 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 17 Oct 2016 19:15:51 -0700 Subject: net: Remove all_adj_list and its references Only direct adjacencies are maintained. All upper or lower devices can be learned via the new walk API which recursively walks the adj_list for upper devices or lower devices. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a5902d995907..458c87631e7f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1456,7 +1456,6 @@ enum netdev_priv_flags { * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding - * @all_adj_list: All linked devices, *including* neighbours * @features: Currently active device features * @hw_features: User-changeable features * @@ -1675,11 +1674,6 @@ struct net_device { struct list_head lower; } adj_list; - struct { - struct list_head upper; - struct list_head lower; - } all_adj_list; - netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -3771,13 +3765,6 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) -/* iterate through upper list, must be called under RCU read lock */ -#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ - for (iter = &(dev)->all_adj_list.upper, \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \ - updev; \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) - int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, void *data), @@ -3817,18 +3804,6 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, struct list_head **iter); -#define netdev_for_each_all_lower_dev(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ - ldev = netdev_all_lower_get_next(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next(dev, &(iter))) - -#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), -- cgit From 1f9127caece42514a47011326b83ad93d95cd5d7 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 17 Oct 2016 10:49:54 -0500 Subject: net: phy: Create phy_supported_speeds function which lists speeds currently supported by a phydevice phy_supported_speeds provides a means to get a list of all the speeds a phy device currently supports. Signed-off-by: Zach Brown Signed-off-by: David S. Miller --- include/linux/phy.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index c47378c93607..4b6c246c63bb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -84,6 +84,21 @@ typedef enum { PHY_INTERFACE_MODE_MAX, } phy_interface_t; +/** + * phy_supported_speeds - return all speeds currently supported by a phy device + * @phy: The phy device to return supported speeds of. + * @speeds: buffer to store supported speeds in. + * @size: size of speeds buffer. + * + * Description: Returns the number of supported speeds, and + * fills the speeds * buffer with the supported speeds. If speeds buffer is + * too small to contain * all currently supported speeds, will return as + * many speeds as can fit. + */ +unsigned int phy_supported_speeds(struct phy_device *phy, + unsigned int *speeds, + unsigned int size); + /** * It maps 'enum phy_interface_t' found in include/linux/phy.h * into the device tree binding of 'phy-mode', so that Ethernet -- cgit From 2e0bc452f4721520502575362a9cd3c1248d2337 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 17 Oct 2016 10:49:55 -0500 Subject: net: phy: leds: add support for led triggers on phy link state change Create an option CONFIG_LED_TRIGGER_PHY (default n), which will create a set of led triggers for each instantiated PHY device. There is one LED trigger per link-speed, per-phy. The triggers are registered during phy_attach and unregistered during phy_detach. This allows for a user to configure their system to allow a set of LEDs not controlled by the phy to represent link state changes on the phy. LEDS controlled by the phy are unaffected. For example, we have a board where some of the leds in the RJ45 socket are controlled by the phy, but others are not. Using the triggers provided by this patch the leds not controlled by the phy can be configured to show the current speed of the ethernet connection. The leds controlled by the phy are unaffected. Signed-off-by: Josh Cartwright Signed-off-by: Nathan Sullivan Signed-off-by: Zach Brown Signed-off-by: David S. Miller --- include/linux/phy.h | 7 ++++++ include/linux/phy_led_triggers.h | 51 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 include/linux/phy_led_triggers.h (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4b6c246c63bb..e7e1fd382564 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -420,6 +421,12 @@ struct phy_device { int link_timeout; +#ifdef CONFIG_LED_TRIGGER_PHY + struct phy_led_trigger *phy_led_triggers; + unsigned int phy_num_led_triggers; + struct phy_led_trigger *last_triggered; +#endif + /* * Interrupt number for this PHY * -1 means no interrupt diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h new file mode 100644 index 000000000000..a2daea0a37d2 --- /dev/null +++ b/include/linux/phy_led_triggers.h @@ -0,0 +1,51 @@ +/* Copyright (C) 2016 National Instruments Corp. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef __PHY_LED_TRIGGERS +#define __PHY_LED_TRIGGERS + +struct phy_device; + +#ifdef CONFIG_LED_TRIGGER_PHY + +#include + +#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 +#define PHY_MII_BUS_ID_SIZE (20 - 3) + +#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \ + FIELD_SIZEOF(struct mdio_device, addr)+\ + PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) + +struct phy_led_trigger { + struct led_trigger trigger; + char name[PHY_LINK_LED_TRIGGER_NAME_SIZE]; + unsigned int speed; +}; + + +extern int phy_led_triggers_register(struct phy_device *phy); +extern void phy_led_triggers_unregister(struct phy_device *phy); +extern void phy_led_trigger_change_speed(struct phy_device *phy); + +#else + +static inline int phy_led_triggers_register(struct phy_device *phy) +{ + return 0; +} +static inline void phy_led_triggers_unregister(struct phy_device *phy) { } +static inline void phy_led_trigger_change_speed(struct phy_device *phy) { } + +#endif + +#endif -- cgit From 797476b88bde2a6001f9552f383f147e58c1a330 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 18 Oct 2016 15:40:29 +0900 Subject: block: Add 'zoned' queue limit Add the zoned queue limit to indicate the zoning model of a block device. Defined values are 0 (BLK_ZONED_NONE) for regular block devices, 1 (BLK_ZONED_HA) for host-aware zone block devices and 2 (BLK_ZONED_HM) for host-managed zone block devices. The standards defined drive managed model is not defined here since these block devices do not provide any command for accessing zone information. Drive managed model devices will be reported as BLK_ZONED_NONE. The helper functions blk_queue_zoned_model and bdev_zoned_model return the zoned limit and the functions blk_queue_is_zoned and bdev_is_zoned return a boolean for callers to test if a block device is zoned. The zoned attribute is also exported as a string to applications via sysfs. BLK_ZONED_NONE shows as "none", BLK_ZONED_HA as "host-aware" and BLK_ZONED_HM as "host-managed". Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c47c358ba052..f19e16bb43d1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -261,6 +261,15 @@ struct blk_queue_tag { #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) +/* + * Zoned block device models (zoned limit). + */ +enum blk_zoned_model { + BLK_ZONED_NONE, /* Regular block device */ + BLK_ZONED_HA, /* Host-aware zoned block device */ + BLK_ZONED_HM, /* Host-managed zoned block device */ +}; + struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; @@ -290,6 +299,7 @@ struct queue_limits { unsigned char cluster; unsigned char discard_zeroes_data; unsigned char raid_partial_stripes_expensive; + enum blk_zoned_model zoned; }; struct request_queue { @@ -627,6 +637,23 @@ static inline unsigned int blk_queue_cluster(struct request_queue *q) return q->limits.cluster; } +static inline enum blk_zoned_model +blk_queue_zoned_model(struct request_queue *q) +{ + return q->limits.zoned; +} + +static inline bool blk_queue_is_zoned(struct request_queue *q) +{ + switch (blk_queue_zoned_model(q)) { + case BLK_ZONED_HA: + case BLK_ZONED_HM: + return true; + default: + return false; + } +} + /* * We regard a request as sync, if either a read or a sync write */ @@ -1354,6 +1381,26 @@ static inline unsigned int bdev_write_same(struct block_device *bdev) return 0; } +static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return blk_queue_zoned_model(q); + + return BLK_ZONED_NONE; +} + +static inline bool bdev_is_zoned(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return blk_queue_is_zoned(q); + + return false; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit From 2d253440b5afb128d22ccdae812dde9ba77a2cca Mon Sep 17 00:00:00 2001 From: Shaun Tancheff Date: Tue, 18 Oct 2016 15:40:32 +0900 Subject: block: Define zoned block device operations Define REQ_OP_ZONE_REPORT and REQ_OP_ZONE_RESET for handling zones of host-managed and host-aware zoned block devices. With with these two new operations, the total number of operations defined reaches 8 and still fits with the 3 bits definition of REQ_OP_BITS. Signed-off-by: Shaun Tancheff Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cd395ecec99d..dd50dce89a80 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -243,6 +243,8 @@ enum req_op { REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ REQ_OP_WRITE_SAME, /* write same block many times */ REQ_OP_FLUSH, /* request for cache flush */ + REQ_OP_ZONE_REPORT, /* Get zone information */ + REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ }; #define REQ_OP_BITS 3 -- cgit From 6a0cb1bc106fc07ce0443303bcdb7f7da5131e5c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 18 Oct 2016 15:40:33 +0900 Subject: block: Implement support for zoned block devices Implement zoned block device zone information reporting and reset. Zone information are reported as struct blk_zone. This implementation does not differentiate between host-aware and host-managed device models and is valid for both. Two functions are provided: blkdev_report_zones for discovering the zone configuration of a zoned block device, and blkdev_reset_zones for resetting the write pointer of sequential zones. The helper function blk_queue_zone_size and bdev_zone_size are also provided for, as the name suggest, obtaining the zone size (in 512B sectors) of the zones of the device. Signed-off-by: Hannes Reinecke [Damien: * Removed the zone cache * Implement report zones operation based on earlier proposal by Shaun Tancheff ] Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f19e16bb43d1..252043f7cd2c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -302,6 +303,21 @@ struct queue_limits { enum blk_zoned_model zoned; }; +#ifdef CONFIG_BLK_DEV_ZONED + +struct blk_zone_report_hdr { + unsigned int nr_zones; + u8 padding[60]; +}; + +extern int blkdev_report_zones(struct block_device *bdev, + sector_t sector, struct blk_zone *zones, + unsigned int *nr_zones, gfp_t gfp_mask); +extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, + sector_t nr_sectors, gfp_t gfp_mask); + +#endif /* CONFIG_BLK_DEV_ZONED */ + struct request_queue { /* * Together with queue_head for cacheline sharing @@ -654,6 +670,11 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } +static inline unsigned int blk_queue_zone_size(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; +} + /* * We regard a request as sync, if either a read or a sync write */ @@ -1401,6 +1422,16 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } +static inline unsigned int bdev_zone_size(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return blk_queue_zone_size(q); + + return 0; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit From 3ed05a987e0f63b21e634101e0b460d32f3581c3 Mon Sep 17 00:00:00 2001 From: Shaun Tancheff Date: Tue, 18 Oct 2016 15:40:35 +0900 Subject: blk-zoned: implement ioctls Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for respectively obtaining the zone configuration of a zoned block device and resetting the write pointer of sequential zones of a zoned block device. The BLKREPORTZONE ioctl maps directly to a single call of the function blkdev_report_zones. The zone information result is passed as an array of struct blk_zone identical to the structure used internally for processing the REQ_OP_ZONE_REPORT operation. The BLKRESETZONE ioctl maps to a single call of the blkdev_reset_zones function. Signed-off-by: Shaun Tancheff Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 252043f7cd2c..90097dd8b8ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -316,6 +316,27 @@ extern int blkdev_report_zones(struct block_device *bdev, extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); +extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); + +#else /* CONFIG_BLK_DEV_ZONED */ + +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + +static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { -- cgit From 9a97434215819872b054c3d0c067e5e4fa768b0e Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Mon, 17 Oct 2016 21:45:29 +0200 Subject: ARM: pxa: enhance smc91x platform data Instead of having the smc91x driver relying on machine_is_*() calls, provide this data through platform data, ie. idp, mainstone and stargate. This way, the driver doesn't need anymore machine_is_*() calls, which wouldn't work anymore with a device-tree build. Signed-off-by: Robert Jarzmik Signed-off-by: David S. Miller --- include/linux/smc91x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index e302c447e057..129bc674dcf5 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -39,6 +39,7 @@ struct smc91x_platdata { unsigned long flags; unsigned char leda; unsigned char ledb; + bool pxa_u16_align4; /* PXA buggy u16 writes on 4*n+2 addresses */ }; #endif /* __SMC91X_H__ */ -- cgit From 0f57dc6ae1ff0c702450083176b657ba37c07363 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 17 Oct 2016 16:48:58 +0100 Subject: remoteproc: Keep local copy of firmware name Storage of the firmware name was inconsistent, either storing a pointer to a name stored with unknown ownership, or a variable length tacked onto the end of the struct proc allocated in rproc_alloc. In preparation for allowing the firmware of an already allocated struct rproc to be changed, instead always keep a locally maintained copy of the firmware name. Signed-off-by: Matt Redfearn Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 930023b7c825..940e4cf2ac48 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -415,7 +415,7 @@ struct rproc { struct list_head node; struct iommu_domain *domain; const char *name; - const char *firmware; + char *firmware; void *priv; const struct rproc_ops *ops; struct device dev; -- cgit From 57a09bf0a416700676e77102c28f9cfcb48267e0 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 18 Oct 2016 19:51:19 +0200 Subject: bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers A BPF program is required to check the return register of a map_elem_lookup() call before accessing memory. The verifier keeps track of this by converting the type of the result register from PTR_TO_MAP_VALUE_OR_NULL to PTR_TO_MAP_VALUE after a conditional jump ensures safety. This check is currently exclusively performed for the result register 0. In the event the compiler reorders instructions, BPF_MOV64_REG instructions may be moved before the conditional jump which causes them to keep their type PTR_TO_MAP_VALUE_OR_NULL to which the verifier objects when the register is accessed: 0: (b7) r1 = 10 1: (7b) *(u64 *)(r10 -8) = r1 2: (bf) r2 = r10 3: (07) r2 += -8 4: (18) r1 = 0x59c00000 6: (85) call 1 7: (bf) r4 = r0 8: (15) if r0 == 0x0 goto pc+1 R0=map_value(ks=8,vs=8) R4=map_value_or_null(ks=8,vs=8) R10=fp 9: (7a) *(u64 *)(r4 +0) = 0 R4 invalid mem access 'map_value_or_null' This commit extends the verifier to keep track of all identical PTR_TO_MAP_VALUE_OR_NULL registers after a map_elem_lookup() by assigning them an ID and then marking them all when the conditional jump is observed. Signed-off-by: Thomas Graf Reviewed-by: Josef Bacik Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7035b997aaa5..ac5b393ee6b2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -23,13 +23,13 @@ struct bpf_reg_state { * result in a bad access. */ u64 min_value, max_value; + u32 id; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; /* valid when type == PTR_TO_PACKET* */ struct { - u32 id; u16 off; u16 range; }; -- cgit From 3ca45a46f8af8c4a92dd8a08eac57787242d5021 Mon Sep 17 00:00:00 2001 From: zijun_hu Date: Fri, 14 Oct 2016 15:12:54 +0800 Subject: percpu: ensure the requested alignment is power of two The percpu allocator expectedly assumes that the requested alignment is power of two but hasn't been veryfing the input. If the specified alignment isn't power of two, the allocator can malfunction. Add the sanity check. The following is detailed analysis of the effects of alignments which aren't power of two. The alignment must be a even at least since the LSB of a chunk->map element is used as free/in-use flag of a area; besides, the alignment must be a power of 2 too since ALIGN() doesn't work well for other alignment always but is adopted by pcpu_fit_in_area(). IOW, the current allocator only works well for a power of 2 aligned area allocation. See below opposite example for why an odd alignment doesn't work. Let's assume area [16, 36) is free but its previous one is in-use, we want to allocate a @size == 8 and @align == 7 area. The larger area [16, 36) is split to three areas [16, 21), [21, 29), [29, 36) eventually. However, due to the usage for a chunk->map element, the actual offset of the aim area [21, 29) is 21 but is recorded in relevant element as 20; moreover, the residual tail free area [29, 36) is mistook as in-use and is lost silently Unlike macro roundup(), ALIGN(x, a) doesn't work if @a isn't a power of 2 for example, roundup(10, 6) == 12 but ALIGN(10, 6) == 10, and the latter result isn't desired obviously. tj: Code style and patch description updates. Signed-off-by: zijun_hu Suggested-by: Tejun Heo Signed-off-by: Tejun Heo --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc6ed52a39b9..0dc0b21bd164 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -45,6 +45,7 @@ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) +/* @a is a power of 2 value */ #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) #define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) -- cgit From 5dc8b362a2374d007bc0db649b7ab6a79dd32bda Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Mon, 17 Oct 2016 11:27:28 -0700 Subject: block: Add iocontext priority to request Patch adds an association between iocontext ioprio and the ioprio of a request. This is done to enable request based drivers the ability to act on priority information stored in the request. An example being ATA devices that support command priorities. If the ATA driver discovers that the device supports command priorities and the request has valid priority information indicating the request is high priority, then a high priority command can be sent to the device. This should improve tail latencies for high priority IO on any device that queues requests internally and can make use of the priority information stored in the request. The ioprio of the request is set in blk_rq_set_prio which takes the request and the ioc as arguments. If the ioc is valid in blk_rq_set_prio then the iopriority of the request is set as the iopriority of the ioc. In init_request_from_bio a check is made to see if the ioprio of the bio is valid and if so then the request prio comes from the bio. Signed-off-by: Adam Manzananares Reviewed-by: Jens Axboe Signed-off-by: Tejun Heo --- include/linux/blkdev.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c47c358ba052..9a0ceaa1b7e6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -933,6 +933,20 @@ static inline unsigned int blk_rq_count_bios(struct request *rq) return nr_bios; } +/* + * blk_rq_set_prio - associate a request with prio from ioc + * @rq: request of interest + * @ioc: target iocontext + * + * Assocate request prio with ioc prio so request based drivers + * can leverage priority information. + */ +static inline void blk_rq_set_prio(struct request *rq, struct io_context *ioc) +{ + if (ioc) + rq->ioprio = ioc->ioprio; +} + /* * Request issue related functions. */ -- cgit From 8e061784b51ec4a4efed0deaafb5bd9725bf5b06 Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Mon, 17 Oct 2016 11:27:29 -0700 Subject: ata: Enabling ATA Command Priorities This patch checks to see if an ATA device supports NCQ command priorities. If so and the user has specified an iocontext that indicates IO_PRIO_CLASS_RT then we build a tf with a high priority command. This is done to improve the tail latency of commands that are high priority by passing priority to the device. tj: Removed trivial ata_ncq_prio_enabled() and open-coded the test. Signed-off-by: Adam Manzanares Signed-off-by: Tejun Heo --- include/linux/ata.h | 6 ++++++ include/linux/libata.h | 3 +++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index fdb180367ba1..af6859b3a93d 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -348,6 +348,7 @@ enum { ATA_LOG_DEVSLP_DETO = 0x01, ATA_LOG_DEVSLP_VALID = 0x07, ATA_LOG_DEVSLP_VALID_MASK = 0x80, + ATA_LOG_NCQ_PRIO_OFFSET = 0x09, /* NCQ send and receive log */ ATA_LOG_NCQ_SEND_RECV_SUBCMDS_OFFSET = 0x00, @@ -940,6 +941,11 @@ static inline bool ata_id_has_ncq_non_data(const u16 *id) return id[ATA_ID_SATA_CAPABILITY_2] & BIT(5); } +static inline bool ata_id_has_ncq_prio(const u16 *id) +{ + return id[ATA_ID_SATA_CAPABILITY] & BIT(12); +} + static inline bool ata_id_has_trim(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/libata.h b/include/linux/libata.h index 616eef4d81ea..90b69a6293a3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -166,6 +166,7 @@ enum { ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ + ATA_DFLAG_NCQ_PRIO = (1 << 20), /* device supports NCQ priority */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -342,7 +343,9 @@ enum { ATA_SHIFT_PIO = 0, ATA_SHIFT_MWDMA = ATA_SHIFT_PIO + ATA_NR_PIO_MODES, ATA_SHIFT_UDMA = ATA_SHIFT_MWDMA + ATA_NR_MWDMA_MODES, + ATA_SHIFT_PRIO = 6, + ATA_PRIO_HIGH = 2, /* size of buffer to pad xfers ending on unaligned boundaries */ ATA_DMA_PAD_SZ = 4, -- cgit From 84f95243b5439a20c33837075b88926bfa00c4ec Mon Sep 17 00:00:00 2001 From: Adam Manzanares Date: Mon, 17 Oct 2016 11:27:30 -0700 Subject: ata: ATA Command Priority Disabled By Default Add a sysfs entry to turn on priority information being passed to a ATA device. By default this feature is turned off. This patch depends on ata: Enabling ATA Command Priorities tj: Renamed ncq_prio_on to ncq_prio_enable and removed trivial ata_ncq_prio_on() and open-coded the test. Signed-off-by: Adam Manzanares Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 90b69a6293a3..c170be548b7f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -167,6 +167,7 @@ enum { ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_NCQ_PRIO = (1 << 20), /* device supports NCQ priority */ + ATA_DFLAG_NCQ_PRIO_ENABLE = (1 << 21), /* Priority cmds sent to dev */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -545,6 +546,7 @@ typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes) extern struct device_attribute dev_attr_link_power_management_policy; extern struct device_attribute dev_attr_unload_heads; +extern struct device_attribute dev_attr_ncq_prio_enable; extern struct device_attribute dev_attr_em_message_type; extern struct device_attribute dev_attr_em_message; extern struct device_attribute dev_attr_sw_activity; -- cgit From 3c3fcb45d524feb5d14a14f332e3eec7f2aff8f3 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Wed, 19 Oct 2016 15:10:59 +0100 Subject: sched/fair: Kill the unused 'sched_shares_window_ns' tunable The last user of this tunable was removed in 2012 in commit: 82958366cfea ("sched: Replace update_shares weight distribution with per-entity computation") Delete it since its very existence confuses people. Signed-off-by: Matt Fleming Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul Turner Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161019141059.26408-1-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/sched/sysctl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 22db1e63707e..441145351301 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -36,7 +36,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; -extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, -- cgit From 50066a042da5457ae5b6397425f0a7ca556231e3 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Wed, 19 Oct 2016 18:03:42 -0700 Subject: HID: wacom: generic: Add support for height, tilt, and twist usages The HID standard defines usages that allow digitizers to report the pen's height, tilt, and rotation and which are used by Wacom's new "MobileStudio Pro" devices. Note that 'hidinput_calc_abs_res' expects ABS_Z (historically used by our driver to report twist) to have linear units. To ensure it calculates a resolution with the actually-angular units provided in the HID descriptor we nedd to lie and tell it we're calculating it for the (rotational) ABS_RZ axis instead. Signed-off-by: Jason Gerecke Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b2ec82712baa..e712101a1670 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -232,6 +232,9 @@ struct hid_item { #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a #define HID_DG_INVERT 0x000d003c +#define HID_DG_TILT_X 0x000d003d +#define HID_DG_TILT_Y 0x000d003e +#define HID_DG_TWIST 0x000d0041 #define HID_DG_TIPSWITCH 0x000d0042 #define HID_DG_TIPSWITCH2 0x000d0043 #define HID_DG_BARRELSWITCH 0x000d0044 -- cgit From 93aab7fa4f8091d8fe2aed7e79a650fc1c084512 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Wed, 19 Oct 2016 18:03:52 -0700 Subject: HID: wacom: generic: Add support for battery status on pen and pad interfaces Adds support for usages that may appear on the pen or pad interface which report the state of the tablet battery. Signed-off-by: Jason Gerecke Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e712101a1670..3baa2f962e48 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -231,6 +231,7 @@ struct hid_item { #define HID_DG_TAP 0x000d0035 #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a +#define HID_DG_BATTERYSTRENGTH 0x000d003b #define HID_DG_INVERT 0x000d003c #define HID_DG_TILT_X 0x000d003d #define HID_DG_TILT_Y 0x000d003e -- cgit From 8b6b4135e4fb2b537f33b811c13f77bee25ca8d3 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 20 Oct 2016 13:55:19 -0400 Subject: net: use core MTU range checking in WAN drivers - set min/max_mtu in all hdlc drivers, remove hdlc_change_mtu - sent max_mtu in lec driver, remove lec_change_mtu - set min/max_mtu in x25_asy driver CC: netdev@vger.kernel.org CC: Krzysztof Halasa CC: Krzysztof Halasa CC: Jan "Yenya" Kasprzak CC: Francois Romieu CC: Kevin Curtis CC: Zhao Qiang Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/hdlc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index e31bcd4c7859..97585d9679f3 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -93,8 +93,6 @@ static __inline__ void debug_frame(const struct sk_buff *skb) int hdlc_open(struct net_device *dev); /* Must be called by hardware driver when HDLC device is being closed */ void hdlc_close(struct net_device *dev); -/* May be used by hardware driver */ -int hdlc_change_mtu(struct net_device *dev, int new_mtu); /* Must be pointed to by hw driver's dev->netdev_ops->ndo_start_xmit */ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev); -- cgit From b3e3893e1253692c3d2b8e8ebd5a26183ed30443 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 20 Oct 2016 13:55:22 -0400 Subject: net: use core MTU range checking in misc drivers firewire-net: - set min/max_mtu - remove fwnet_change_mtu nes: - set max_mtu - clean up nes_netdev_change_mtu xpnet: - set min/max_mtu - remove xpnet_dev_change_mtu hippi: - set min/max_mtu - remove hippi_change_mtu batman-adv: - set max_mtu - remove batadv_interface_change_mtu - initialization is a little async, not 100% certain that max_mtu is set in the optimal place, don't have hardware to test with rionet: - set min/max_mtu - remove rionet_change_mtu slip: - set min/max_mtu - streamline sl_change_mtu um/net_kern: - remove pointless ndo_change_mtu hsi/clients/ssi_protocol: - use core MTU range checking - remove now redundant ssip_pn_set_mtu ipoib: - set a default max MTU value - Note: ipoib's actual max MTU can vary, depending on if the device is in connected mode or not, so we'll just set the max_mtu value to the max possible, and let the ndo_change_mtu function continue to validate any new MTU change requests with checks for CM or not. Note that ipoib has no min_mtu set, and thus, the network core's mtu > 0 check is the only lower bounds here. mptlan: - use net core MTU range checking - remove now redundant mpt_lan_change_mtu fddi: - min_mtu = 21, max_mtu = 4470 - remove now redundant fddi_change_mtu (including export) fjes: - min_mtu = 8192, max_mtu = 65536 - The max_mtu value is actually one over IP_MAX_MTU here, but the idea is to get past the core net MTU range checks so fjes_change_mtu can validate a new MTU against what it supports (see fjes_support_mtu in fjes_hw.c) hsr: - min_mtu = 0 (calls ether_setup, max_mtu is 1500) f_phonet: - min_mtu = 6, max_mtu = 65541 u_ether: - min_mtu = 14, max_mtu = 15412 phonet/pep-gprs: - min_mtu = 576, max_mtu = 65530 - remove redundant gprs_set_mtu CC: netdev@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: Stefan Richter CC: Faisal Latif CC: linux-rdma@vger.kernel.org CC: Cliff Whickman CC: Robin Holt CC: Jes Sorensen CC: Marek Lindner CC: Simon Wunderlich CC: Antonio Quartulli CC: Sathya Prakash CC: Chaitra P B CC: Suganath Prabu Subramani CC: MPT-FusionLinux.pdl@broadcom.com CC: Sebastian Reichel CC: Felipe Balbi CC: Arvid Brodin CC: Remi Denis-Courmont Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/fddidevice.h | 1 - include/linux/hippidevice.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fddidevice.h b/include/linux/fddidevice.h index 9a79f0106da1..32c22cfb238b 100644 --- a/include/linux/fddidevice.h +++ b/include/linux/fddidevice.h @@ -26,7 +26,6 @@ #ifdef __KERNEL__ __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev); -int fddi_change_mtu(struct net_device *dev, int new_mtu); struct net_device *alloc_fddidev(int sizeof_priv); #endif diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 8ec23fb0b412..402f99e328d4 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -32,7 +32,6 @@ struct hippi_cb { }; __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev); -int hippi_change_mtu(struct net_device *dev, int new_mtu); int hippi_mac_addr(struct net_device *dev, void *p); int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p); struct net_device *alloc_hippi_dev(int sizeof_priv); -- cgit From e5f1b245870d59be0e6cc3b33edf5406a3b59648 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 5 Oct 2016 09:33:12 +0200 Subject: cpuidle: governors: Remove remaining old module code The governor's code use try_module_get() and put_module() to refcount the governor's module. But the governors are not compiled as module. The refcount does not prevent to switch the governor or unload a module as they aren't compiled as modules. The code is pointless, so remove it. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index bb31373c3478..15deea449edc 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -235,8 +235,6 @@ struct cpuidle_governor { int (*select) (struct cpuidle_driver *drv, struct cpuidle_device *dev); void (*reflect) (struct cpuidle_device *dev, int index); - - struct module *owner; }; #ifdef CONFIG_CPU_IDLE -- cgit From 62006c1702b3b1be0c0726949e0ee0ea2326be9c Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 17 Oct 2016 20:16:58 +0200 Subject: PM / Runtime: Remove the exported function pm_children_suspended() The exported function pm_children_suspended() has only one caller, which is the runtime PM internal function, rpm_check_suspend_allowed(). Let's clean-up this code, by removing pm_children_suspended() altogether and instead do the one-liner check directly in rpm_check_suspend_allowed(). Signed-off-by: Ulf Hansson Reviewed-by: Linus Walleij Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2e14d2667b6c..61ea5666c94c 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -61,12 +61,6 @@ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) dev->power.ignore_children = enable; } -static inline bool pm_children_suspended(struct device *dev) -{ - return dev->power.ignore_children - || !atomic_read(&dev->power.child_count); -} - static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); @@ -162,7 +156,6 @@ static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} -static inline bool pm_children_suspended(struct device *dev) { return false; } static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool device_run_wake(struct device *dev) { return false; } -- cgit From b1a60995a684f2b6052cda640b0704361ab40089 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 17 Oct 2016 20:17:00 +0200 Subject: PM / Runtime: Convert pm_runtime_set_suspended() to return an int Because pm_runtime_set_suspended() invokes __pm_runtime_set_status(), which can fail, pm_runtime_set_suspended() can also fail. Instead of hiding a potential error, let's propagate it by converting pm_runtime_set_suspended() from a void to return an int. In this way users are able to check the error code and act accordingly. Signed-off-by: Ulf Hansson Reviewed-by: Linus Walleij Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 61ea5666c94c..4957fc185ea9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -258,9 +258,9 @@ static inline int pm_runtime_set_active(struct device *dev) return __pm_runtime_set_status(dev, RPM_ACTIVE); } -static inline void pm_runtime_set_suspended(struct device *dev) +static inline int pm_runtime_set_suspended(struct device *dev) { - __pm_runtime_set_status(dev, RPM_SUSPENDED); + return __pm_runtime_set_status(dev, RPM_SUSPENDED); } static inline void pm_runtime_disable(struct device *dev) -- cgit From 59d65b73a23cee48e6f3e44686f199d79b7ee854 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:49 -0700 Subject: PM / Domains: Make genpd state allocation dynamic Allow PM Domain states to be defined dynamically by the drivers. This removes the limitation on the maximum number of states possible for a domain. Suggested-by: Ulf Hansson Signed-off-by: Lina Iyer Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a09fe5c009c8..de1d8f331b03 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -19,8 +19,6 @@ /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ -#define GENPD_MAX_NUM_STATES 8 /* Number of possible low power states */ - enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ GPD_STATE_POWER_OFF, /* PM domain is off */ @@ -70,9 +68,10 @@ struct generic_pm_domain { void (*detach_dev)(struct generic_pm_domain *domain, struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ - struct genpd_power_state states[GENPD_MAX_NUM_STATES]; + struct genpd_power_state *states; unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ + void *free; /* Free the state that was allocated for default */ }; -- cgit From 405f7226014093a2809f27ba32a8230e770ac876 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:50 -0700 Subject: PM / Domains: Add residency property to genpd states Residency of a domain's idle state indicates that the minimum idle time for the domain's idle state to be beneficial for power. Add the parameter to the state node. Future patches, will use the residency value in the genpd governor to determine if it is worth while to enter an idle state. Signed-off-by: Lina Iyer Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index de1d8f331b03..f4492eb71701 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -38,6 +38,7 @@ struct gpd_dev_ops { struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; + s64 residency_ns; }; struct generic_pm_domain { -- cgit From 30f604283e05d34cb10108c7ba017e5f4fc9d62c Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:51 -0700 Subject: PM / Domains: Allow domain power states to be read from DT This patch allows domains to define idle states in the DT. SoC's can define domain idle states in DT using the "domain-idle-states" property of the domain provider. Add API to read the idle states from DT that can be set in the genpd object. This patch is based on the original patch by Marc Titinger. Signed-off-by: Marc Titinger Signed-off-by: Ulf Hansson Signed-off-by: Lina Iyer Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f4492eb71701..b4894969fbec 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -205,6 +205,8 @@ extern int of_genpd_add_device(struct of_phandle_args *args, extern int of_genpd_add_subdomain(struct of_phandle_args *parent, struct of_phandle_args *new_subdomain); extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); +extern int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n); int genpd_dev_pm_attach(struct device *dev); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -234,6 +236,12 @@ static inline int of_genpd_add_subdomain(struct of_phandle_args *parent, return -ENODEV; } +static inline int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n) +{ + return -ENODEV; +} + static inline int genpd_dev_pm_attach(struct device *dev) { return -ENODEV; -- cgit From 0c9b694a8a7d4853318c4f2ce315afa2bd3664b6 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:52 -0700 Subject: PM / Domains: Save the fwnode in genpd_power_state Save the fwnode for the genpd state in the state node. PM Domain clients may use the fwnode to read in the platform specific domain state properties and associate them with the state. Signed-off-by: Lina Iyer Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b4894969fbec..6a8988166899 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -39,6 +39,7 @@ struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; s64 residency_ns; + struct fwnode_handle *fwnode; }; struct generic_pm_domain { -- cgit From 35241d12f750d2f1556a9c85f175ce7044716881 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:54 -0700 Subject: PM / Domains: Abstract genpd locking Abstract genpd lock/unlock calls, in preparation for domain specific locks added in the following patches. Signed-off-by: Lina Iyer Signed-off-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 6a8988166899..811b968eb740 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -42,13 +42,14 @@ struct genpd_power_state { struct fwnode_handle *fwnode; }; +struct genpd_lock_ops; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head master_links; /* Links with PM domain as a master */ struct list_head slave_links; /* Links with PM domain as a slave */ struct list_head dev_list; /* List of devices */ - struct mutex lock; struct dev_power_governor *gov; struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ @@ -74,6 +75,8 @@ struct generic_pm_domain { unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ void *free; /* Free the state that was allocated for default */ + const struct genpd_lock_ops *lock_ops; + struct mutex mlock; }; -- cgit From d716f4798ff8c65ace4a6ab291f9a4ff265df4ba Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 14 Oct 2016 10:47:55 -0700 Subject: PM / Domains: Support IRQ safe PM domains Generic Power Domains currently support turning on/off only in process context. This prevents the usage of PM domains for domains that could be powered on/off in a context where IRQs are disabled. Many such domains exist today and do not get powered off, when the IRQ safe devices in that domain are powered off, because of this limitation. However, not all domains can operate in IRQ safe contexts. Genpd therefore, has to support both cases where the domain may or may not operate in IRQ safe contexts. Configuring genpd to use an appropriate lock for that domain, would allow domains that have IRQ safe devices to runtime suspend and resume, in atomic context. To achieve domain specific locking, set the domain's ->flag to GENPD_FLAG_IRQ_SAFE while defining the domain. This indicates that genpd should use a spinlock instead of a mutex for locking the domain. Locking is abstracted through genpd_lock() and genpd_unlock() functions that use the flag to determine the appropriate lock to be used for that domain. Domains that have lower latency to suspend and resume and can operate with IRQs disabled may now be able to save power, when the component devices and sub-domains are idle at runtime. The restriction this imposes on the domain hierarchy is that non-IRQ safe domains may not have IRQ-safe subdomains, but IRQ safe domains may have IRQ safe and non-IRQ safe subdomains and devices. Signed-off-by: Lina Iyer Acked-by: Ulf Hansson Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 811b968eb740..81ece61075df 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -15,9 +15,11 @@ #include #include #include +#include /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ +#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -76,7 +78,13 @@ struct generic_pm_domain { unsigned int state_idx; /* state that genpd will go to when off */ void *free; /* Free the state that was allocated for default */ const struct genpd_lock_ops *lock_ops; - struct mutex mlock; + union { + struct mutex mlock; + struct { + spinlock_t slock; + unsigned long lock_flags; + }; + }; }; -- cgit From 2d0e30c30f84d08dc16f0f2af41f1b8a85f0755e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 21 Oct 2016 12:46:33 +0200 Subject: bpf: add helper for retrieving current numa node id Use case is mainly for soreuseport to select sockets for the local numa node, but since generic, lets also add this for other networking and tracing program types. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c201017b5730..edcd96ded8aa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -319,6 +319,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; +extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; -- cgit From 304887041d953b6692c0d4a9f8fafb252d32e9a0 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 20 Oct 2016 16:28:01 +0000 Subject: platform/x86: Introduce support for Mellanox hotplug driver Enable system support for the Mellanox Technologies hotplug platform driver, which provides support for the next Mellanox basic systems: "msx6710", "msx6720", "msb7700", "msn2700", "msx1410", "msn2410", "msb7800", "msn2740", "msn2100" and also various number of derivative systems from the above basic types. This driver handles hot-plug events for the power suppliers, power cables and fans for the above systems. The Kconfig currently controlling compilation of this code is: driver/platform/x86:config MLX_CPLD_PLATFORM tristate "Mellanox platform hotplug driver support" Signed-off-by: Vadim Pasternak Signed-off-by: Darren Hart --- include/linux/platform_data/mlxcpld-hotplug.h | 99 +++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 include/linux/platform_data/mlxcpld-hotplug.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxcpld-hotplug.h b/include/linux/platform_data/mlxcpld-hotplug.h new file mode 100644 index 000000000000..e4cfcffaa6f4 --- /dev/null +++ b/include/linux/platform_data/mlxcpld-hotplug.h @@ -0,0 +1,99 @@ +/* + * include/linux/platform_data/mlxcpld-hotplug.h + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Vadim Pasternak + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H +#define __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H + +/** + * struct mlxcpld_hotplug_device - I2C device data: + * @adapter: I2C device adapter; + * @client: I2C device client; + * @brdinfo: device board information; + * @bus: I2C bus, where device is attached; + * + * Structure represents I2C hotplug device static data (board topology) and + * dynamic data (related kernel objects handles). + */ +struct mlxcpld_hotplug_device { + struct i2c_adapter *adapter; + struct i2c_client *client; + struct i2c_board_info brdinfo; + u16 bus; +}; + +/** + * struct mlxcpld_hotplug_platform_data - device platform data: + * @top_aggr_offset: offset of top aggregation interrupt register; + * @top_aggr_mask: top aggregation interrupt common mask; + * @top_aggr_psu_mask: top aggregation interrupt PSU mask; + * @psu_reg_offset: offset of PSU interrupt register; + * @psu_mask: PSU interrupt mask; + * @psu_count: number of equipped replaceable PSUs; + * @psu: pointer to PSU devices data array; + * @top_aggr_pwr_mask: top aggregation interrupt power mask; + * @pwr_reg_offset: offset of power interrupt register + * @pwr_mask: power interrupt mask; + * @pwr_count: number of power sources; + * @pwr: pointer to power devices data array; + * @top_aggr_fan_mask: top aggregation interrupt FAN mask; + * @fan_reg_offset: offset of FAN interrupt register; + * @fan_mask: FAN interrupt mask; + * @fan_count: number of equipped replaceable FANs; + * @fan: pointer to FAN devices data array; + * + * Structure represents board platform data, related to system hotplug events, + * like FAN, PSU, power cable insertion and removing. This data provides the + * number of hot-pluggable devices and hardware description for event handling. + */ +struct mlxcpld_hotplug_platform_data { + u16 top_aggr_offset; + u8 top_aggr_mask; + u8 top_aggr_psu_mask; + u16 psu_reg_offset; + u8 psu_mask; + u8 psu_count; + struct mlxcpld_hotplug_device *psu; + u8 top_aggr_pwr_mask; + u16 pwr_reg_offset; + u8 pwr_mask; + u8 pwr_count; + struct mlxcpld_hotplug_device *pwr; + u8 top_aggr_fan_mask; + u16 fan_reg_offset; + u8 fan_mask; + u8 fan_count; + struct mlxcpld_hotplug_device *fan; +}; + +#endif /* __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H */ -- cgit From b440f1d90ec54fd2586537ea46e958343ad4b151 Mon Sep 17 00:00:00 2001 From: Tomas Novotny Date: Tue, 11 Oct 2016 15:57:40 +0200 Subject: iio: dac: mcp4725: use regulator framework Use a standard framework to get the reference voltage. It is done that way in the iio subsystem and it will simplify extending of the driver. Structure mcp4725_platform_data is left undeleted because it used in the next patch. This change breaks the current users of the driver, but there is no mainline user of struct mcp4725_platform_data. Signed-off-by: Tomas Novotny Signed-off-by: Jonathan Cameron --- include/linux/iio/dac/mcp4725.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/dac/mcp4725.h b/include/linux/iio/dac/mcp4725.h index 91530e6611e9..7c062e8d2a48 100644 --- a/include/linux/iio/dac/mcp4725.h +++ b/include/linux/iio/dac/mcp4725.h @@ -10,7 +10,6 @@ #define IIO_DAC_MCP4725_H_ struct mcp4725_platform_data { - u16 vref_mv; }; #endif /* IIO_DAC_MCP4725_H_ */ -- cgit From 29157c6d601db8cb9f3bea93fc933b73db3bf869 Mon Sep 17 00:00:00 2001 From: Tomas Novotny Date: Tue, 18 Oct 2016 19:43:08 +0200 Subject: iio: dac: mcp4725: support voltage reference selection MCP47x6 chip supports selection of a voltage reference (VDD, VREF buffered or unbuffered). MCP4725 doesn't have this feature thus the eventual setting is ignored and user is warned. The setting is stored only in the volatile memory of the chip. You need to manually store it to the EEPROM of the chip via 'store_eeprom' sysfs entry. Signed-off-by: Tomas Novotny Signed-off-by: Jonathan Cameron --- include/linux/iio/dac/mcp4725.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/dac/mcp4725.h b/include/linux/iio/dac/mcp4725.h index 7c062e8d2a48..628b2cf54c50 100644 --- a/include/linux/iio/dac/mcp4725.h +++ b/include/linux/iio/dac/mcp4725.h @@ -9,7 +9,18 @@ #ifndef IIO_DAC_MCP4725_H_ #define IIO_DAC_MCP4725_H_ +/** + * struct mcp4725_platform_data - MCP4725/6 DAC specific data. + * @use_vref: Whether an external reference voltage on Vref pin should be used. + * Additional vref-supply must be specified when used. + * @vref_buffered: Controls buffering of the external reference voltage. + * + * Vref related settings are available only on MCP4756. See + * Documentation/devicetree/bindings/iio/dac/mcp4725.txt for more information. + */ struct mcp4725_platform_data { + bool use_vref; + bool vref_buffered; }; #endif /* IIO_DAC_MCP4725_H_ */ -- cgit From 7b889adbac8db4220e07c93fff0b0b235d08496b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 23 Oct 2016 09:30:44 -0700 Subject: doc: add missing docbook parameter for fence-array Fixes 'make htmldocs' warning. Signed-off-by: Stephen Hemminger Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161023093044.324edfb6@xeon-e3 --- include/linux/fence-array.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h index a44794e508df..9ea2bde10ac1 100644 --- a/include/linux/fence-array.h +++ b/include/linux/fence-array.h @@ -53,6 +53,7 @@ extern const struct fence_ops fence_array_ops; /** * fence_is_array - check if a fence is from the array subsclass + * @fence: fence to test * * Return true if it is a fence_array and false otherwise. */ -- cgit From 8c27ceff3604b249a9efafbd1bd8b141b79e619d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Oct 2016 10:12:27 -0200 Subject: docs: fix locations of several documents that got moved The previous patch renamed several files that are cross-referenced along the Kernel documentation. Adjust the links to point to the right places. Signed-off-by: Mauro Carvalho Chehab --- include/linux/device.h | 2 +- include/linux/pm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index bc41e87a969b..36d3a9867da9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -733,7 +733,7 @@ struct device_dma_parameters { * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @power: For device power management. - * See Documentation/power/devices.txt for details. + * See Documentation/power/admin-guide/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. diff --git a/include/linux/pm.h b/include/linux/pm.h index 06eb353182ab..efa67b2dfee9 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -258,7 +258,7 @@ typedef struct pm_message { * example, if it detects that a child was unplugged while the system was * asleep). * - * Refer to Documentation/power/devices.txt for more information about the role + * Refer to Documentation/power/admin-guide/devices.rst for more information about the role * of the above callbacks in the system suspend process. * * There also are callbacks related to runtime power management of devices. -- cgit From 864e2fe935228c5c551da8638b5fdd07f82d04a7 Mon Sep 17 00:00:00 2001 From: Amitesh Singh Date: Fri, 30 Sep 2016 22:40:57 +0530 Subject: usb: fix a typo in usb_class_driver documentation replace usb_unregister_dev by usb_deregister_dev Signed-off-by: Amitesh Singh Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index eba1f10e8cfd..7e68259360de 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1160,7 +1160,7 @@ extern struct bus_type usb_bus_type; * @minor_base: the start of the minor range for this driver. * * This structure is used for the usb_register_dev() and - * usb_unregister_dev() functions, to consolidate a number of the + * usb_deregister_dev() functions, to consolidate a number of the * parameters used for them. */ struct usb_class_driver { -- cgit From 08bcd3edec2559833aa0ed0213cc300fc9705dd6 Mon Sep 17 00:00:00 2001 From: Anthony Best Date: Tue, 4 Oct 2016 14:15:42 -0600 Subject: gpio: fix struct gpio_chip comment It should have been @reg_clr instead of @reg_clk Signed-off-by: Anthony Best Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 24e2cc56beb1..2dfcf25b1724 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -91,7 +91,7 @@ enum single_ended_mode { * bit. This callback assigns the right bit mask. * @reg_dat: data (in) register for generic GPIO * @reg_set: output set register (out=high) for generic GPIO - * @reg_clk: output clear register (out=low) for generic GPIO + * @reg_clr: output clear register (out=low) for generic GPIO * @reg_dir: direction setting register for generic GPIO * @bgpio_bits: number of register bits used for a generic GPIO i.e. * * 8 -- cgit From daa6e41ce2b594e7d622b4cd3978defca1139666 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 6 Sep 2016 15:18:29 -0700 Subject: soc: qcom: wcnss_ctrl: Stub wcnss_ctrl API Stub the wcnss_ctrl API to allow compile testing wcnss function drivers. Cc: Marcel Holtmann Signed-off-by: Bjorn Andersson Acked-by: Andy Gross Signed-off-by: Andy Gross --- include/linux/soc/qcom/wcnss_ctrl.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h index a37bc5538f19..eab64976a73b 100644 --- a/include/linux/soc/qcom/wcnss_ctrl.h +++ b/include/linux/soc/qcom/wcnss_ctrl.h @@ -3,6 +3,19 @@ #include +#if IS_ENABLED(CONFIG_QCOM_WCNSS_CTRL) + struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb); +#else + +static inline struct qcom_smd_channel* +qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb) +{ + WARN_ON(1); + return ERR_PTR(-ENXIO); +} + +#endif + #endif -- cgit From c8d283ff8b0b6b2061dfc137afd6c56608a34bcb Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Thu, 20 Oct 2016 21:20:59 +0200 Subject: crypto: ccp - fix typo "CPP" The abbreviation for Cryptographic Coprocessor is "CCP". Signed-off-by: Paul Bolle Acked-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/ccp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ccp.h b/include/linux/ccp.h index a7653339fedb..c71dd8fa5764 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -11,8 +11,8 @@ * published by the Free Software Foundation. */ -#ifndef __CPP_H__ -#define __CPP_H__ +#ifndef __CCP_H__ +#define __CCP_H__ #include #include @@ -553,7 +553,7 @@ enum ccp_engine { #define CCP_CMD_PASSTHRU_NO_DMA_MAP 0x00000002 /** - * struct ccp_cmd - CPP operation request + * struct ccp_cmd - CCP operation request * @entry: list element (ccp driver use only) * @work: work element used for callbacks (ccp driver use only) * @ccp: CCP device to be run on (ccp driver use only) -- cgit From 2ebda74fd6c9d3fc3b9f0234fc519795e23025a5 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Fri, 21 Oct 2016 13:19:47 +0100 Subject: crypto: acomp - add asynchronous compression api Add acomp, an asynchronous compression api that uses scatterlist buffers. Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 7cee5551625b..dc57a0505505 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -50,6 +50,7 @@ #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_KPP 0x00000008 +#define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_DIGEST 0x0000000e -- cgit From 1ab53a77b772bf7369464a0e4fa6fd6499acf8f1 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Fri, 21 Oct 2016 13:19:48 +0100 Subject: crypto: acomp - add driver-side scomp interface Add a synchronous back-end (scomp) to acomp. This allows to easily expose the already present compression algorithms in LKCF via acomp. Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index dc57a0505505..8348d83d8b5e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -51,6 +51,7 @@ #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a +#define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_DIGEST 0x0000000e @@ -61,6 +62,7 @@ #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_BLKCIPHER_MASK 0x0000000c +#define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 -- cgit From a225023828038a1aaea876a65313c863ec23fa44 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Oct 2016 15:45:27 +0200 Subject: sched/core: Explain sleep/wakeup in a better way There were a few questions wrt. how sleep-wakeup works. Try and explain it more. Requested-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/sched.h | 52 +++++++++++++++++++++++++++++++++++---------------- 1 file changed, 36 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..3762fe4e3a80 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -262,20 +262,9 @@ extern char ___assert_task_state[1 - 2*!!( #define set_task_state(tsk, state_value) \ do { \ (tsk)->task_state_change = _THIS_IP_; \ - smp_store_mb((tsk)->state, (state_value)); \ + smp_store_mb((tsk)->state, (state_value)); \ } while (0) -/* - * set_current_state() includes a barrier so that the write of current->state - * is correctly serialised wrt the caller's subsequent test of whether to - * actually sleep: - * - * set_current_state(TASK_UNINTERRUPTIBLE); - * if (do_i_need_to_sleep()) - * schedule(); - * - * If the caller does not need such serialisation then use __set_current_state() - */ #define __set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ @@ -284,11 +273,19 @@ extern char ___assert_task_state[1 - 2*!!( #define set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ - smp_store_mb(current->state, (state_value)); \ + smp_store_mb(current->state, (state_value)); \ } while (0) #else +/* + * @tsk had better be current, or you get to keep the pieces. + * + * The only reason is that computing current can be more expensive than + * using a pointer that's already available. + * + * Therefore, see set_current_state(). + */ #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ @@ -299,11 +296,34 @@ extern char ___assert_task_state[1 - 2*!!( * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * + * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); - * if (do_i_need_to_sleep()) - * schedule(); + * if (!need_sleep) + * break; + * + * schedule(); + * } + * __set_current_state(TASK_RUNNING); + * + * If the caller does not need such serialisation (because, for instance, the + * condition test and condition change and wakeup are under the same lock) then + * use __set_current_state(). + * + * The above is typically ordered against the wakeup, which does: + * + * need_sleep = false; + * wake_up_state(p, TASK_UNINTERRUPTIBLE); + * + * Where wake_up_state() (and all other wakeup primitives) imply enough + * barriers to order the store of the variable against wakeup. + * + * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, + * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a + * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). + * + * This is obviously fine, since they both store the exact same value. * - * If the caller does not need such serialisation then use __set_current_state() + * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) -- cgit From 3ca0ff571b092ee4d807f1168caa428d95b0173b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Aug 2016 13:36:04 +0200 Subject: locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Will Deacon Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/mutex-debug.h | 24 ----------------------- include/linux/mutex.h | 46 +++++++++++++++++++++++++++++---------------- 2 files changed, 30 insertions(+), 40 deletions(-) delete mode 100644 include/linux/mutex-debug.h (limited to 'include/linux') diff --git a/include/linux/mutex-debug.h b/include/linux/mutex-debug.h deleted file mode 100644 index 4ac8b1977b73..000000000000 --- a/include/linux/mutex-debug.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef __LINUX_MUTEX_DEBUG_H -#define __LINUX_MUTEX_DEBUG_H - -#include -#include -#include - -/* - * Mutexes - debugging helpers: - */ - -#define __DEBUG_MUTEX_INITIALIZER(lockname) \ - , .magic = &lockname - -#define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ -} while (0) - -extern void mutex_destroy(struct mutex *lock); - -#endif diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 2cb7531e7d7a..4d3bccabbea5 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -18,6 +18,7 @@ #include #include #include +#include /* * Simple, straightforward mutexes with strict semantics: @@ -48,16 +49,12 @@ * locks and tasks (and only those tasks) */ struct mutex { - /* 1: unlocked, 0: locked, negative: locked, possible waiters */ - atomic_t count; + atomic_long_t owner; spinlock_t wait_lock; - struct list_head wait_list; -#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) - struct task_struct *owner; -#endif #ifdef CONFIG_MUTEX_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif + struct list_head wait_list; #ifdef CONFIG_DEBUG_MUTEXES void *magic; #endif @@ -66,6 +63,11 @@ struct mutex { #endif }; +static inline struct task_struct *__mutex_owner(struct mutex *lock) +{ + return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03); +} + /* * This is the control structure for tasks blocked on mutex, * which resides on the blocked task's kernel stack: @@ -79,9 +81,20 @@ struct mutex_waiter { }; #ifdef CONFIG_DEBUG_MUTEXES -# include + +#define __DEBUG_MUTEX_INITIALIZER(lockname) \ + , .magic = &lockname + +extern void mutex_destroy(struct mutex *lock); + #else + # define __DEBUG_MUTEX_INITIALIZER(lockname) + +static inline void mutex_destroy(struct mutex *lock) {} + +#endif + /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -90,14 +103,12 @@ struct mutex_waiter { * * It is not allowed to initialize an already locked mutex. */ -# define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ +#define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + __mutex_init((mutex), #mutex, &__key); \ } while (0) -static inline void mutex_destroy(struct mutex *lock) {} -#endif #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -107,7 +118,7 @@ static inline void mutex_destroy(struct mutex *lock) {} #endif #define __MUTEX_INITIALIZER(lockname) \ - { .count = ATOMIC_INIT(1) \ + { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ @@ -127,7 +138,10 @@ extern void __mutex_init(struct mutex *lock, const char *name, */ static inline int mutex_is_locked(struct mutex *lock) { - return atomic_read(&lock->count) != 1; + /* + * XXX think about spin_is_locked + */ + return __mutex_owner(lock) != NULL; } /* -- cgit From f54d1867005c3323f5d8ad83eed823e84226c429 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 25 Oct 2016 13:00:45 +0100 Subject: dma-buf: Rename struct fence to dma_fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson Reviewed-by: Gustavo Padovan Acked-by: Sumit Semwal Acked-by: Christian König Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk --- include/linux/dma-buf.h | 4 +- include/linux/dma-fence-array.h | 86 ++++++++ include/linux/dma-fence.h | 437 ++++++++++++++++++++++++++++++++++++++++ include/linux/fence-array.h | 84 -------- include/linux/fence.h | 424 -------------------------------------- include/linux/reservation.h | 28 +-- include/linux/seqno-fence.h | 20 +- include/linux/sync_file.h | 14 +- 8 files changed, 556 insertions(+), 541 deletions(-) create mode 100644 include/linux/dma-fence-array.h create mode 100644 include/linux/dma-fence.h delete mode 100644 include/linux/fence-array.h delete mode 100644 include/linux/fence.h (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index e0b0741ae671..8daeb3ce0016 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include struct device; @@ -143,7 +143,7 @@ struct dma_buf { wait_queue_head_t poll; struct dma_buf_poll_cb_t { - struct fence_cb cb; + struct dma_fence_cb cb; wait_queue_head_t *poll; unsigned long active; diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h new file mode 100644 index 000000000000..5900945f962d --- /dev/null +++ b/include/linux/dma-fence-array.h @@ -0,0 +1,86 @@ +/* + * fence-array: aggregates fence to be waited together + * + * Copyright (C) 2016 Collabora Ltd + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * Authors: + * Gustavo Padovan + * Christian König + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __LINUX_DMA_FENCE_ARRAY_H +#define __LINUX_DMA_FENCE_ARRAY_H + +#include + +/** + * struct dma_fence_array_cb - callback helper for fence array + * @cb: fence callback structure for signaling + * @array: reference to the parent fence array object + */ +struct dma_fence_array_cb { + struct dma_fence_cb cb; + struct dma_fence_array *array; +}; + +/** + * struct dma_fence_array - fence to represent an array of fences + * @base: fence base class + * @lock: spinlock for fence handling + * @num_fences: number of fences in the array + * @num_pending: fences in the array still pending + * @fences: array of the fences + */ +struct dma_fence_array { + struct dma_fence base; + + spinlock_t lock; + unsigned num_fences; + atomic_t num_pending; + struct dma_fence **fences; +}; + +extern const struct dma_fence_ops dma_fence_array_ops; + +/** + * dma_fence_is_array - check if a fence is from the array subsclass + * @fence: fence to test + * + * Return true if it is a dma_fence_array and false otherwise. + */ +static inline bool dma_fence_is_array(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_array_ops; +} + +/** + * to_dma_fence_array - cast a fence to a dma_fence_array + * @fence: fence to cast to a dma_fence_array + * + * Returns NULL if the fence is not a dma_fence_array, + * or the dma_fence_array otherwise. + */ +static inline struct dma_fence_array * +to_dma_fence_array(struct dma_fence *fence) +{ + if (fence->ops != &dma_fence_array_ops) + return NULL; + + return container_of(fence, struct dma_fence_array, base); +} + +struct dma_fence_array *dma_fence_array_create(int num_fences, + struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any); + +#endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h new file mode 100644 index 000000000000..ba60c043a5d3 --- /dev/null +++ b/include/linux/dma-fence.h @@ -0,0 +1,437 @@ +/* + * Fence mechanism for dma-buf to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark + * Maarten Lankhorst + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __LINUX_DMA_FENCE_H +#define __LINUX_DMA_FENCE_H + +#include +#include +#include +#include +#include +#include +#include +#include + +struct dma_fence; +struct dma_fence_ops; +struct dma_fence_cb; + +/** + * struct dma_fence - software synchronization primitive + * @refcount: refcount for this fence + * @ops: dma_fence_ops associated with this fence + * @rcu: used for releasing fence with kfree_rcu + * @cb_list: list of all callbacks to call + * @lock: spin_lock_irqsave used for locking + * @context: execution context this fence belongs to, returned by + * dma_fence_context_alloc() + * @seqno: the sequence number of this fence inside the execution context, + * can be compared to decide which fence would be signaled later. + * @flags: A mask of DMA_FENCE_FLAG_* defined below + * @timestamp: Timestamp when the fence was signaled. + * @status: Optional, only valid if < 0, must be set before calling + * dma_fence_signal, indicates that the fence has completed with an error. + * + * the flags member must be manipulated and read using the appropriate + * atomic ops (bit_*), so taking the spinlock will not be needed most + * of the time. + * + * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled + * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called + * DMA_FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the + * implementer of the fence for its own purposes. Can be used in different + * ways by different fence implementers, so do not rely on this. + * + * Since atomic bitops are used, this is not guaranteed to be the case. + * Particularly, if the bit was set, but dma_fence_signal was called right + * before this bit was set, it would have been able to set the + * DMA_FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called. + * Adding a check for DMA_FENCE_FLAG_SIGNALED_BIT after setting + * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT closes this race, and makes sure that + * after dma_fence_signal was called, any enable_signaling call will have either + * been completed, or never called at all. + */ +struct dma_fence { + struct kref refcount; + const struct dma_fence_ops *ops; + struct rcu_head rcu; + struct list_head cb_list; + spinlock_t *lock; + u64 context; + unsigned seqno; + unsigned long flags; + ktime_t timestamp; + int status; +}; + +enum dma_fence_flag_bits { + DMA_FENCE_FLAG_SIGNALED_BIT, + DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + DMA_FENCE_FLAG_USER_BITS, /* must always be last member */ +}; + +typedef void (*dma_fence_func_t)(struct dma_fence *fence, + struct dma_fence_cb *cb); + +/** + * struct dma_fence_cb - callback for dma_fence_add_callback + * @node: used by dma_fence_add_callback to append this struct to fence::cb_list + * @func: dma_fence_func_t to call + * + * This struct will be initialized by dma_fence_add_callback, additional + * data can be passed along by embedding dma_fence_cb in another struct. + */ +struct dma_fence_cb { + struct list_head node; + dma_fence_func_t func; +}; + +/** + * struct dma_fence_ops - operations implemented for fence + * @get_driver_name: returns the driver name. + * @get_timeline_name: return the name of the context this fence belongs to. + * @enable_signaling: enable software signaling of fence. + * @signaled: [optional] peek whether the fence is signaled, can be null. + * @wait: custom wait implementation, or dma_fence_default_wait. + * @release: [optional] called on destruction of fence, can be null + * @fill_driver_data: [optional] callback to fill in free-form debug info + * Returns amount of bytes filled, or -errno. + * @fence_value_str: [optional] fills in the value of the fence as a string + * @timeline_value_str: [optional] fills in the current value of the timeline + * as a string + * + * Notes on enable_signaling: + * For fence implementations that have the capability for hw->hw + * signaling, they can implement this op to enable the necessary + * irqs, or insert commands into cmdstream, etc. This is called + * in the first wait() or add_callback() path to let the fence + * implementation know that there is another driver waiting on + * the signal (ie. hw->sw case). + * + * This function can be called called from atomic context, but not + * from irq context, so normal spinlocks can be used. + * + * A return value of false indicates the fence already passed, + * or some failure occurred that made it impossible to enable + * signaling. True indicates successful enabling. + * + * fence->status may be set in enable_signaling, but only when false is + * returned. + * + * Calling dma_fence_signal before enable_signaling is called allows + * for a tiny race window in which enable_signaling is called during, + * before, or after dma_fence_signal. To fight this, it is recommended + * that before enable_signaling returns true an extra reference is + * taken on the fence, to be released when the fence is signaled. + * This will mean dma_fence_signal will still be called twice, but + * the second time will be a noop since it was already signaled. + * + * Notes on signaled: + * May set fence->status if returning true. + * + * Notes on wait: + * Must not be NULL, set to dma_fence_default_wait for default implementation. + * the dma_fence_default_wait implementation should work for any fence, as long + * as enable_signaling works correctly. + * + * Must return -ERESTARTSYS if the wait is intr = true and the wait was + * interrupted, and remaining jiffies if fence has signaled, or 0 if wait + * timed out. Can also return other error values on custom implementations, + * which should be treated as if the fence is signaled. For example a hardware + * lockup could be reported like that. + * + * Notes on release: + * Can be NULL, this function allows additional commands to run on + * destruction of the fence. Can be called from irq context. + * If pointer is set to NULL, kfree will get called instead. + */ + +struct dma_fence_ops { + const char * (*get_driver_name)(struct dma_fence *fence); + const char * (*get_timeline_name)(struct dma_fence *fence); + bool (*enable_signaling)(struct dma_fence *fence); + bool (*signaled)(struct dma_fence *fence); + signed long (*wait)(struct dma_fence *fence, + bool intr, signed long timeout); + void (*release)(struct dma_fence *fence); + + int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); + void (*fence_value_str)(struct dma_fence *fence, char *str, int size); + void (*timeline_value_str)(struct dma_fence *fence, + char *str, int size); +}; + +void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, + spinlock_t *lock, u64 context, unsigned seqno); + +void dma_fence_release(struct kref *kref); +void dma_fence_free(struct dma_fence *fence); + +/** + * dma_fence_put - decreases refcount of the fence + * @fence: [in] fence to reduce refcount of + */ +static inline void dma_fence_put(struct dma_fence *fence) +{ + if (fence) + kref_put(&fence->refcount, dma_fence_release); +} + +/** + * dma_fence_get - increases refcount of the fence + * @fence: [in] fence to increase refcount of + * + * Returns the same fence, with refcount increased by 1. + */ +static inline struct dma_fence *dma_fence_get(struct dma_fence *fence) +{ + if (fence) + kref_get(&fence->refcount); + return fence; +} + +/** + * dma_fence_get_rcu - get a fence from a reservation_object_list with + * rcu read lock + * @fence: [in] fence to increase refcount of + * + * Function returns NULL if no refcount could be obtained, or the fence. + */ +static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence) +{ + if (kref_get_unless_zero(&fence->refcount)) + return fence; + else + return NULL; +} + +/** + * dma_fence_get_rcu_safe - acquire a reference to an RCU tracked fence + * @fence: [in] pointer to fence to increase refcount of + * + * Function returns NULL if no refcount could be obtained, or the fence. + * This function handles acquiring a reference to a fence that may be + * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU), + * so long as the caller is using RCU on the pointer to the fence. + * + * An alternative mechanism is to employ a seqlock to protect a bunch of + * fences, such as used by struct reservation_object. When using a seqlock, + * the seqlock must be taken before and checked after a reference to the + * fence is acquired (as shown here). + * + * The caller is required to hold the RCU read lock. + */ +static inline struct dma_fence * +dma_fence_get_rcu_safe(struct dma_fence * __rcu *fencep) +{ + do { + struct dma_fence *fence; + + fence = rcu_dereference(*fencep); + if (!fence || !dma_fence_get_rcu(fence)) + return NULL; + + /* The atomic_inc_not_zero() inside dma_fence_get_rcu() + * provides a full memory barrier upon success (such as now). + * This is paired with the write barrier from assigning + * to the __rcu protected fence pointer so that if that + * pointer still matches the current fence, we know we + * have successfully acquire a reference to it. If it no + * longer matches, we are holding a reference to some other + * reallocated pointer. This is possible if the allocator + * is using a freelist like SLAB_DESTROY_BY_RCU where the + * fence remains valid for the RCU grace period, but it + * may be reallocated. When using such allocators, we are + * responsible for ensuring the reference we get is to + * the right fence, as below. + */ + if (fence == rcu_access_pointer(*fencep)) + return rcu_pointer_handoff(fence); + + dma_fence_put(fence); + } while (1); +} + +int dma_fence_signal(struct dma_fence *fence); +int dma_fence_signal_locked(struct dma_fence *fence); +signed long dma_fence_default_wait(struct dma_fence *fence, + bool intr, signed long timeout); +int dma_fence_add_callback(struct dma_fence *fence, + struct dma_fence_cb *cb, + dma_fence_func_t func); +bool dma_fence_remove_callback(struct dma_fence *fence, + struct dma_fence_cb *cb); +void dma_fence_enable_sw_signaling(struct dma_fence *fence); + +/** + * dma_fence_is_signaled_locked - Return an indication if the fence + * is signaled yet. + * @fence: [in] the fence to check + * + * Returns true if the fence was already signaled, false if not. Since this + * function doesn't enable signaling, it is not guaranteed to ever return + * true if dma_fence_add_callback, dma_fence_wait or + * dma_fence_enable_sw_signaling haven't been called before. + * + * This function requires fence->lock to be held. + */ +static inline bool +dma_fence_is_signaled_locked(struct dma_fence *fence) +{ + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return true; + + if (fence->ops->signaled && fence->ops->signaled(fence)) { + dma_fence_signal_locked(fence); + return true; + } + + return false; +} + +/** + * dma_fence_is_signaled - Return an indication if the fence is signaled yet. + * @fence: [in] the fence to check + * + * Returns true if the fence was already signaled, false if not. Since this + * function doesn't enable signaling, it is not guaranteed to ever return + * true if dma_fence_add_callback, dma_fence_wait or + * dma_fence_enable_sw_signaling haven't been called before. + * + * It's recommended for seqno fences to call dma_fence_signal when the + * operation is complete, it makes it possible to prevent issues from + * wraparound between time of issue and time of use by checking the return + * value of this function before calling hardware-specific wait instructions. + */ +static inline bool +dma_fence_is_signaled(struct dma_fence *fence) +{ + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return true; + + if (fence->ops->signaled && fence->ops->signaled(fence)) { + dma_fence_signal(fence); + return true; + } + + return false; +} + +/** + * dma_fence_is_later - return if f1 is chronologically later than f2 + * @f1: [in] the first fence from the same context + * @f2: [in] the second fence from the same context + * + * Returns true if f1 is chronologically later than f2. Both fences must be + * from the same context, since a seqno is not re-used across contexts. + */ +static inline bool dma_fence_is_later(struct dma_fence *f1, + struct dma_fence *f2) +{ + if (WARN_ON(f1->context != f2->context)) + return false; + + return (int)(f1->seqno - f2->seqno) > 0; +} + +/** + * dma_fence_later - return the chronologically later fence + * @f1: [in] the first fence from the same context + * @f2: [in] the second fence from the same context + * + * Returns NULL if both fences are signaled, otherwise the fence that would be + * signaled last. Both fences must be from the same context, since a seqno is + * not re-used across contexts. + */ +static inline struct dma_fence *dma_fence_later(struct dma_fence *f1, + struct dma_fence *f2) +{ + if (WARN_ON(f1->context != f2->context)) + return NULL; + + /* + * Can't check just DMA_FENCE_FLAG_SIGNALED_BIT here, it may never + * have been set if enable_signaling wasn't called, and enabling that + * here is overkill. + */ + if (dma_fence_is_later(f1, f2)) + return dma_fence_is_signaled(f1) ? NULL : f1; + else + return dma_fence_is_signaled(f2) ? NULL : f2; +} + +signed long dma_fence_wait_timeout(struct dma_fence *, + bool intr, signed long timeout); +signed long dma_fence_wait_any_timeout(struct dma_fence **fences, + uint32_t count, + bool intr, signed long timeout); + +/** + * dma_fence_wait - sleep until the fence gets signaled + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * + * This function will return -ERESTARTSYS if interrupted by a signal, + * or 0 if the fence was signaled. Other error values may be + * returned on custom implementations. + * + * Performs a synchronous wait on this fence. It is assumed the caller + * directly or indirectly holds a reference to the fence, otherwise the + * fence might be freed before return, resulting in undefined behavior. + */ +static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) +{ + signed long ret; + + /* Since dma_fence_wait_timeout cannot timeout with + * MAX_SCHEDULE_TIMEOUT, only valid return values are + * -ERESTARTSYS and MAX_SCHEDULE_TIMEOUT. + */ + ret = dma_fence_wait_timeout(fence, intr, MAX_SCHEDULE_TIMEOUT); + + return ret < 0 ? ret : 0; +} + +u64 dma_fence_context_alloc(unsigned num); + +#define DMA_FENCE_TRACE(f, fmt, args...) \ + do { \ + struct dma_fence *__ff = (f); \ + if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE)) \ + pr_info("f %llu#%u: " fmt, \ + __ff->context, __ff->seqno, ##args); \ + } while (0) + +#define DMA_FENCE_WARN(f, fmt, args...) \ + do { \ + struct dma_fence *__ff = (f); \ + pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno, \ + ##args); \ + } while (0) + +#define DMA_FENCE_ERR(f, fmt, args...) \ + do { \ + struct dma_fence *__ff = (f); \ + pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno, \ + ##args); \ + } while (0) + +#endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h deleted file mode 100644 index 9ea2bde10ac1..000000000000 --- a/include/linux/fence-array.h +++ /dev/null @@ -1,84 +0,0 @@ -/* - * fence-array: aggregates fence to be waited together - * - * Copyright (C) 2016 Collabora Ltd - * Copyright (C) 2016 Advanced Micro Devices, Inc. - * Authors: - * Gustavo Padovan - * Christian König - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#ifndef __LINUX_FENCE_ARRAY_H -#define __LINUX_FENCE_ARRAY_H - -#include - -/** - * struct fence_array_cb - callback helper for fence array - * @cb: fence callback structure for signaling - * @array: reference to the parent fence array object - */ -struct fence_array_cb { - struct fence_cb cb; - struct fence_array *array; -}; - -/** - * struct fence_array - fence to represent an array of fences - * @base: fence base class - * @lock: spinlock for fence handling - * @num_fences: number of fences in the array - * @num_pending: fences in the array still pending - * @fences: array of the fences - */ -struct fence_array { - struct fence base; - - spinlock_t lock; - unsigned num_fences; - atomic_t num_pending; - struct fence **fences; -}; - -extern const struct fence_ops fence_array_ops; - -/** - * fence_is_array - check if a fence is from the array subsclass - * @fence: fence to test - * - * Return true if it is a fence_array and false otherwise. - */ -static inline bool fence_is_array(struct fence *fence) -{ - return fence->ops == &fence_array_ops; -} - -/** - * to_fence_array - cast a fence to a fence_array - * @fence: fence to cast to a fence_array - * - * Returns NULL if the fence is not a fence_array, - * or the fence_array otherwise. - */ -static inline struct fence_array *to_fence_array(struct fence *fence) -{ - if (fence->ops != &fence_array_ops) - return NULL; - - return container_of(fence, struct fence_array, base); -} - -struct fence_array *fence_array_create(int num_fences, struct fence **fences, - u64 context, unsigned seqno, - bool signal_on_any); - -#endif /* __LINUX_FENCE_ARRAY_H */ diff --git a/include/linux/fence.h b/include/linux/fence.h deleted file mode 100644 index c9c5ba98c302..000000000000 --- a/include/linux/fence.h +++ /dev/null @@ -1,424 +0,0 @@ -/* - * Fence mechanism for dma-buf to allow for asynchronous dma access - * - * Copyright (C) 2012 Canonical Ltd - * Copyright (C) 2012 Texas Instruments - * - * Authors: - * Rob Clark - * Maarten Lankhorst - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#ifndef __LINUX_FENCE_H -#define __LINUX_FENCE_H - -#include -#include -#include -#include -#include -#include -#include -#include - -struct fence; -struct fence_ops; -struct fence_cb; - -/** - * struct fence - software synchronization primitive - * @refcount: refcount for this fence - * @ops: fence_ops associated with this fence - * @rcu: used for releasing fence with kfree_rcu - * @cb_list: list of all callbacks to call - * @lock: spin_lock_irqsave used for locking - * @context: execution context this fence belongs to, returned by - * fence_context_alloc() - * @seqno: the sequence number of this fence inside the execution context, - * can be compared to decide which fence would be signaled later. - * @flags: A mask of FENCE_FLAG_* defined below - * @timestamp: Timestamp when the fence was signaled. - * @status: Optional, only valid if < 0, must be set before calling - * fence_signal, indicates that the fence has completed with an error. - * - * the flags member must be manipulated and read using the appropriate - * atomic ops (bit_*), so taking the spinlock will not be needed most - * of the time. - * - * FENCE_FLAG_SIGNALED_BIT - fence is already signaled - * FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called* - * FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the - * implementer of the fence for its own purposes. Can be used in different - * ways by different fence implementers, so do not rely on this. - * - * Since atomic bitops are used, this is not guaranteed to be the case. - * Particularly, if the bit was set, but fence_signal was called right - * before this bit was set, it would have been able to set the - * FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called. - * Adding a check for FENCE_FLAG_SIGNALED_BIT after setting - * FENCE_FLAG_ENABLE_SIGNAL_BIT closes this race, and makes sure that - * after fence_signal was called, any enable_signaling call will have either - * been completed, or never called at all. - */ -struct fence { - struct kref refcount; - const struct fence_ops *ops; - struct rcu_head rcu; - struct list_head cb_list; - spinlock_t *lock; - u64 context; - unsigned seqno; - unsigned long flags; - ktime_t timestamp; - int status; -}; - -enum fence_flag_bits { - FENCE_FLAG_SIGNALED_BIT, - FENCE_FLAG_ENABLE_SIGNAL_BIT, - FENCE_FLAG_USER_BITS, /* must always be last member */ -}; - -typedef void (*fence_func_t)(struct fence *fence, struct fence_cb *cb); - -/** - * struct fence_cb - callback for fence_add_callback - * @node: used by fence_add_callback to append this struct to fence::cb_list - * @func: fence_func_t to call - * - * This struct will be initialized by fence_add_callback, additional - * data can be passed along by embedding fence_cb in another struct. - */ -struct fence_cb { - struct list_head node; - fence_func_t func; -}; - -/** - * struct fence_ops - operations implemented for fence - * @get_driver_name: returns the driver name. - * @get_timeline_name: return the name of the context this fence belongs to. - * @enable_signaling: enable software signaling of fence. - * @signaled: [optional] peek whether the fence is signaled, can be null. - * @wait: custom wait implementation, or fence_default_wait. - * @release: [optional] called on destruction of fence, can be null - * @fill_driver_data: [optional] callback to fill in free-form debug info - * Returns amount of bytes filled, or -errno. - * @fence_value_str: [optional] fills in the value of the fence as a string - * @timeline_value_str: [optional] fills in the current value of the timeline - * as a string - * - * Notes on enable_signaling: - * For fence implementations that have the capability for hw->hw - * signaling, they can implement this op to enable the necessary - * irqs, or insert commands into cmdstream, etc. This is called - * in the first wait() or add_callback() path to let the fence - * implementation know that there is another driver waiting on - * the signal (ie. hw->sw case). - * - * This function can be called called from atomic context, but not - * from irq context, so normal spinlocks can be used. - * - * A return value of false indicates the fence already passed, - * or some failure occurred that made it impossible to enable - * signaling. True indicates successful enabling. - * - * fence->status may be set in enable_signaling, but only when false is - * returned. - * - * Calling fence_signal before enable_signaling is called allows - * for a tiny race window in which enable_signaling is called during, - * before, or after fence_signal. To fight this, it is recommended - * that before enable_signaling returns true an extra reference is - * taken on the fence, to be released when the fence is signaled. - * This will mean fence_signal will still be called twice, but - * the second time will be a noop since it was already signaled. - * - * Notes on signaled: - * May set fence->status if returning true. - * - * Notes on wait: - * Must not be NULL, set to fence_default_wait for default implementation. - * the fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. - * - * Must return -ERESTARTSYS if the wait is intr = true and the wait was - * interrupted, and remaining jiffies if fence has signaled, or 0 if wait - * timed out. Can also return other error values on custom implementations, - * which should be treated as if the fence is signaled. For example a hardware - * lockup could be reported like that. - * - * Notes on release: - * Can be NULL, this function allows additional commands to run on - * destruction of the fence. Can be called from irq context. - * If pointer is set to NULL, kfree will get called instead. - */ - -struct fence_ops { - const char * (*get_driver_name)(struct fence *fence); - const char * (*get_timeline_name)(struct fence *fence); - bool (*enable_signaling)(struct fence *fence); - bool (*signaled)(struct fence *fence); - signed long (*wait)(struct fence *fence, bool intr, signed long timeout); - void (*release)(struct fence *fence); - - int (*fill_driver_data)(struct fence *fence, void *data, int size); - void (*fence_value_str)(struct fence *fence, char *str, int size); - void (*timeline_value_str)(struct fence *fence, char *str, int size); -}; - -void fence_init(struct fence *fence, const struct fence_ops *ops, - spinlock_t *lock, u64 context, unsigned seqno); - -void fence_release(struct kref *kref); -void fence_free(struct fence *fence); - -/** - * fence_put - decreases refcount of the fence - * @fence: [in] fence to reduce refcount of - */ -static inline void fence_put(struct fence *fence) -{ - if (fence) - kref_put(&fence->refcount, fence_release); -} - -/** - * fence_get - increases refcount of the fence - * @fence: [in] fence to increase refcount of - * - * Returns the same fence, with refcount increased by 1. - */ -static inline struct fence *fence_get(struct fence *fence) -{ - if (fence) - kref_get(&fence->refcount); - return fence; -} - -/** - * fence_get_rcu - get a fence from a reservation_object_list with rcu read lock - * @fence: [in] fence to increase refcount of - * - * Function returns NULL if no refcount could be obtained, or the fence. - */ -static inline struct fence *fence_get_rcu(struct fence *fence) -{ - if (kref_get_unless_zero(&fence->refcount)) - return fence; - else - return NULL; -} - -/** - * fence_get_rcu_safe - acquire a reference to an RCU tracked fence - * @fence: [in] pointer to fence to increase refcount of - * - * Function returns NULL if no refcount could be obtained, or the fence. - * This function handles acquiring a reference to a fence that may be - * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU), - * so long as the caller is using RCU on the pointer to the fence. - * - * An alternative mechanism is to employ a seqlock to protect a bunch of - * fences, such as used by struct reservation_object. When using a seqlock, - * the seqlock must be taken before and checked after a reference to the - * fence is acquired (as shown here). - * - * The caller is required to hold the RCU read lock. - */ -static inline struct fence *fence_get_rcu_safe(struct fence * __rcu *fencep) -{ - do { - struct fence *fence; - - fence = rcu_dereference(*fencep); - if (!fence || !fence_get_rcu(fence)) - return NULL; - - /* The atomic_inc_not_zero() inside fence_get_rcu() - * provides a full memory barrier upon success (such as now). - * This is paired with the write barrier from assigning - * to the __rcu protected fence pointer so that if that - * pointer still matches the current fence, we know we - * have successfully acquire a reference to it. If it no - * longer matches, we are holding a reference to some other - * reallocated pointer. This is possible if the allocator - * is using a freelist like SLAB_DESTROY_BY_RCU where the - * fence remains valid for the RCU grace period, but it - * may be reallocated. When using such allocators, we are - * responsible for ensuring the reference we get is to - * the right fence, as below. - */ - if (fence == rcu_access_pointer(*fencep)) - return rcu_pointer_handoff(fence); - - fence_put(fence); - } while (1); -} - -int fence_signal(struct fence *fence); -int fence_signal_locked(struct fence *fence); -signed long fence_default_wait(struct fence *fence, bool intr, signed long timeout); -int fence_add_callback(struct fence *fence, struct fence_cb *cb, - fence_func_t func); -bool fence_remove_callback(struct fence *fence, struct fence_cb *cb); -void fence_enable_sw_signaling(struct fence *fence); - -/** - * fence_is_signaled_locked - Return an indication if the fence is signaled yet. - * @fence: [in] the fence to check - * - * Returns true if the fence was already signaled, false if not. Since this - * function doesn't enable signaling, it is not guaranteed to ever return - * true if fence_add_callback, fence_wait or fence_enable_sw_signaling - * haven't been called before. - * - * This function requires fence->lock to be held. - */ -static inline bool -fence_is_signaled_locked(struct fence *fence) -{ - if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return true; - - if (fence->ops->signaled && fence->ops->signaled(fence)) { - fence_signal_locked(fence); - return true; - } - - return false; -} - -/** - * fence_is_signaled - Return an indication if the fence is signaled yet. - * @fence: [in] the fence to check - * - * Returns true if the fence was already signaled, false if not. Since this - * function doesn't enable signaling, it is not guaranteed to ever return - * true if fence_add_callback, fence_wait or fence_enable_sw_signaling - * haven't been called before. - * - * It's recommended for seqno fences to call fence_signal when the - * operation is complete, it makes it possible to prevent issues from - * wraparound between time of issue and time of use by checking the return - * value of this function before calling hardware-specific wait instructions. - */ -static inline bool -fence_is_signaled(struct fence *fence) -{ - if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return true; - - if (fence->ops->signaled && fence->ops->signaled(fence)) { - fence_signal(fence); - return true; - } - - return false; -} - -/** - * fence_is_later - return if f1 is chronologically later than f2 - * @f1: [in] the first fence from the same context - * @f2: [in] the second fence from the same context - * - * Returns true if f1 is chronologically later than f2. Both fences must be - * from the same context, since a seqno is not re-used across contexts. - */ -static inline bool fence_is_later(struct fence *f1, struct fence *f2) -{ - if (WARN_ON(f1->context != f2->context)) - return false; - - return (int)(f1->seqno - f2->seqno) > 0; -} - -/** - * fence_later - return the chronologically later fence - * @f1: [in] the first fence from the same context - * @f2: [in] the second fence from the same context - * - * Returns NULL if both fences are signaled, otherwise the fence that would be - * signaled last. Both fences must be from the same context, since a seqno is - * not re-used across contexts. - */ -static inline struct fence *fence_later(struct fence *f1, struct fence *f2) -{ - if (WARN_ON(f1->context != f2->context)) - return NULL; - - /* - * can't check just FENCE_FLAG_SIGNALED_BIT here, it may never have been - * set if enable_signaling wasn't called, and enabling that here is - * overkill. - */ - if (fence_is_later(f1, f2)) - return fence_is_signaled(f1) ? NULL : f1; - else - return fence_is_signaled(f2) ? NULL : f2; -} - -signed long fence_wait_timeout(struct fence *, bool intr, signed long timeout); -signed long fence_wait_any_timeout(struct fence **fences, uint32_t count, - bool intr, signed long timeout); - -/** - * fence_wait - sleep until the fence gets signaled - * @fence: [in] the fence to wait on - * @intr: [in] if true, do an interruptible wait - * - * This function will return -ERESTARTSYS if interrupted by a signal, - * or 0 if the fence was signaled. Other error values may be - * returned on custom implementations. - * - * Performs a synchronous wait on this fence. It is assumed the caller - * directly or indirectly holds a reference to the fence, otherwise the - * fence might be freed before return, resulting in undefined behavior. - */ -static inline signed long fence_wait(struct fence *fence, bool intr) -{ - signed long ret; - - /* Since fence_wait_timeout cannot timeout with - * MAX_SCHEDULE_TIMEOUT, only valid return values are - * -ERESTARTSYS and MAX_SCHEDULE_TIMEOUT. - */ - ret = fence_wait_timeout(fence, intr, MAX_SCHEDULE_TIMEOUT); - - return ret < 0 ? ret : 0; -} - -u64 fence_context_alloc(unsigned num); - -#define FENCE_TRACE(f, fmt, args...) \ - do { \ - struct fence *__ff = (f); \ - if (IS_ENABLED(CONFIG_FENCE_TRACE)) \ - pr_info("f %llu#%u: " fmt, \ - __ff->context, __ff->seqno, ##args); \ - } while (0) - -#define FENCE_WARN(f, fmt, args...) \ - do { \ - struct fence *__ff = (f); \ - pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno, \ - ##args); \ - } while (0) - -#define FENCE_ERR(f, fmt, args...) \ - do { \ - struct fence *__ff = (f); \ - pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno, \ - ##args); \ - } while (0) - -#endif /* __LINUX_FENCE_H */ diff --git a/include/linux/reservation.h b/include/linux/reservation.h index b0f305e77b7f..2e313cca08f0 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -40,7 +40,7 @@ #define _LINUX_RESERVATION_H #include -#include +#include #include #include #include @@ -59,7 +59,7 @@ extern const char reservation_seqcount_string[]; struct reservation_object_list { struct rcu_head rcu; u32 shared_count, shared_max; - struct fence __rcu *shared[]; + struct dma_fence __rcu *shared[]; }; /** @@ -74,7 +74,7 @@ struct reservation_object { struct ww_mutex lock; seqcount_t seq; - struct fence __rcu *fence_excl; + struct dma_fence __rcu *fence_excl; struct reservation_object_list __rcu *fence; struct reservation_object_list *staged; }; @@ -107,7 +107,7 @@ reservation_object_fini(struct reservation_object *obj) { int i; struct reservation_object_list *fobj; - struct fence *excl; + struct dma_fence *excl; /* * This object should be dead and all references must have @@ -115,12 +115,12 @@ reservation_object_fini(struct reservation_object *obj) */ excl = rcu_dereference_protected(obj->fence_excl, 1); if (excl) - fence_put(excl); + dma_fence_put(excl); fobj = rcu_dereference_protected(obj->fence, 1); if (fobj) { for (i = 0; i < fobj->shared_count; ++i) - fence_put(rcu_dereference_protected(fobj->shared[i], 1)); + dma_fence_put(rcu_dereference_protected(fobj->shared[i], 1)); kfree(fobj); } @@ -155,7 +155,7 @@ reservation_object_get_list(struct reservation_object *obj) * RETURNS * The exclusive fence or NULL */ -static inline struct fence * +static inline struct dma_fence * reservation_object_get_excl(struct reservation_object *obj) { return rcu_dereference_protected(obj->fence_excl, @@ -173,10 +173,10 @@ reservation_object_get_excl(struct reservation_object *obj) * RETURNS * The exclusive fence or NULL if none */ -static inline struct fence * +static inline struct dma_fence * reservation_object_get_excl_rcu(struct reservation_object *obj) { - struct fence *fence; + struct dma_fence *fence; unsigned seq; retry: seq = read_seqcount_begin(&obj->seq); @@ -186,22 +186,22 @@ retry: rcu_read_unlock(); goto retry; } - fence = fence_get(fence); + fence = dma_fence_get(fence); rcu_read_unlock(); return fence; } int reservation_object_reserve_shared(struct reservation_object *obj); void reservation_object_add_shared_fence(struct reservation_object *obj, - struct fence *fence); + struct dma_fence *fence); void reservation_object_add_excl_fence(struct reservation_object *obj, - struct fence *fence); + struct dma_fence *fence); int reservation_object_get_fences_rcu(struct reservation_object *obj, - struct fence **pfence_excl, + struct dma_fence **pfence_excl, unsigned *pshared_count, - struct fence ***pshared); + struct dma_fence ***pshared); long reservation_object_wait_timeout_rcu(struct reservation_object *obj, bool wait_all, bool intr, diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h index a1ba6a5ccdd6..c58c535d12a8 100644 --- a/include/linux/seqno-fence.h +++ b/include/linux/seqno-fence.h @@ -20,7 +20,7 @@ #ifndef __LINUX_SEQNO_FENCE_H #define __LINUX_SEQNO_FENCE_H -#include +#include #include enum seqno_fence_condition { @@ -29,15 +29,15 @@ enum seqno_fence_condition { }; struct seqno_fence { - struct fence base; + struct dma_fence base; - const struct fence_ops *ops; + const struct dma_fence_ops *ops; struct dma_buf *sync_buf; uint32_t seqno_ofs; enum seqno_fence_condition condition; }; -extern const struct fence_ops seqno_fence_ops; +extern const struct dma_fence_ops seqno_fence_ops; /** * to_seqno_fence - cast a fence to a seqno_fence @@ -47,7 +47,7 @@ extern const struct fence_ops seqno_fence_ops; * or the seqno_fence otherwise. */ static inline struct seqno_fence * -to_seqno_fence(struct fence *fence) +to_seqno_fence(struct dma_fence *fence) { if (fence->ops != &seqno_fence_ops) return NULL; @@ -83,9 +83,9 @@ to_seqno_fence(struct fence *fence) * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the * device's vm can be expensive. * - * It is recommended for creators of seqno_fence to call fence_signal + * It is recommended for creators of seqno_fence to call dma_fence_signal() * before destruction. This will prevent possible issues from wraparound at - * time of issue vs time of check, since users can check fence_is_signaled + * time of issue vs time of check, since users can check dma_fence_is_signaled() * before submitting instructions for the hardware to wait on the fence. * However, when ops.enable_signaling is not called, it doesn't have to be * done as soon as possible, just before there's any real danger of seqno @@ -96,18 +96,18 @@ seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock, struct dma_buf *sync_buf, uint32_t context, uint32_t seqno_ofs, uint32_t seqno, enum seqno_fence_condition cond, - const struct fence_ops *ops) + const struct dma_fence_ops *ops) { BUG_ON(!fence || !sync_buf || !ops); BUG_ON(!ops->wait || !ops->enable_signaling || !ops->get_driver_name || !ops->get_timeline_name); /* - * ops is used in fence_init for get_driver_name, so needs to be + * ops is used in dma_fence_init for get_driver_name, so needs to be * initialized first */ fence->ops = ops; - fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); + dma_fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); get_dma_buf(sync_buf); fence->sync_buf = sync_buf; fence->seqno_ofs = seqno_ofs; diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index aa17ccfc2f57..3e3ab84fc4cd 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -18,8 +18,8 @@ #include #include #include -#include -#include +#include +#include /** * struct sync_file - sync file to export to the userspace @@ -41,13 +41,13 @@ struct sync_file { wait_queue_head_t wq; - struct fence *fence; - struct fence_cb cb; + struct dma_fence *fence; + struct dma_fence_cb cb; }; -#define POLL_ENABLED FENCE_FLAG_USER_BITS +#define POLL_ENABLED DMA_FENCE_FLAG_USER_BITS -struct sync_file *sync_file_create(struct fence *fence); -struct fence *sync_file_get_fence(int fd); +struct sync_file *sync_file_create(struct dma_fence *fence); +struct dma_fence *sync_file_get_fence(int fd); #endif /* _LINUX_SYNC_H */ -- cgit From 974e6f02e27e1b46c6c5e600e70ced25079f73eb Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 1 Aug 2016 11:54:35 +0200 Subject: iio: cros_ec_sensors_core: Add common functions for the ChromeOS EC Sensor Hub. Add the core functions to be able to support the sensors attached behind the ChromeOS Embedded Controller and used by other IIO cros-ec sensor drivers. The cros_ec_sensor_core driver matches with current driver in ChromeOS 4.4 tree, so it includes all the fixes at the moment. The support for this driver was made by Gwendal Grignou. The original patch and all the fixes has been squashed and rebased on top of mainline. Signed-off-by: Gwendal Grignou Signed-off-by: Guenter Roeck [eballetbo: split, squash and rebase on top of mainline the patches found in ChromeOS tree] Signed-off-by: Enric Balletbo i Serra Signed-off-by: Jonathan Cameron --- include/linux/mfd/cros_ec.h | 9 ++++ include/linux/mfd/cros_ec_commands.h | 99 ++++++++++++++++++++++++++++++++++-- 2 files changed, 103 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 76f7ef4d3a0d..1f85b7aff097 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -148,6 +148,15 @@ struct cros_ec_device { int event_size; }; +/** + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information + * + * @sensor_num: Id of the sensor, as reported by the EC. + */ +struct cros_ec_sensor_platform { + u8 sensor_num; +}; + /* struct cros_ec_platform - ChromeOS EC platform information * * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 76728ff37d01..8826e0f64b0e 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -1315,6 +1315,24 @@ enum motionsense_command { */ MOTIONSENSE_CMD_KB_WAKE_ANGLE = 5, + /* + * Returns a single sensor data. + */ + MOTIONSENSE_CMD_DATA = 6, + + /* + * Perform low level calibration.. On sensors that support it, ask to + * do offset calibration. + */ + MOTIONSENSE_CMD_PERFORM_CALIB = 10, + + /* + * Sensor Offset command is a setter/getter command for the offset used + * for calibration. The offsets can be calculated by the host, or via + * PERFORM_CALIB command. + */ + MOTIONSENSE_CMD_SENSOR_OFFSET = 11, + /* Number of motionsense sub-commands. */ MOTIONSENSE_NUM_CMDS }; @@ -1335,12 +1353,18 @@ enum motionsensor_id { enum motionsensor_type { MOTIONSENSE_TYPE_ACCEL = 0, MOTIONSENSE_TYPE_GYRO = 1, + MOTIONSENSE_TYPE_MAG = 2, + MOTIONSENSE_TYPE_PROX = 3, + MOTIONSENSE_TYPE_LIGHT = 4, + MOTIONSENSE_TYPE_ACTIVITY = 5, + MOTIONSENSE_TYPE_MAX }; /* List of motion sensor locations. */ enum motionsensor_location { MOTIONSENSE_LOC_BASE = 0, MOTIONSENSE_LOC_LID = 1, + MOTIONSENSE_LOC_MAX, }; /* List of motion sensor chips. */ @@ -1361,6 +1385,31 @@ enum motionsensor_chip { */ #define EC_MOTION_SENSE_NO_VALUE -1 +#define EC_MOTION_SENSE_INVALID_CALIB_TEMP 0x8000 + +/* Set Calibration information */ +#define MOTION_SENSE_SET_OFFSET 1 + +struct ec_response_motion_sensor_data { + /* Flags for each sensor. */ + uint8_t flags; + /* Sensor number the data comes from */ + uint8_t sensor_num; + /* Each sensor is up to 3-axis. */ + union { + int16_t data[3]; + struct { + uint16_t rsvd; + uint32_t timestamp; + } __packed; + struct { + uint8_t activity; /* motionsensor_activity */ + uint8_t state; + int16_t add_info[2]; + }; + }; +} __packed; + struct ec_params_motion_sense { uint8_t cmd; union { @@ -1378,9 +1427,37 @@ struct ec_params_motion_sense { int16_t data; } ec_rate, kb_wake_angle; + /* Used for MOTIONSENSE_CMD_SENSOR_OFFSET */ + struct { + uint8_t sensor_num; + + /* + * bit 0: If set (MOTION_SENSE_SET_OFFSET), set + * the calibration information in the EC. + * If unset, just retrieve calibration information. + */ + uint16_t flags; + + /* + * Temperature at calibration, in units of 0.01 C + * 0x8000: invalid / unknown. + * 0x0: 0C + * 0x7fff: +327.67C + */ + int16_t temp; + + /* + * Offset for calibration. + * Unit: + * Accelerometer: 1/1024 g + * Gyro: 1/1024 deg/s + * Compass: 1/16 uT + */ + int16_t offset[3]; + } __packed sensor_offset; + /* Used for MOTIONSENSE_CMD_INFO. */ struct { - /* Should be element of enum motionsensor_id. */ uint8_t sensor_num; } info; @@ -1410,11 +1487,14 @@ struct ec_response_motion_sense { /* Flags representing the motion sensor module. */ uint8_t module_flags; - /* Flags for each sensor in enum motionsensor_id. */ - uint8_t sensor_flags[EC_MOTION_SENSOR_COUNT]; + /* Number of sensors managed directly by the EC. */ + uint8_t sensor_count; - /* Array of all sensor data. Each sensor is 3-axis. */ - int16_t data[3*EC_MOTION_SENSOR_COUNT]; + /* + * Sensor data is truncated if response_max is too small + * for holding all the data. + */ + struct ec_response_motion_sensor_data sensor[0]; } dump; /* Used for MOTIONSENSE_CMD_INFO. */ @@ -1429,6 +1509,9 @@ struct ec_response_motion_sense { uint8_t chip; } info; + /* Used for MOTIONSENSE_CMD_DATA */ + struct ec_response_motion_sensor_data data; + /* * Used for MOTIONSENSE_CMD_EC_RATE, MOTIONSENSE_CMD_SENSOR_ODR, * MOTIONSENSE_CMD_SENSOR_RANGE, and @@ -1438,6 +1521,12 @@ struct ec_response_motion_sense { /* Current value of the parameter queried. */ int32_t ret; } ec_rate, sensor_odr, sensor_range, kb_wake_angle; + + /* Used for MOTIONSENSE_CMD_SENSOR_OFFSET */ + struct { + int16_t temp; + int16_t offset[3]; + } sensor_offset, perform_calib; }; } __packed; -- cgit From e4244ebddae27e9200146bba897f12a3950ce722 Mon Sep 17 00:00:00 2001 From: Vincent Palatin Date: Mon, 1 Aug 2016 11:54:37 +0200 Subject: platform/chrome: Introduce a new function to check EC features. Use the EC_CMD_GET_FEATURES message to check the supported features for each MCU. Signed-off-by: Vincent Palatin [tomeu: adapted to changes in mainline] Signed-off-by: Tomeu Vizoso [enric: remove references to USB PD feature and do it more generic] Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck For the MFD changes: Acked-by: Lee Jones Signed-off-by: Jonathan Cameron --- include/linux/mfd/cros_ec.h | 1 + include/linux/mfd/cros_ec_commands.h | 84 ++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 1f85b7aff097..f62043a75f43 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -184,6 +184,7 @@ struct cros_ec_dev { struct cros_ec_device *ec_dev; struct device *dev; u16 cmd_offset; + u32 features[2]; }; /** diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 8826e0f64b0e..1683003603f3 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -713,6 +713,90 @@ struct ec_response_get_set_value { /* More than one command can use these structs to get/set paramters. */ #define EC_CMD_GSV_PAUSE_IN_S5 0x0c +/*****************************************************************************/ +/* List the features supported by the firmware */ +#define EC_CMD_GET_FEATURES 0x0d + +/* Supported features */ +enum ec_feature_code { + /* + * This image contains a limited set of features. Another image + * in RW partition may support more features. + */ + EC_FEATURE_LIMITED = 0, + /* + * Commands for probing/reading/writing/erasing the flash in the + * EC are present. + */ + EC_FEATURE_FLASH = 1, + /* + * Can control the fan speed directly. + */ + EC_FEATURE_PWM_FAN = 2, + /* + * Can control the intensity of the keyboard backlight. + */ + EC_FEATURE_PWM_KEYB = 3, + /* + * Support Google lightbar, introduced on Pixel. + */ + EC_FEATURE_LIGHTBAR = 4, + /* Control of LEDs */ + EC_FEATURE_LED = 5, + /* Exposes an interface to control gyro and sensors. + * The host goes through the EC to access these sensors. + * In addition, the EC may provide composite sensors, like lid angle. + */ + EC_FEATURE_MOTION_SENSE = 6, + /* The keyboard is controlled by the EC */ + EC_FEATURE_KEYB = 7, + /* The AP can use part of the EC flash as persistent storage. */ + EC_FEATURE_PSTORE = 8, + /* The EC monitors BIOS port 80h, and can return POST codes. */ + EC_FEATURE_PORT80 = 9, + /* + * Thermal management: include TMP specific commands. + * Higher level than direct fan control. + */ + EC_FEATURE_THERMAL = 10, + /* Can switch the screen backlight on/off */ + EC_FEATURE_BKLIGHT_SWITCH = 11, + /* Can switch the wifi module on/off */ + EC_FEATURE_WIFI_SWITCH = 12, + /* Monitor host events, through for example SMI or SCI */ + EC_FEATURE_HOST_EVENTS = 13, + /* The EC exposes GPIO commands to control/monitor connected devices. */ + EC_FEATURE_GPIO = 14, + /* The EC can send i2c messages to downstream devices. */ + EC_FEATURE_I2C = 15, + /* Command to control charger are included */ + EC_FEATURE_CHARGER = 16, + /* Simple battery support. */ + EC_FEATURE_BATTERY = 17, + /* + * Support Smart battery protocol + * (Common Smart Battery System Interface Specification) + */ + EC_FEATURE_SMART_BATTERY = 18, + /* EC can dectect when the host hangs. */ + EC_FEATURE_HANG_DETECT = 19, + /* Report power information, for pit only */ + EC_FEATURE_PMU = 20, + /* Another Cros EC device is present downstream of this one */ + EC_FEATURE_SUB_MCU = 21, + /* Support USB Power delivery (PD) commands */ + EC_FEATURE_USB_PD = 22, + /* Control USB multiplexer, for audio through USB port for instance. */ + EC_FEATURE_USB_MUX = 23, + /* Motion Sensor code has an internal software FIFO */ + EC_FEATURE_MOTION_SENSE_FIFO = 24, +}; + +#define EC_FEATURE_MASK_0(event_code) (1UL << (event_code % 32)) +#define EC_FEATURE_MASK_1(event_code) (1UL << (event_code - 32)) +struct ec_response_get_features { + uint32_t flags[2]; +} __packed; /*****************************************************************************/ /* Flash commands */ -- cgit From 0aced355757ddc150f78a6bf4f8d885bd4eaf0e2 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Mon, 19 Sep 2016 13:09:02 +0530 Subject: mfd: tps65218: Remove redundant read wrapper Currently read directly calls the repmap read function. Hence remove the redundant wrapper and use regmap read wherever needed. Signed-off-by: Keerthy Signed-off-by: Lee Jones --- include/linux/mfd/tps65218.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index d1db9527fab5..51bef539091c 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -284,8 +284,6 @@ struct tps65218 { struct regmap *regmap; }; -int tps65218_reg_read(struct tps65218 *tps, unsigned int reg, - unsigned int *val); int tps65218_reg_write(struct tps65218 *tps, unsigned int reg, unsigned int val, unsigned int level); int tps65218_set_bits(struct tps65218 *tps, unsigned int reg, -- cgit From 2dc4940360d4c0c38aa9275532c7c0d7542f6258 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Mon, 19 Sep 2016 13:09:06 +0530 Subject: regulator: tps65218: Remove all the compatibles Remove all the individual compatibles for all the regulators and introduce id_table and update the driver accordingly to parse device tree nodes using the regulator framework. Signed-off-by: Keerthy Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/mfd/tps65218.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index 51bef539091c..bccd2d68b1e3 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -282,6 +282,7 @@ struct tps65218 { struct regulator_desc desc[TPS65218_NUM_REGULATOR]; struct tps_info *info[TPS65218_NUM_REGULATOR]; struct regmap *regmap; + u8 *strobes; }; int tps65218_reg_write(struct tps65218 *tps, unsigned int reg, -- cgit From e9a2ea5a1ba09c35258f3663842fb8d8cf2e00c2 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Sat, 22 Oct 2016 06:19:49 -0700 Subject: cacheinfo: Introduce cache id Cache management software needs an id for each instance of a cache of a particular type. The current cacheinfo structure does not provide any information about the underlying hardware so there is no way to expose it. Hardware with cache management features provides means (cpuid, enumeration etc.) to retrieve the hardware id of a particular cache instance. Cache instances which share hardware have the same hardware id. Add an 'id' field to struct cacheinfo to store this information. Expose this information under the /sys/devices/system/cpu/cpu*/cache/index*/ directory as well. Signed-off-by: Fenghua Yu Cc: "Ravi V Shankar" Cc: "Tony Luck" Cc: "David Carrillo-Cisneros" Cc: "Sai Prakhya" Cc: "Peter Zijlstra" Cc: "Stephane Eranian" Cc: "Dave Hansen" Cc: "Shaohua Li" Cc: "Nilay Vaish" Cc: "Vikas Shivappa" Cc: "Ingo Molnar" Cc: "Borislav Petkov" Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1477142405-32078-3-git-send-email-fenghua.yu@intel.com Signed-off-by: Thomas Gleixner --- include/linux/cacheinfo.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2189935075b4..0bcbb674da9d 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -18,6 +18,7 @@ enum cache_type { /** * struct cacheinfo - represent a cache leaf node + * @id: This cache's id. It is unique among caches with the same (type, level). * @type: type of the cache - data, inst or unified * @level: represents the hierarchy in the multi-level cache * @coherency_line_size: size of each cache line usually representing @@ -44,6 +45,7 @@ enum cache_type { * keeping, the remaining members form the core properties of the cache */ struct cacheinfo { + unsigned int id; enum cache_type type; unsigned int level; unsigned int coherency_line_size; @@ -61,6 +63,7 @@ struct cacheinfo { #define CACHE_WRITE_ALLOCATE BIT(3) #define CACHE_ALLOCATE_POLICY_MASK \ (CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE) +#define CACHE_ID BIT(4) struct device_node *of_node; bool disable_sysfs; -- cgit From 3cf25904fe467aebeaa77d402b6cf3c6c5d6303b Mon Sep 17 00:00:00 2001 From: Xo Wang Date: Fri, 21 Oct 2016 10:20:12 -0700 Subject: net: phy: broadcom: Update Auxiliary Control Register macros Add the RXD-to-RXC skew (delay) time bit in the Miscellaneous Control shadow register and a mask for the shadow selector field. Remove a re-definition of MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL. Signed-off-by: Xo Wang Reviewed-by: Florian Fainelli Reviewed-by: Joel Stanley Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index e3354b74286c..22c4421c916c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -105,11 +105,12 @@ #define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 #define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 +#define MII_BCM54XX_AUXCTL_MISC_RXD_RXC_SKEW 0x0100 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 #define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 -#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 /* * Broadcom LED source encodings. These are used in BCM5461, BCM5481, -- cgit From d92ead16be405b6d52ff7b366d1c9865ccc684bd Mon Sep 17 00:00:00 2001 From: Xo Wang Date: Fri, 21 Oct 2016 10:20:13 -0700 Subject: net: phy: broadcom: Add support for BCM54612E This PHY has internal delays enabled after reset. This clears the internal delay enables unless the interface specifically requests them. Signed-off-by: Xo Wang Reviewed-by: Florian Fainelli Reviewed-by: Joel Stanley Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 22c4421c916c..60def78c4e12 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -18,6 +18,7 @@ #define PHY_ID_BCM5421 0x002060e0 #define PHY_ID_BCM5464 0x002060b0 #define PHY_ID_BCM5461 0x002060c0 +#define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 #define PHY_ID_BCM57780 0x03625d90 -- cgit From aa276781a64a5f15ecc21e920960c5b1f84e5fee Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 18 Oct 2016 18:08:34 -0500 Subject: firmware: Add basic support for TI System Control Interface (TI-SCI) protocol Texas Instrument's System Control Interface (TI-SCI) Message Protocol is used in Texas Instrument's System on Chip (SoC) such as those in keystone family K2G SoC to communicate between various compute processors with a central system controller entity. TI-SCI message protocol provides support for management of various hardware entities within the SoC. Add support driver to allow communication with system controller entity within the SoC using the mailbox client. We introduce the basic registration and query capability for the driver protocol as part of this change. Subsequent patches add in functionality specific to the TI-SCI features. Signed-off-by: Nishanth Menon Signed-off-by: Tero Kristo --- include/linux/soc/ti/ti_sci_protocol.h | 69 ++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 include/linux/soc/ti/ti_sci_protocol.h (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h new file mode 100644 index 000000000000..e73483fd5327 --- /dev/null +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -0,0 +1,69 @@ +/* + * Texas Instruments System Control Interface Protocol + * + * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ + * Nishanth Menon + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __TISCI_PROTOCOL_H +#define __TISCI_PROTOCOL_H + +/** + * struct ti_sci_version_info - version information structure + * @abi_major: Major ABI version. Change here implies risk of backward + * compatibility break. + * @abi_minor: Minor ABI version. Change here implies new feature addition, + * or compatible change in ABI. + * @firmware_revision: Firmware revision (not usually used). + * @firmware_description: Firmware description (not usually used). + */ +struct ti_sci_version_info { + u8 abi_major; + u8 abi_minor; + u16 firmware_revision; + char firmware_description[32]; +}; + +/** + * struct ti_sci_handle - Handle returned to TI SCI clients for usage. + * @version: structure containing version information + */ +struct ti_sci_handle { + struct ti_sci_version_info version; +}; + +#if IS_ENABLED(CONFIG_TI_SCI_PROTOCOL) +const struct ti_sci_handle *ti_sci_get_handle(struct device *dev); +int ti_sci_put_handle(const struct ti_sci_handle *handle); +const struct ti_sci_handle *devm_ti_sci_get_handle(struct device *dev); + +#else /* CONFIG_TI_SCI_PROTOCOL */ + +static inline const struct ti_sci_handle *ti_sci_get_handle(struct device *dev) +{ + return ERR_PTR(-EINVAL); +} + +static inline int ti_sci_put_handle(const struct ti_sci_handle *handle) +{ + return -EINVAL; +} + +static inline +const struct ti_sci_handle *devm_ti_sci_get_handle(struct device *dev) +{ + return ERR_PTR(-EINVAL); +} + +#endif /* CONFIG_TI_SCI_PROTOCOL */ + +#endif /* __TISCI_PROTOCOL_H */ -- cgit From 9e7d756da7a5b0cc756d1f512f3eaf261834180a Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 18 Oct 2016 18:08:35 -0500 Subject: firmware: ti_sci: Add support for Device control Texas Instrument's System Control Interface (TI-SCI) Message Protocol is used in Texas Instrument's System on Chip (SoC) such as those in keystone family K2G SoC to communicate between various compute processors with a central system controller entity. TI-SCI message protocol provides support for management of various hardware entitites within the SoC. Add support driver to allow communication with system controller entity within the SoC using the mailbox client. We introduce the fundamental device management capability support to the driver protocol as part of this change. [d-gerlach@ti.com: Contributed device reset handling] Signed-off-by: Dave Gerlach Signed-off-by: Nishanth Menon Signed-off-by: Tero Kristo --- include/linux/soc/ti/ti_sci_protocol.h | 91 ++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index e73483fd5327..87fa73851471 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -33,12 +33,103 @@ struct ti_sci_version_info { char firmware_description[32]; }; +struct ti_sci_handle; + +/** + * struct ti_sci_dev_ops - Device control operations + * @get_device: Command to request for device managed by TISCI + * Returns 0 for successful exclusive request, else returns + * corresponding error message. + * @idle_device: Command to idle a device managed by TISCI + * Returns 0 for successful exclusive request, else returns + * corresponding error message. + * @put_device: Command to release a device managed by TISCI + * Returns 0 for successful release, else returns corresponding + * error message. + * @is_valid: Check if the device ID is a valid ID. + * Returns 0 if the ID is valid, else returns corresponding error. + * @get_context_loss_count: Command to retrieve context loss counter - this + * increments every time the device looses context. Overflow + * is possible. + * - count: pointer to u32 which will retrieve counter + * Returns 0 for successful information request and count has + * proper data, else returns corresponding error message. + * @is_idle: Reports back about device idle state + * - req_state: Returns requested idle state + * Returns 0 for successful information request and req_state and + * current_state has proper data, else returns corresponding error + * message. + * @is_stop: Reports back about device stop state + * - req_state: Returns requested stop state + * - current_state: Returns current stop state + * Returns 0 for successful information request and req_state and + * current_state has proper data, else returns corresponding error + * message. + * @is_on: Reports back about device ON(or active) state + * - req_state: Returns requested ON state + * - current_state: Returns current ON state + * Returns 0 for successful information request and req_state and + * current_state has proper data, else returns corresponding error + * message. + * @is_transitioning: Reports back if the device is in the middle of transition + * of state. + * -current_state: Returns 'true' if currently transitioning. + * @set_device_resets: Command to configure resets for device managed by TISCI. + * -reset_state: Device specific reset bit field + * Returns 0 for successful request, else returns + * corresponding error message. + * @get_device_resets: Command to read state of resets for device managed + * by TISCI. + * -reset_state: pointer to u32 which will retrieve resets + * Returns 0 for successful request, else returns + * corresponding error message. + * + * NOTE: for all these functions, the following parameters are generic in + * nature: + * -handle: Pointer to TISCI handle as retrieved by *ti_sci_get_handle + * -id: Device Identifier + * + * Request for the device - NOTE: the client MUST maintain integrity of + * usage count by balancing get_device with put_device. No refcounting is + * managed by driver for that purpose. + */ +struct ti_sci_dev_ops { + int (*get_device)(const struct ti_sci_handle *handle, u32 id); + int (*idle_device)(const struct ti_sci_handle *handle, u32 id); + int (*put_device)(const struct ti_sci_handle *handle, u32 id); + int (*is_valid)(const struct ti_sci_handle *handle, u32 id); + int (*get_context_loss_count)(const struct ti_sci_handle *handle, + u32 id, u32 *count); + int (*is_idle)(const struct ti_sci_handle *handle, u32 id, + bool *requested_state); + int (*is_stop)(const struct ti_sci_handle *handle, u32 id, + bool *req_state, bool *current_state); + int (*is_on)(const struct ti_sci_handle *handle, u32 id, + bool *req_state, bool *current_state); + int (*is_transitioning)(const struct ti_sci_handle *handle, u32 id, + bool *current_state); + int (*set_device_resets)(const struct ti_sci_handle *handle, u32 id, + u32 reset_state); + int (*get_device_resets)(const struct ti_sci_handle *handle, u32 id, + u32 *reset_state); +}; + +/** + * struct ti_sci_ops - Function support for TI SCI + * @dev_ops: Device specific operations + */ +struct ti_sci_ops { + struct ti_sci_dev_ops dev_ops; +}; + /** * struct ti_sci_handle - Handle returned to TI SCI clients for usage. * @version: structure containing version information + * @ops: operations that are made available to TI SCI clients */ struct ti_sci_handle { struct ti_sci_version_info version; + struct ti_sci_ops ops; }; #if IS_ENABLED(CONFIG_TI_SCI_PROTOCOL) -- cgit From 9f72322050e4762adde66619f048b7317ad12d77 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 18 Oct 2016 18:08:36 -0500 Subject: firmware: ti_sci: Add support for Clock control Texas Instrument's System Control Interface (TI-SCI) Message Protocol is used in Texas Instrument's System on Chip (SoC) such as those in keystone family K2G SoC to communicate between various compute processors with a central system controller entity. TI-SCI message protocol provides support for management of various hardware entities within the SoC. Add support driver to allow communication with system controller entity within the SoC using the mailbox client. In general, we expect to function at a device level of abstraction, however, for proper operation of hardware blocks, many clocks directly supplying the hardware block needs to be queried or configured. Introduce support for the set of SCI message protocol support that provide us with this capability. Signed-off-by: Nishanth Menon Signed-off-by: Tero Kristo --- include/linux/soc/ti/ti_sci_protocol.h | 78 ++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 87fa73851471..76378fddf609 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -114,12 +114,90 @@ struct ti_sci_dev_ops { u32 *reset_state); }; +/** + * struct ti_sci_clk_ops - Clock control operations + * @get_clock: Request for activation of clock and manage by processor + * - needs_ssc: 'true' if Spread Spectrum clock is desired. + * - can_change_freq: 'true' if frequency change is desired. + * - enable_input_term: 'true' if input termination is desired. + * @idle_clock: Request for Idling a clock managed by processor + * @put_clock: Release the clock to be auto managed by TISCI + * @is_auto: Is the clock being auto managed + * - req_state: state indicating if the clock is auto managed + * @is_on: Is the clock ON + * - req_state: if the clock is requested to be forced ON + * - current_state: if the clock is currently ON + * @is_off: Is the clock OFF + * - req_state: if the clock is requested to be forced OFF + * - current_state: if the clock is currently Gated + * @set_parent: Set the clock source of a specific device clock + * - parent_id: Parent clock identifier to set. + * @get_parent: Get the current clock source of a specific device clock + * - parent_id: Parent clock identifier which is the parent. + * @get_num_parents: Get the number of parents of the current clock source + * - num_parents: returns the number of parent clocks. + * @get_best_match_freq: Find a best matching frequency for a frequency + * range. + * - match_freq: Best matching frequency in Hz. + * @set_freq: Set the Clock frequency + * @get_freq: Get the Clock frequency + * - current_freq: Frequency in Hz that the clock is at. + * + * NOTE: for all these functions, the following parameters are generic in + * nature: + * -handle: Pointer to TISCI handle as retrieved by *ti_sci_get_handle + * -did: Device identifier this request is for + * -cid: Clock identifier for the device for this request. + * Each device has it's own set of clock inputs. This indexes + * which clock input to modify. + * -min_freq: The minimum allowable frequency in Hz. This is the minimum + * allowable programmed frequency and does not account for clock + * tolerances and jitter. + * -target_freq: The target clock frequency in Hz. A frequency will be + * processed as close to this target frequency as possible. + * -max_freq: The maximum allowable frequency in Hz. This is the maximum + * allowable programmed frequency and does not account for clock + * tolerances and jitter. + * + * Request for the clock - NOTE: the client MUST maintain integrity of + * usage count by balancing get_clock with put_clock. No refcounting is + * managed by driver for that purpose. + */ +struct ti_sci_clk_ops { + int (*get_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid, + bool needs_ssc, bool can_change_freq, + bool enable_input_term); + int (*idle_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid); + int (*put_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid); + int (*is_auto)(const struct ti_sci_handle *handle, u32 did, u8 cid, + bool *req_state); + int (*is_on)(const struct ti_sci_handle *handle, u32 did, u8 cid, + bool *req_state, bool *current_state); + int (*is_off)(const struct ti_sci_handle *handle, u32 did, u8 cid, + bool *req_state, bool *current_state); + int (*set_parent)(const struct ti_sci_handle *handle, u32 did, u8 cid, + u8 parent_id); + int (*get_parent)(const struct ti_sci_handle *handle, u32 did, u8 cid, + u8 *parent_id); + int (*get_num_parents)(const struct ti_sci_handle *handle, u32 did, + u8 cid, u8 *num_parents); + int (*get_best_match_freq)(const struct ti_sci_handle *handle, u32 did, + u8 cid, u64 min_freq, u64 target_freq, + u64 max_freq, u64 *match_freq); + int (*set_freq)(const struct ti_sci_handle *handle, u32 did, u8 cid, + u64 min_freq, u64 target_freq, u64 max_freq); + int (*get_freq)(const struct ti_sci_handle *handle, u32 did, u8 cid, + u64 *current_freq); +}; + /** * struct ti_sci_ops - Function support for TI SCI * @dev_ops: Device specific operations + * @clk_ops: Clock specific operations */ struct ti_sci_ops { struct ti_sci_dev_ops dev_ops; + struct ti_sci_clk_ops clk_ops; }; /** -- cgit From 912cffb4ed8612dc99ee0251cc0c9785855162cd Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 18 Oct 2016 18:08:37 -0500 Subject: firmware: ti_sci: Add support for reboot core service Since system controller now has control over SoC power management, it needs to be explicitly requested to reboot the SoC. Add support for it. In some systems however, SoC needs to toggle a GPIO or send event to an external entity (like a PMIC) for a system reboot to take place. To facilitate that, we allow for a DT property to determine if the reboot handler will be registered and further, the service is also made available to other drivers (such as PMIC driver) to sequence the additional operation and trigger the SoC reboot as the last step. Tested-by: Lokesh Vutla Signed-off-by: Nishanth Menon Signed-off-by: Tero Kristo --- include/linux/soc/ti/ti_sci_protocol.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 76378fddf609..0ccbc138c26a 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -35,6 +35,16 @@ struct ti_sci_version_info { struct ti_sci_handle; +/** + * struct ti_sci_core_ops - SoC Core Operations + * @reboot_device: Reboot the SoC + * Returns 0 for successful request(ideally should never return), + * else returns corresponding error value. + */ +struct ti_sci_core_ops { + int (*reboot_device)(const struct ti_sci_handle *handle); +}; + /** * struct ti_sci_dev_ops - Device control operations * @get_device: Command to request for device managed by TISCI @@ -196,6 +206,7 @@ struct ti_sci_clk_ops { * @clk_ops: Clock specific operations */ struct ti_sci_ops { + struct ti_sci_core_ops core_ops; struct ti_sci_dev_ops dev_ops; struct ti_sci_clk_ops clk_ops; }; -- cgit From 3f817fe718c6cb3ddcc2ab04ba86faecc20ef8fe Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:01 +0300 Subject: cfg80211: Define IEEE P802.11ai (FILS) information elements Define the Element IDs and Element ID Extensions from IEEE P802.11ai/D11.0. In addition, add a new cfg80211_find_ext_ie() wrapper to make it easier to find information elements that used the Element ID Extension field. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a80516fd65c8..d428adf51446 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1960,6 +1960,26 @@ enum ieee80211_eid { WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, + WLAN_EID_CAG_NUMBER = 237, + WLAN_EID_AP_CSN = 239, + WLAN_EID_FILS_INDICATION = 240, + WLAN_EID_DILS = 241, + WLAN_EID_FRAGMENT = 242, + WLAN_EID_EXTENSION = 255 +}; + +/* Element ID Extensions for Element ID 255 */ +enum ieee80211_eid_ext { + WLAN_EID_EXT_ASSOC_DELAY_INFO = 1, + WLAN_EID_EXT_FILS_REQ_PARAMS = 2, + WLAN_EID_EXT_FILS_KEY_CONFIRM = 3, + WLAN_EID_EXT_FILS_SESSION = 4, + WLAN_EID_EXT_FILS_HLP_CONTAINER = 5, + WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN = 6, + WLAN_EID_EXT_KEY_DELIVERY = 7, + WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, + WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, + WLAN_EID_EXT_FILS_NONCE = 13, }; /* Action category code */ -- cgit From 631810603a20874554b2f17adf42b72d0f15eda5 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:02 +0300 Subject: cfg80211: Add Fast Initial Link Setup (FILS) auth algs This defines authentication algorithms for FILS (IEEE 802.11ai). Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d428adf51446..793a0174ba29 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1576,6 +1576,9 @@ struct ieee80211_vht_operation { #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 +#define WLAN_AUTH_FILS_SK 4 +#define WLAN_AUTH_FILS_SK_PFS 5 +#define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 -- cgit From 348bd456699801920a309c66e382380809fbdf41 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:03 +0300 Subject: cfg80211: Add KEK/nonces for FILS association frames The new nl80211 attributes can be used to provide KEK and nonces to allow the driver to encrypt and decrypt FILS (Re)Association Request/Response frames in station mode. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 793a0174ba29..fe849329511a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2096,6 +2096,9 @@ enum ieee80211_key_len { #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 +#define FILS_NONCE_LEN 16 +#define FILS_MAX_KEK_LEN 64 + /* Public action codes */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, -- cgit From d705ff38189fcfbbfa6aa97363d30c23348ad166 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 3 Oct 2016 11:18:33 +0200 Subject: tty: vt, cleanup and document con_scroll Scrolling helpers scrup and scrdown both accept 'top' and 'bottom' as unsigned int. Number of lines 'nr' is accepted as int, but all callers pass down unsigned too. So change the type of 'nr' to unsigned too. Now, promote unsigned int from the helpers up to the con_scroll hook which actually accepted all those as signed int. Next, the 'dir' parameter can have only two values and we define constants for that: SM_UP and SM_DOWN. Switch them to enum and do proper type checking on 'dir' too. Finally, document the behaviour of the hook. Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: Tomi Valkeinen Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Cc: Cc: Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 3672809234a7..508b012bd5bd 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -28,9 +28,17 @@ struct tty_struct; #define VT100ID "\033[?1;2c" #define VT102ID "\033[?6c" +enum con_scroll { + SM_UP, + SM_DOWN, +}; + /** * struct consw - callbacks for consoles * + * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. + * Return true if no generic handling should be done. + * Invoked by csi_M and printing to the console. * @con_set_palette: sets the palette of the console to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) @@ -44,7 +52,9 @@ struct consw { void (*con_putc)(struct vc_data *, int, int, int); void (*con_putcs)(struct vc_data *, const unsigned short *, int, int, int); void (*con_cursor)(struct vc_data *, int); - int (*con_scroll)(struct vc_data *, int, int, int, int); + bool (*con_scroll)(struct vc_data *, unsigned int top, + unsigned int bottom, enum con_scroll dir, + unsigned int lines); int (*con_switch)(struct vc_data *); int (*con_blank)(struct vc_data *, int, int); int (*con_font_set)(struct vc_data *, struct console_font *, unsigned); @@ -99,10 +109,6 @@ static inline int con_debug_leave(void) } #endif -/* scroll */ -#define SM_UP (1) -#define SM_DOWN (2) - /* cursor */ #define CM_DRAW (1) #define CM_ERASE (2) -- cgit From 35cc56f9a30480c8a0cca809cf341614a2144758 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 3 Oct 2016 11:18:35 +0200 Subject: tty: vgacon+sisusb, move scrolldelta to a common helper The code is mirrorred in scrolldelta implementations of both vgacon and sisusb. Let's move the code to a separate helper where we will perform a common cleanup and further changes. While we are moving the code, make it linear and save one indentation level. This is done by returning from the "!lines" then-branch immediatelly. This allows flushing the else-branch 1 level to the left, obviously. Few more new lines and comments were added too. And do not forget to export the helper function given sisusb can be built as module. Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: Tomi Valkeinen Cc: Cc: Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 6abd24f258bc..833fdd4794a0 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -191,5 +191,7 @@ extern void vt_set_led_state(int console, int leds); extern void vt_kbd_con_start(int console); extern void vt_kbd_con_stop(int console); +void vc_scrolldelta_helper(struct vc_data *c, int lines, + unsigned int rolled_over, void *_base, unsigned int size); #endif /* _VT_KERN_H */ -- cgit From a07ea4d9941af5a0c6f0be2a71b51ac9c083c5e5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:02 +0200 Subject: genetlink: no longer support using static family IDs Static family IDs have never really been used, the only use case was the workaround I introduced for those users that assumed their family ID was also their multicast group ID. Additionally, because static family IDs would never be reserved by the generic netlink code, using a relatively low ID would only work for built-in families that can be registered immediately after generic netlink is started, which is basically only the control family (apart from the workaround code, which I also had to add code for so it would reserve those IDs) Thus, anything other than GENL_ID_GENERATE is flawed and luckily not used except in the cases I mentioned. Move those workarounds into a few lines of code, and then get rid of GENL_ID_GENERATE entirely, making it more robust. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genl_magic_func.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 667c31101b8b..7c070c1fe457 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -260,7 +260,6 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = { */ #define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) static struct genl_family ZZZ_genl_family __read_mostly = { - .id = GENL_ID_GENERATE, .name = __stringify(GENL_MAGIC_FAMILY), .version = GENL_MAGIC_VERSION, #ifdef GENL_MAGIC_FAMILY_HDRSZ -- cgit From 489111e5c25b93be80340c3113d71903d7c82136 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:03 +0200 Subject: genetlink: statically initialize families Instead of providing macros/inline functions to initialize the families, make all users initialize them statically and get rid of the macros. This reduces the kernel code size by about 1.6k on x86-64 (with allyesconfig). Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/drbd_genl.h | 2 +- include/linux/genl_magic_func.h | 28 ++++++++++++++++------------ 2 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index c934d3a96b5e..2896f93808ae 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -67,7 +67,7 @@ * genl_magic_func.h * generates an entry in the static genl_ops array, * and static register/unregister functions to - * genl_register_family_with_ops(). + * genl_register_family(). * * flags and handler: * GENL_op_init( .doit = x, .dumpit = y, .flags = something) diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 7c070c1fe457..40c2e39362c8 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -259,15 +259,7 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = { * {{{2 */ #define ZZZ_genl_family CONCAT_(GENL_MAGIC_FAMILY, _genl_family) -static struct genl_family ZZZ_genl_family __read_mostly = { - .name = __stringify(GENL_MAGIC_FAMILY), - .version = GENL_MAGIC_VERSION, -#ifdef GENL_MAGIC_FAMILY_HDRSZ - .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), -#endif - .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, -}; - +static struct genl_family ZZZ_genl_family; /* * Magic: define multicast groups * Magic: define multicast group registration helper @@ -301,11 +293,23 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ #undef GENL_mc_group #define GENL_mc_group(group) +static struct genl_family ZZZ_genl_family __read_mostly = { + .name = __stringify(GENL_MAGIC_FAMILY), + .version = GENL_MAGIC_VERSION, +#ifdef GENL_MAGIC_FAMILY_HDRSZ + .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), +#endif + .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, + .ops = ZZZ_genl_ops, + .n_ops = ARRAY_SIZE(ZZZ_genl_ops), + .mcgrps = ZZZ_genl_mcgrps, + .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), + .module = THIS_MODULE, +}; + int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void) { - return genl_register_family_with_ops_groups(&ZZZ_genl_family, \ - ZZZ_genl_ops, \ - ZZZ_genl_mcgrps); + return genl_register_family(&ZZZ_genl_family); } void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void) -- cgit From 56989f6d8568c21257dcec0f5e644d5570ba3281 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:05 +0200 Subject: genetlink: mark families as __ro_after_init Now genl_register_family() is the only thing (other than the users themselves, perhaps, but I didn't find any doing that) writing to the family struct. In all families that I found, genl_register_family() is only called from __init functions (some indirectly, in which case I've add __init annotations to clarifly things), so all can actually be marked __ro_after_init. This protects the data structure from accidental corruption. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genl_magic_func.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 40c2e39362c8..377257d8f7e3 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -293,7 +293,7 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)( \ #undef GENL_mc_group #define GENL_mc_group(group) -static struct genl_family ZZZ_genl_family __read_mostly = { +static struct genl_family ZZZ_genl_family __ro_after_init = { .name = __stringify(GENL_MAGIC_FAMILY), .version = GENL_MAGIC_VERSION, #ifdef GENL_MAGIC_FAMILY_HDRSZ -- cgit From 7f847dd31736f1284538e54f46cf10e63929eb7f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 20 Oct 2016 22:07:53 +0200 Subject: debugfs: improve DEFINE_DEBUGFS_ATTRIBUTE for !CONFIG_DEBUG_FS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The slp_s0_residency_usec debugfs file currently uses DEFINE_DEBUGFS_ATTRIBUTE(), but that macro cannot really be used to define files outside of the debugfs code, as it has no reference to the get/set functions if CONFIG_DEBUG_FS is not defined: drivers/platform/x86/intel_pmc_core.c:80:12: error: ‘pmc_core_dev_state_get’ defined but not used [-Werror=unused-function] This fixes the macro to always contain the reference, and instead rely on the stubbed-out debugfs_create_file to not actually refer to its arguments so the compiler can still drop the reference. This works because the attribute definition is always 'static', and the dead-code removal silently drops all static symbols that are not used. Fixes: c64688081490 ("debugfs: add support for self-protecting attribute file fops") Fixes: df2294fb6428 ("intel_pmc_core: Convert to DEFINE_DEBUGFS_ATTRIBUTE") Signed-off-by: Arnd Bergmann [nicstange@gmail.com: Add dummy implementations of debugfs_attr_read() and debugfs_attr_write() in order to protect against possibly broken dead code elimination and to improve readability. Correct CONFIG_DEBUGFS_FS -> CONFIG_DEBUG_FS typo in changelog.] Signed-off-by: Nicolai Stange Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 44 +++++++++++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 4d3f0d1aec73..1b413a9aab81 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -62,6 +62,21 @@ static inline const struct file_operations *debugfs_real_fops(struct file *filp) return filp->f_path.dentry->d_fsdata; } +#define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ +static int __fops ## _open(struct inode *inode, struct file *file) \ +{ \ + __simple_attr_check_format(__fmt, 0ull); \ + return simple_attr_open(inode, file, __get, __set, __fmt); \ +} \ +static const struct file_operations __fops = { \ + .owner = THIS_MODULE, \ + .open = __fops ## _open, \ + .release = simple_attr_release, \ + .read = debugfs_attr_read, \ + .write = debugfs_attr_write, \ + .llseek = generic_file_llseek, \ +} + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_create_file(const char *name, umode_t mode, @@ -99,21 +114,6 @@ ssize_t debugfs_attr_read(struct file *file, char __user *buf, ssize_t debugfs_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); -#define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ -static int __fops ## _open(struct inode *inode, struct file *file) \ -{ \ - __simple_attr_check_format(__fmt, 0ull); \ - return simple_attr_open(inode, file, __get, __set, __fmt); \ -} \ -static const struct file_operations __fops = { \ - .owner = THIS_MODULE, \ - .open = __fops ## _open, \ - .release = simple_attr_release, \ - .read = debugfs_attr_read, \ - .write = debugfs_attr_write, \ - .llseek = generic_file_llseek, \ -} - struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, const char *new_name); @@ -233,8 +233,18 @@ static inline void debugfs_use_file_finish(int srcu_idx) __releases(&debugfs_srcu) { } -#define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ - static const struct file_operations __fops = { 0 } +static inline ssize_t debugfs_attr_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos) +{ + return -ENODEV; +} + +static inline ssize_t debugfs_attr_write(struct file *file, + const char __user *buf, + size_t len, loff_t *ppos) +{ + return -ENODEV; +} static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, char *new_name) -- cgit From 5be149bdd36c8765c9e785f70b888d028ada40af Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Wed, 19 Oct 2016 16:33:27 +0300 Subject: mei: bus: add module_mei_cl_driver helper macro Add module_mei_cl_driver helper macro for eliminating the boilerplate code from mei_cl drivers registration. The macro is intended for drivers which in their init/exit sections does only register/unregister of a mei_cl driver. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index e746919530f5..e6fbd98ea90e 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -74,6 +74,19 @@ int __mei_cldev_driver_register(struct mei_cl_driver *cldrv, void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); +/** + * module_mei_cl_driver - Helper macro for registering mei cl driver + * + * @__mei_cldrv mei_cl_driver structure + * + * Helper macro for mei cl drivers which do not do anything special in module + * init/exit, for eliminating a boilerplate code. + */ +#define module_mei_cl_driver(__mei_cldrv) \ + module_driver(__mei_cldrv, \ + mei_cldev_driver_register,\ + mei_cldev_driver_unregister) + ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length); ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); -- cgit From 1e4edb3fe93ff9f7b678a8f1b8d9df717edf6ad9 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Wed, 19 Oct 2016 16:33:31 +0300 Subject: mei: bus: remove rx callback context The callback context is redunant as all the information can be retrived from the device struture of its private data. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index e6fbd98ea90e..4adb2e7c9f84 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -9,7 +9,7 @@ struct mei_cl_device; struct mei_device; typedef void (*mei_cldev_event_cb_t)(struct mei_cl_device *cldev, - u32 events, void *context); + u32 events); /** * struct mei_cl_device - MEI device handle @@ -27,7 +27,6 @@ typedef void (*mei_cldev_event_cb_t)(struct mei_cl_device *cldev, * @event_work: async work to execute event callback * @event_cb: Drivers register this callback to get asynchronous ME * events (e.g. Rx buffer pending) notifications. - * @event_context: event callback run context * @events_mask: Events bit mask requested by driver. * @events: Events bitmask sent to the driver. * @@ -46,7 +45,6 @@ struct mei_cl_device { struct work_struct event_work; mei_cldev_event_cb_t event_cb; - void *event_context; unsigned long events_mask; unsigned long events; @@ -92,7 +90,7 @@ ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); int mei_cldev_register_event_cb(struct mei_cl_device *cldev, unsigned long event_mask, - mei_cldev_event_cb_t read_cb, void *context); + mei_cldev_event_cb_t read_cb); #define MEI_CL_EVENT_RX 0 #define MEI_CL_EVENT_TX 1 -- cgit From f71082f815bf0b9599b97546cf1dd057c789c3c1 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 22 Oct 2016 18:36:05 -0400 Subject: miscdevice: introduce builtin_misc_device This is basically the same as module_misc_device but without the presence of an exit/remove function. Similar in nature to the commit f309d4443130bf814e991f836e919dca22df37ae ("platform_device: better support builtin boilerplate avoidance"). Cc: Arnd Bergmann Signed-off-by: Paul Gortmaker Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 722698a43d79..a426cb55dc43 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -71,6 +71,13 @@ struct miscdevice { extern int misc_register(struct miscdevice *misc); extern void misc_deregister(struct miscdevice *misc); +/* + * Helper macro for drivers that don't do anything special in the initcall. + * This helps in eleminating of boilerplate code. + */ +#define builtin_misc_device(__misc_device) \ + builtin_driver(__misc_device, misc_register) + /* * Helper macro for drivers that don't do anything special in module init / exit * call. This helps in eleminating of boilerplate code. -- cgit From c4aebd0332da831a3403faf2035af45059ab6b7c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:09 +0200 Subject: block: remove bio_is_rw With the addition of the zoned operations the tests in this function became incorrect. But I think it's much better to just open code the allow operations in the only caller anyway. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/bio.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 97cb48f03dc7..87ce64dafb93 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -83,17 +83,6 @@ static inline bool bio_no_advance_iter(struct bio *bio) bio_op(bio) == REQ_OP_WRITE_SAME; } -static inline bool bio_is_rw(struct bio *bio) -{ - if (!bio_has_data(bio)) - return false; - - if (bio_no_advance_iter(bio)) - return false; - - return true; -} - static inline bool bio_mergeable(struct bio *bio) { if (bio->bi_opf & REQ_NOMERGE_FLAGS) -- cgit From bd1c1c21741cbd6e894960bcbc8b36f719590064 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:10 +0200 Subject: block: REQ_NOMERGE is common to the bio and request So move it into the common setion of the request flags. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dd50dce89a80..b54142534793 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -158,6 +158,7 @@ enum rq_flag_bits { __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ + __REQ_NOMERGE, /* don't touch this for merging */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ @@ -171,7 +172,6 @@ enum rq_flag_bits { /* request only flags */ __REQ_SORTED, /* elevator knows about this request */ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_NOMERGE, /* don't touch this for merging */ __REQ_STARTED, /* drive already may have started this one */ __REQ_DONTPREP, /* don't call prep for this one */ __REQ_QUEUED, /* uses queueing */ -- cgit From 188bd2b16b3c6ea87a90df20f33db0adcdb75f0c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:11 +0200 Subject: block: move REQ_RAHEAD to common flags The information that am I/O is a read-ahead can be useful for drivers. In fact the NVMe driver already checks it, even if it won't ever be set at the moment. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b54142534793..44f9bca332e5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -163,9 +163,9 @@ enum rq_flag_bits { __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ /* bio only flags */ - __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ @@ -205,7 +205,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE) + REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE | REQ_RAHEAD) #define REQ_CLONE_MASK REQ_COMMON_MASK /* This mask is used for both bio and request merge checking */ -- cgit From 8d2bbd4c8236e9e38e6b36ac9e2c54fdcfe5b335 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:12 +0200 Subject: block: replace REQ_THROTTLED with a bio flag It's the last bio-only REQ_* flag, and we have space for it in the bio bi_flags field. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 44f9bca332e5..6df722de2e22 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -119,6 +119,8 @@ struct bio { #define BIO_QUIET 6 /* Make BIO Quiet */ #define BIO_CHAIN 7 /* chained bio, ->bi_remaining in effect */ #define BIO_REFFED 8 /* bio has elevated ->bi_cnt */ +#define BIO_THROTTLED 9 /* This bio has already been subjected to + * throttling rules. Don't do it again. */ /* * Flags starting here get preserved by bio_reset() - this includes @@ -165,10 +167,6 @@ enum rq_flag_bits { __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ - /* bio only flags */ - __REQ_THROTTLED, /* This bio has already been subjected to - * throttling rules. Don't do it again. */ - /* request only flags */ __REQ_SORTED, /* elevator knows about this request */ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ @@ -213,8 +211,6 @@ enum rq_flag_bits { (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_PREFLUSH | REQ_FUA | REQ_FLUSH_SEQ) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_THROTTLED (1ULL << __REQ_THROTTLED) - #define REQ_SORTED (1ULL << __REQ_SORTED) #define REQ_SOFTBARRIER (1ULL << __REQ_SOFTBARRIER) #define REQ_FUA (1ULL << __REQ_FUA) -- cgit From e806402130c9c494e22c73ae9ead4e79d2a5811c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:13 +0200 Subject: block: split out request-only flags into a new namespace A lot of the REQ_* flags are only used on struct requests, and only of use to the block layer and a few drivers that dig into struct request internals. This patch adds a new req_flags_t rq_flags field to struct request for them, and thus dramatically shrinks the number of common requests. It also removes the unfortunate situation where we have to fit the fields from the same enum into 32 bits for struct bio and 64 bits for struct request. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 39 +------------------------------------ include/linux/blkdev.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 49 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6df722de2e22..ec69a8fe3b29 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,26 +167,6 @@ enum rq_flag_bits { __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ - /* request only flags */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests and also - for requests for which the SCSI "quiesce" - state must be ignored. */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_FLUSH_SEQ, /* request for flush sequence */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_PM, /* runtime pm request */ - __REQ_HASHED, /* on IO scheduler merge hash */ - __REQ_MQ_INFLIGHT, /* track inflight for MQ */ __REQ_NR_BITS, /* stops here */ }; @@ -208,29 +188,12 @@ enum rq_flag_bits { /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_PREFLUSH | REQ_FUA | REQ_FLUSH_SEQ) + (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_SORTED (1ULL << __REQ_SORTED) -#define REQ_SOFTBARRIER (1ULL << __REQ_SOFTBARRIER) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_STARTED (1ULL << __REQ_STARTED) -#define REQ_DONTPREP (1ULL << __REQ_DONTPREP) -#define REQ_QUEUED (1ULL << __REQ_QUEUED) -#define REQ_ELVPRIV (1ULL << __REQ_ELVPRIV) -#define REQ_FAILED (1ULL << __REQ_FAILED) -#define REQ_QUIET (1ULL << __REQ_QUIET) -#define REQ_PREEMPT (1ULL << __REQ_PREEMPT) -#define REQ_ALLOCED (1ULL << __REQ_ALLOCED) -#define REQ_COPY_USER (1ULL << __REQ_COPY_USER) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) -#define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) -#define REQ_IO_STAT (1ULL << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) -#define REQ_PM (1ULL << __REQ_PM) -#define REQ_HASHED (1ULL << __REQ_HASHED) -#define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) enum req_op { REQ_OP_READ, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 90097dd8b8ed..b4415feac679 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -78,6 +78,50 @@ enum rq_cmd_type_bits { REQ_TYPE_DRV_PRIV, /* driver defined types from here */ }; +/* + * request flags */ +typedef __u32 __bitwise req_flags_t; + +/* elevator knows about this request */ +#define RQF_SORTED ((__force req_flags_t)(1 << 0)) +/* drive already may have started this one */ +#define RQF_STARTED ((__force req_flags_t)(1 << 1)) +/* uses tagged queueing */ +#define RQF_QUEUED ((__force req_flags_t)(1 << 2)) +/* may not be passed by ioscheduler */ +#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) +/* request for flush sequence */ +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) +/* merge of different types, fail separately */ +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) +/* track inflight for MQ */ +#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) +/* don't call prep for this one */ +#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* set for "ide_preempt" requests and also for requests for which the SCSI + "quiesce" state must be ignored. */ +#define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) +/* contains copies of user pages */ +#define RQF_COPY_USER ((__force req_flags_t)(1 << 9)) +/* vaguely specified driver internal error. Ignored by the block layer */ +#define RQF_FAILED ((__force req_flags_t)(1 << 10)) +/* don't warn about errors */ +#define RQF_QUIET ((__force req_flags_t)(1 << 11)) +/* elevator private data attached */ +#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) +/* account I/O stat */ +#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) +/* request came from our alloc pool */ +#define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) +/* runtime pm request */ +#define RQF_PM ((__force req_flags_t)(1 << 15)) +/* on IO scheduler merge hash */ +#define RQF_HASHED ((__force req_flags_t)(1 << 16)) + +/* flags that prevent us from merging requests: */ +#define RQF_NOMERGE_FLAGS \ + (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ) + #define BLK_MAX_CDB 16 /* @@ -99,6 +143,7 @@ struct request { int cpu; unsigned cmd_type; u64 cmd_flags; + req_flags_t rq_flags; unsigned long atomic_flags; /* the following two fields are internal, NEVER access directly */ @@ -648,7 +693,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) REQ_FAILFAST_DRIVER)) #define blk_account_rq(rq) \ - (((rq)->cmd_flags & REQ_STARTED) && \ + (((rq)->rq_flags & RQF_STARTED) && \ ((rq)->cmd_type == REQ_TYPE_FS)) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) @@ -740,6 +785,8 @@ static inline bool rq_mergeable(struct request *rq) if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; + if (rq->rq_flags & RQF_NOMERGE_FLAGS) + return false; return true; } -- cgit From ef295ecf090d3e86e5b742fc6ab34f1122a43773 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Oct 2016 08:48:16 -0600 Subject: block: better op and flags encoding Now that we don't need the common flags to overflow outside the range of a 32-bit type we can encode them the same way for both the bio and request fields. This in addition allows us to place the operation first (and make some room for more ops while we're at it) and to stop having to shift around the operation values. In addition this allows passing around only one value in the block layer instead of two (and eventuall also in the file systems, but we can do that later) and thus clean up a lot of code. Last but not least this allows decreasing the size of the cmd_flags field in struct request to 32-bits. Various functions passing this value could also be updated, but I'd like to avoid the churn for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 11 +++--- include/linux/blk_types.h | 83 ++++++++++++++++++++------------------------ include/linux/blkdev.h | 26 ++------------ include/linux/blktrace_api.h | 2 +- include/linux/dm-io.h | 2 +- include/linux/elevator.h | 4 +-- 6 files changed, 48 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 3bf5d33800ab..ddaf28d0988f 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -581,15 +581,14 @@ static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) /** * blkg_rwstat_add - add a value to a blkg_rwstat * @rwstat: target blkg_rwstat - * @op: REQ_OP - * @op_flags: rq_flag_bits + * @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, - int op, int op_flags, uint64_t val) + unsigned int op, uint64_t val) { struct percpu_counter *cnt; @@ -600,7 +599,7 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); - if (op_flags & REQ_SYNC) + if (op & REQ_SYNC) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; @@ -705,9 +704,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf, + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } rcu_read_unlock(); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ec69a8fe3b29..dca972d67548 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -88,24 +88,6 @@ struct bio { struct bio_vec bi_inline_vecs[0]; }; -#define BIO_OP_SHIFT (8 * FIELD_SIZEOF(struct bio, bi_opf) - REQ_OP_BITS) -#define bio_flags(bio) ((bio)->bi_opf & ((1 << BIO_OP_SHIFT) - 1)) -#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) - -#define bio_set_op_attrs(bio, op, op_flags) do { \ - if (__builtin_constant_p(op)) \ - BUILD_BUG_ON((op) + 0U >= (1U << REQ_OP_BITS)); \ - else \ - WARN_ON_ONCE((op) + 0U >= (1U << REQ_OP_BITS)); \ - if (__builtin_constant_p(op_flags)) \ - BUILD_BUG_ON((op_flags) + 0U >= (1U << BIO_OP_SHIFT)); \ - else \ - WARN_ON_ONCE((op_flags) + 0U >= (1U << BIO_OP_SHIFT)); \ - (bio)->bi_opf = bio_flags(bio); \ - (bio)->bi_opf |= (((op) + 0U) << BIO_OP_SHIFT); \ - (bio)->bi_opf |= (op_flags); \ -} while (0) - #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) /* @@ -147,26 +129,40 @@ struct bio { #endif /* CONFIG_BLOCK */ /* - * Request flags. For use in the cmd_flags field of struct request, and in - * bi_opf of struct bio. Note that some flags are only valid in either one. + * Operations and flags common to the bio and request structures. + * We use 8 bits for encoding the operation, and the remaining 24 for flags. */ -enum rq_flag_bits { - /* common flags */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ +#define REQ_OP_BITS 8 +#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) +#define REQ_FLAG_BITS 24 + +enum req_opf { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ + REQ_OP_ZONE_REPORT, /* Get zone information */ + REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ + + REQ_OP_LAST, +}; + +enum req_flag_bits { + __REQ_FAILFAST_DEV = /* no driver retries of device errors */ + REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ - __REQ_NOMERGE, /* don't touch this for merging */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ - __REQ_NR_BITS, /* stops here */ }; @@ -176,37 +172,32 @@ enum rq_flag_bits { #define REQ_SYNC (1ULL << __REQ_SYNC) #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) +#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) #define REQ_NOIDLE (1ULL << __REQ_NOIDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) +#define REQ_FUA (1ULL << __REQ_FUA) +#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) +#define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -#define REQ_COMMON_MASK \ - (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE | REQ_RAHEAD) -#define REQ_CLONE_MASK REQ_COMMON_MASK -/* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) -#define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_FUA (1ULL << __REQ_FUA) -#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) +#define bio_op(bio) \ + ((bio)->bi_opf & REQ_OP_MASK) +#define req_op(req) \ + ((req)->cmd_flags & REQ_OP_MASK) -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ - REQ_OP_ZONE_REPORT, /* Get zone information */ - REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ -}; +/* obsolete, don't use in new code */ +#define bio_set_op_attrs(bio, op, op_flags) \ + ((bio)->bi_opf |= (op | op_flags)) -#define REQ_OP_BITS 3 +static inline bool op_is_sync(unsigned int op) +{ + return (op & REQ_OP_MASK) == REQ_OP_READ || (op & REQ_SYNC); +} typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b4415feac679..8396da2bb698 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -142,7 +142,7 @@ struct request { int cpu; unsigned cmd_type; - u64 cmd_flags; + unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; unsigned long atomic_flags; @@ -244,20 +244,6 @@ struct request { struct request *next_rq; }; -#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS) -#define req_op(req) ((req)->cmd_flags >> REQ_OP_SHIFT) - -#define req_set_op(req, op) do { \ - WARN_ON(op >= (1 << REQ_OP_BITS)); \ - (req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1); \ - (req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT); \ -} while (0) - -#define req_set_op_attrs(req, op, flags) do { \ - req_set_op(req, op); \ - (req)->cmd_flags |= flags; \ -} while (0) - static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -741,17 +727,9 @@ static inline unsigned int blk_queue_zone_size(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } -/* - * We regard a request as sync, if either a read or a sync write - */ -static inline bool rw_is_sync(int op, unsigned int rw_flags) -{ - return op == REQ_OP_READ || (rw_flags & REQ_SYNC); -} - static inline bool rq_is_sync(struct request *rq) { - return rw_is_sync(req_op(rq), rq->cmd_flags); + return op_is_sync(rq->cmd_flags); } static inline bool blk_rl_full(struct request_list *rl, bool sync) diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cceb72f9e29f..e417f080219a 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -118,7 +118,7 @@ static inline int blk_cmd_buf_len(struct request *rq) } extern void blk_dump_cmd(char *buf, struct request *rq); -extern void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes); +extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */ diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index b91b023deffb..a52c6580cc9a 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -58,7 +58,7 @@ struct dm_io_notify { struct dm_io_client; struct dm_io_request { int bi_op; /* REQ_OP */ - int bi_op_flags; /* rq_flag_bits */ + int bi_op_flags; /* req_flag_bits */ struct dm_io_memory mem; /* Memory to use for io */ struct dm_io_notify notify; /* Synchronous if notify.fn is NULL */ struct dm_io_client *client; /* Client memory handler */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index e7f358d2e5fc..f219c9aed360 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -30,7 +30,7 @@ typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_may_queue_fn) (struct request_queue *, int, int); +typedef int (elevator_may_queue_fn) (struct request_queue *, unsigned int); typedef void (elevator_init_icq_fn) (struct io_cq *); typedef void (elevator_exit_icq_fn) (struct io_cq *); @@ -139,7 +139,7 @@ extern struct request *elv_former_request(struct request_queue *, struct request extern struct request *elv_latter_request(struct request_queue *, struct request *); extern int elv_register_queue(struct request_queue *q); extern void elv_unregister_queue(struct request_queue *q); -extern int elv_may_queue(struct request_queue *, int, int); +extern int elv_may_queue(struct request_queue *, unsigned int); extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *q, struct request *rq, struct bio *bio, gfp_t gfp_mask); -- cgit From 87374179c535a98337569904727aa02f960fe79e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:15 +0200 Subject: block: add a proper block layer data direction encoding Currently the block layer op_is_write, bio_data_dir and rq_data_dir helper treat every operation that is not a READ as a data out operation. This worked surprisingly long, but the new REQ_OP_ZONE_REPORT operation actually adds a second operation that reads data from the device. Surprisingly nothing critical relied on this direction, but this might be a good opportunity to properly fix this issue up. We take a little inspiration and use the least significant bit of the operation number to encode the data direction, which just requires us to renumber the operations to fix this scheme. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 38 ++++++++++++++++++++++++++++++-------- include/linux/fs.h | 5 ----- 2 files changed, 30 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dca972d67548..3fa62cabe8d2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -131,20 +131,37 @@ struct bio { /* * Operations and flags common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. + * + * The least significant bit of the operation number indicates the data + * transfer direction: + * + * - if the least significant bit is set transfers are TO the device + * - if the least significant bit is not set transfers are FROM the device + * + * If a operation does not transfer data the least significant bit has no + * meaning. */ #define REQ_OP_BITS 8 #define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) #define REQ_FLAG_BITS 24 enum req_opf { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ - REQ_OP_ZONE_REPORT, /* Get zone information */ - REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ + /* read sectors from the device */ + REQ_OP_READ = 0, + /* write sectors to the device */ + REQ_OP_WRITE = 1, + /* flush the volatile write cache */ + REQ_OP_FLUSH = 2, + /* discard sectors */ + REQ_OP_DISCARD = 3, + /* get zone information */ + REQ_OP_ZONE_REPORT = 4, + /* securely erase sectors */ + REQ_OP_SECURE_ERASE = 5, + /* seset a zone write pointer */ + REQ_OP_ZONE_RESET = 6, + /* write the same sector many times */ + REQ_OP_WRITE_SAME = 7, REQ_OP_LAST, }; @@ -194,6 +211,11 @@ enum req_flag_bits { #define bio_set_op_attrs(bio, op, op_flags) \ ((bio)->bi_opf |= (op | op_flags)) +static inline bool op_is_write(unsigned int op) +{ + return (op & 1); +} + static inline bool op_is_sync(unsigned int op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & REQ_SYNC); diff --git a/include/linux/fs.h b/include/linux/fs.h index 16d2b6e874d6..e3e878f12b25 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2499,11 +2499,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -static inline bool op_is_write(unsigned int op) -{ - return op == REQ_OP_READ ? false : true; -} - /* * return data direction, READ or WRITE */ -- cgit From 42412c3aae5d8ea57a46b8ff86bb67bc1a270d9c Mon Sep 17 00:00:00 2001 From: Silvio Fricke Date: Fri, 28 Oct 2016 10:14:09 +0200 Subject: workqueue: kerneldocify workqueue_attrs Only formating changes. Signed-off-by: Silvio Fricke Acked-by: Tejun Heo Signed-off-by: Jonathan Corbet --- include/linux/workqueue.h | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index fc6e22186405..d4f16cf6281c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -119,18 +119,30 @@ struct delayed_work { int cpu; }; -/* - * A struct for workqueue attributes. This can be used to change - * attributes of an unbound workqueue. +/** + * struct workqueue_attrs - A struct for workqueue attributes. * - * Unlike other fields, ->no_numa isn't a property of a worker_pool. It - * only modifies how apply_workqueue_attrs() select pools and thus doesn't - * participate in pool hash calculations or equality comparisons. + * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { - int nice; /* nice level */ - cpumask_var_t cpumask; /* allowed CPUs */ - bool no_numa; /* disable NUMA affinity */ + /** + * @nice: nice level + */ + int nice; + + /** + * @cpumask: allowed CPUs + */ + cpumask_var_t cpumask; + + /** + * @no_numa: disable NUMA affinity + * + * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It + * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus + * doesn't participate in pool hash calculations or equality comparisons. + */ + bool no_numa; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) @@ -272,7 +284,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } /* * Workqueue flags and constants. For details, please refer to - * Documentation/workqueue.txt. + * Documentation/core-api/workqueue.rst. */ enum { WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ @@ -370,7 +382,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * @args...: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed - * information on WQ_* flags, please refer to Documentation/workqueue.txt. + * information on WQ_* flags, please refer to + * Documentation/core-api/workqueue.rst. * * The __lock_name macro dance is to guarantee that single lock_class_key * doesn't end up with different namesm, which isn't allowed by lockdep. -- cgit From b917783c7b350518f8c5d88bb5848aa8064408a6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 26 Oct 2016 18:49:46 +0200 Subject: flow_dissector: __skb_get_hash_symmetric arg can be const Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 601258f6e621..663fda2887f7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1086,7 +1086,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) } void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(struct sk_buff *skb); +u32 __skb_get_hash_symmetric(const struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen); -- cgit From 5579e1519bad43b874922dbe87c74fdcbd97a7db Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Wed, 31 Aug 2016 05:17:54 +0000 Subject: net/mlx5: Update struct mlx5_ifc_xrqc_bits Update struct mlx5_ifc_xrqc_bits according to last specification Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6045d4d58065..12f72e45a3f0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2844,7 +2844,7 @@ struct mlx5_ifc_xrqc_bits { struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; - u8 reserved_at_180[0x200]; + u8 reserved_at_180[0x880]; struct mlx5_ifc_wq_bits wq; }; -- cgit From dd257efb1e0f8875ed7e42b88837a8dada0d0e41 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Wed, 31 Aug 2016 05:29:58 +0000 Subject: net/mlx5: Ensure SRQ physical address structure endianness SRQ physical address structure field should be in big-endian format. Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Leon Romanovsky --- include/linux/mlx5/srq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 33c97dc900f8..1cde0fd53f90 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -55,7 +55,7 @@ struct mlx5_srq_attr { u32 lwm; u32 user_index; u64 db_record; - u64 *pas; + __be64 *pas; }; struct mlx5_core_dev; -- cgit From 813f854053c26204e2723c498def4c7870dcc7f4 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 11 Aug 2016 11:21:39 +0300 Subject: net/mlx5: Introduce TSAR manipulation firmware commands TSAR (stands for Transmit Scheduling ARbiter) is a hardware component that is responsible for selecting the next entity to serve on the transmit path. The arbitration defines the QoS policy between the agents connected to the TSAR. The TSAR is a consist two main features: 1) BW Allocation between agents: The TSAR implements a defecit weighted round robin between the agents. Each agent attached to the TSAR is assigned with a weight and it is awarded transmission tokens according to this weight. 2) Rate limer per agent: Each agent attached to the TSAR is (optionally) assigned with a rate limit. TSAR will not allow scheduling for an agent exceeding its defined rate limit. In this patch we implement the API of manipulating the TSAR. Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 199 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 195 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 12f72e45a3f0..2632cb2caf10 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -145,6 +145,12 @@ enum { MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, MLX5_CMD_OP_SET_RATE_LIMIT = 0x780, MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, + MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782, + MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783, + MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT = 0x784, + MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT = 0x785, + MLX5_CMD_OP_CREATE_QOS_PARA_VPORT = 0x786, + MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT = 0x787, MLX5_CMD_OP_ALLOC_PD = 0x800, MLX5_CMD_OP_DEALLOC_PD = 0x801, MLX5_CMD_OP_ALLOC_UAR = 0x802, @@ -537,13 +543,27 @@ struct mlx5_ifc_e_switch_cap_bits { struct mlx5_ifc_qos_cap_bits { u8 packet_pacing[0x1]; - u8 reserved_0[0x1f]; - u8 reserved_1[0x20]; + u8 esw_scheduling[0x1]; + u8 reserved_at_2[0x1e]; + + u8 reserved_at_20[0x20]; + u8 packet_pacing_max_rate[0x20]; + u8 packet_pacing_min_rate[0x20]; - u8 reserved_2[0x10]; + + u8 reserved_at_80[0x10]; u8 packet_pacing_rate_table_size[0x10]; - u8 reserved_3[0x760]; + + u8 esw_element_type[0x10]; + u8 esw_tsar_type[0x10]; + + u8 reserved_at_c0[0x10]; + u8 max_qos_para_vport[0x10]; + + u8 max_tsar_bw_share[0x20]; + + u8 reserved_at_100[0x700]; }; struct mlx5_ifc_per_protocol_networking_offload_caps_bits { @@ -2333,6 +2353,30 @@ struct mlx5_ifc_sqc_bits { struct mlx5_ifc_wq_bits wq; }; +enum { + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR = 0x0, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, + SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, +}; + +struct mlx5_ifc_scheduling_context_bits { + u8 element_type[0x8]; + u8 reserved_at_8[0x18]; + + u8 element_attributes[0x20]; + + u8 parent_element_id[0x20]; + + u8 reserved_at_60[0x40]; + + u8 bw_share[0x20]; + + u8 max_average_bw[0x20]; + + u8 reserved_at_e0[0x120]; +}; + struct mlx5_ifc_rqtc_bits { u8 reserved_at_0[0xa0]; @@ -2920,6 +2964,29 @@ struct mlx5_ifc_register_loopback_control_bits { u8 reserved_at_20[0x60]; }; +struct mlx5_ifc_vport_tc_element_bits { + u8 traffic_class[0x4]; + u8 reserved_at_4[0xc]; + u8 vport_number[0x10]; +}; + +struct mlx5_ifc_vport_element_bits { + u8 reserved_at_0[0x10]; + u8 vport_number[0x10]; +}; + +enum { + TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0, + TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1, + TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, +}; + +struct mlx5_ifc_tsar_element_bits { + u8 reserved_at_0[0x8]; + u8 tsar_type[0x8]; + u8 reserved_at_10[0x10]; +}; + struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -3540,6 +3607,39 @@ struct mlx5_ifc_query_special_contexts_in_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_query_scheduling_element_out_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0xc0]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + +enum { + SCHEDULING_HIERARCHY_E_SWITCH = 0x2, +}; + +struct mlx5_ifc_query_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_query_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4725,6 +4825,43 @@ struct mlx5_ifc_modify_sq_in_bits { struct mlx5_ifc_sqc_bits ctx; }; +struct mlx5_ifc_modify_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1c0]; +}; + +enum { + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE = 0x1, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW = 0x2, +}; + +struct mlx5_ifc_modify_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x20]; + + u8 modify_bitmask[0x20]; + + u8 reserved_at_c0[0x40]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + struct mlx5_ifc_modify_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5390,6 +5527,30 @@ struct mlx5_ifc_destroy_sq_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_destroy_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1c0]; +}; + +struct mlx5_ifc_destroy_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_destroy_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6017,6 +6178,36 @@ struct mlx5_ifc_create_sq_in_bits { struct mlx5_ifc_sqc_bits ctx; }; +struct mlx5_ifc_create_scheduling_element_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 scheduling_element_id[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_create_scheduling_element_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 scheduling_hierarchy[0x8]; + u8 reserved_at_48[0x18]; + + u8 reserved_at_60[0xa0]; + + struct mlx5_ifc_scheduling_context_bits scheduling_context; + + u8 reserved_at_300[0x100]; +}; + struct mlx5_ifc_create_rqt_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit From 74491de937125d0c98c9b9c9208b4105717a3caa Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 31 Aug 2016 11:24:25 +0000 Subject: net/mlx5: Add multi dest support Currently when calling mlx5_add_flow_rule we accept only one flow destination, this commit allows to pass multiple destinations. This change forces us to change the return structure to a more flexible one. We introduce a flow handle (struct mlx5_flow_handle), it holds internally the number for rules created and holds an array where each cell points the to a flow rule. From the consumers (of mlx5_add_flow_rule) point of view this change is only cosmetic and requires only to change the type of the returned value they store. From the core point of view, we now need to use a loop when allocating and deleting rules (e.g given to us a flow handler). Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 93ebc5e21334..0dcd287f4bd0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -69,8 +69,8 @@ enum mlx5_flow_namespace_type { struct mlx5_flow_table; struct mlx5_flow_group; -struct mlx5_flow_rule; struct mlx5_flow_namespace; +struct mlx5_flow_handle; struct mlx5_flow_spec { u8 match_criteria_enable; @@ -127,18 +127,20 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); /* Single destination per rule. * Group ID is implied by the match criteria. */ -struct mlx5_flow_rule * -mlx5_add_flow_rule(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest); -void mlx5_del_flow_rule(struct mlx5_flow_rule *fr); - -int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, - struct mlx5_flow_destination *dest); - -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule); +struct mlx5_flow_handle * +mlx5_add_flow_rules(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest, + int dest_num); +void mlx5_del_flow_rules(struct mlx5_flow_handle *fr); + +int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, + struct mlx5_flow_destination *new_dest, + struct mlx5_flow_destination *old_dest); + +struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, -- cgit From e02737d5b82640497637d18428e2793bb7f02881 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 28 Oct 2016 15:04:46 -0700 Subject: x86/intel_rdt: Add tasks files The root directory all subdirectories are automatically populated with a read/write (mode 0644) file named "tasks". When read it will show all the task IDs assigned to the resource group. Tasks can be added (one at a time) to a group by writing the task ID to the file. E.g. Membership in a resource group is indicated by a new field in the task_struct "int closid" which holds the CLOSID for each task. The default resource group uses CLOSID=0 which means that all existing tasks when the resctrl file system is mounted belong to the default group. If a group is removed, tasks which are members of that group are moved to the default group. Signed-off-by: Fenghua Yu Cc: "Ravi V Shankar" Cc: "Tony Luck" Cc: "Shaohua Li" Cc: "Sai Prakhya" Cc: "Peter Zijlstra" Cc: "Stephane Eranian" Cc: "Dave Hansen" Cc: "David Carrillo-Cisneros" Cc: "Nilay Vaish" Cc: "Vikas Shivappa" Cc: "Ingo Molnar" Cc: "Borislav Petkov" Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1477692289-37412-8-git-send-email-fenghua.yu@intel.com Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..c8f4152e7265 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1791,6 +1791,9 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock */ struct list_head cg_list; #endif +#ifdef CONFIG_INTEL_RDT_A + int closid; +#endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT -- cgit From 766763dbdc1dca11deabdb00077a1c19e2803f0a Mon Sep 17 00:00:00 2001 From: Alexandre Bailon Date: Thu, 27 Oct 2016 17:32:36 +0200 Subject: ARM: davinci: da8xx: Remove duplicated defines Some macro for DA8xx CFGCHIP are defined in usb-davinci.h, but da8xx-cfgchip.h intend to replace them. Remove duplicated defines between da8xx-cfgchip.h and usb-davinci.h Signed-off-by: Alexandre Bailon Signed-off-by: Sekhar Nori --- include/linux/platform_data/usb-davinci.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/usb-davinci.h b/include/linux/platform_data/usb-davinci.h index e0bc4abe69c2..0926e99f2e8f 100644 --- a/include/linux/platform_data/usb-davinci.h +++ b/include/linux/platform_data/usb-davinci.h @@ -11,29 +11,6 @@ #ifndef __ASM_ARCH_USB_H #define __ASM_ARCH_USB_H -/* DA8xx CFGCHIP2 (USB 2.0 PHY Control) register bits */ -#define CFGCHIP2_PHYCLKGD (1 << 17) -#define CFGCHIP2_VBUSSENSE (1 << 16) -#define CFGCHIP2_RESET (1 << 15) -#define CFGCHIP2_OTGMODE (3 << 13) -#define CFGCHIP2_NO_OVERRIDE (0 << 13) -#define CFGCHIP2_FORCE_HOST (1 << 13) -#define CFGCHIP2_FORCE_DEVICE (2 << 13) -#define CFGCHIP2_FORCE_HOST_VBUS_LOW (3 << 13) -#define CFGCHIP2_USB1PHYCLKMUX (1 << 12) -#define CFGCHIP2_USB2PHYCLKMUX (1 << 11) -#define CFGCHIP2_PHYPWRDN (1 << 10) -#define CFGCHIP2_OTGPWRDN (1 << 9) -#define CFGCHIP2_DATPOL (1 << 8) -#define CFGCHIP2_USB1SUSPENDM (1 << 7) -#define CFGCHIP2_PHY_PLLON (1 << 6) /* override PLL suspend */ -#define CFGCHIP2_SESENDEN (1 << 5) /* Vsess_end comparator */ -#define CFGCHIP2_VBDTCTEN (1 << 4) /* Vbus comparator */ -#define CFGCHIP2_REFFREQ (0xf << 0) -#define CFGCHIP2_REFFREQ_12MHZ (1 << 0) -#define CFGCHIP2_REFFREQ_24MHZ (2 << 0) -#define CFGCHIP2_REFFREQ_48MHZ (3 << 0) - struct da8xx_ohci_root_hub; typedef void (*da8xx_ocic_handler_t)(struct da8xx_ohci_root_hub *hub, -- cgit From c62cce2caee558e18aa05c01c2fd3b40f07174f2 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 24 Oct 2016 18:29:13 -0700 Subject: net: add an ioctl to get a socket network namespace Each socket operates in a network namespace where it has been created, so if we want to dump and restore a socket, we have to know its network namespace. We have a socket_diag to get information about sockets, it doesn't report sockets which are not bound or connected. This patch introduces a new socket ioctl, which is called SIOCGSKNS and used to get a file descriptor for a socket network namespace. A task must have CAP_NET_ADMIN in a target network namespace to use this ioctl. Cc: "David S. Miller" Cc: Eric W. Biederman Signed-off-by: Andrei Vagin Signed-off-by: David S. Miller --- include/linux/proc_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b97bf2ef996e..368c7ad06ae5 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -82,4 +82,8 @@ static inline struct proc_dir_entry *proc_net_mkdir( return proc_mkdir_data(name, 0, parent, net); } +struct ns_common; +int open_related_ns(struct ns_common *ns, + struct ns_common *(*get_ns)(struct ns_common *ns)); + #endif /* _LINUX_PROC_FS_H */ -- cgit From 9ed9895370aedd6032af2a9181c62c394d08223b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 30 Oct 2016 17:32:16 +0100 Subject: driver core: Functional dependencies tracking support Currently, there is a problem with taking functional dependencies between devices into account. What I mean by a "functional dependency" is when the driver of device B needs device A to be functional and (generally) its driver to be present in order to work properly. This has certain consequences for power management (suspend/resume and runtime PM ordering) and shutdown ordering of these devices. In general, it also implies that the driver of A needs to be working for B to be probed successfully and it cannot be unbound from the device before the B's driver. Support for representing those functional dependencies between devices is added here to allow the driver core to track them and act on them in certain cases where applicable. The argument for doing that in the driver core is that there are quite a few distinct use cases involving device dependencies, they are relatively hard to get right in a driver (if one wants to address all of them properly) and it only gets worse if multiplied by the number of drivers potentially needing to do it. Morever, at least one case (asynchronous system suspend/resume) cannot be handled in a single driver at all, because it requires the driver of A to wait for B to suspend (during system suspend) and the driver of B to wait for A to resume (during system resume). For this reason, represent dependencies between devices as "links", with the help of struct device_link objects each containing pointers to the "linked" devices, a list node for each of them, status information, flags, and an RCU head for synchronization. Also add two new list heads, representing the lists of links to the devices that depend on the given one (consumers) and to the devices depended on by it (suppliers), and a "driver presence status" field (needed for figuring out initial states of device links) to struct device. The entire data structure consisting of all of the lists of link objects for all devices is protected by a mutex (for link object addition/removal and for list walks during device driver probing and removal) and by SRCU (for list walking in other case that will be introduced by subsequent change sets). If CONFIG_SRCU is not selected, however, an rwsem is used for protecting the entire data structure. In addition, each link object has an internal status field whose value reflects whether or not drivers are bound to the devices pointed to by the link or probing/removal of their drivers is in progress etc. That field is only modified under the device links mutex, but it may be read outside of it in some cases (introduced by subsequent change sets), so modifications of it are annotated with WRITE_ONCE(). New links are added by calling device_link_add() which takes three arguments: pointers to the devices in question and flags. In particular, if DL_FLAG_STATELESS is set in the flags, the link status is not to be taken into account for this link and the driver core will not manage it. In turn, if DL_FLAG_AUTOREMOVE is set in the flags, the driver core will remove the link automatically when the consumer device driver unbinds from it. One of the actions carried out by device_link_add() is to reorder the lists used for device shutdown and system suspend/resume to put the consumer device along with all of its children and all of its consumers (and so on, recursively) to the ends of those lists in order to ensure the right ordering between all of the supplier and consumer devices. For this reason, it is not possible to create a link between two devices if the would-be supplier device already depends on the would-be consumer device as either a direct descendant of it or a consumer of one of its direct descendants or one of its consumers and so on. There are two types of link objects, persistent and non-persistent. The persistent ones stay around until one of the target devices is deleted, while the non-persistent ones are removed automatically when the consumer driver unbinds from its device (ie. they are assumed to be valid only as long as the consumer device has a driver bound to it). Persistent links are created by default and non-persistent links are created when the DL_FLAG_AUTOREMOVE flag is passed to device_link_add(). Both persistent and non-persistent device links can be deleted with an explicit call to device_link_del(). Links created without the DL_FLAG_STATELESS flag set are managed by the driver core using a simple state machine. There are 5 states each link can be in: DORMANT (unused), AVAILABLE (the supplier driver is present and functional), CONSUMER_PROBE (the consumer driver is probing), ACTIVE (both supplier and consumer drivers are present and functional), and SUPPLIER_UNBIND (the supplier driver is unbinding). The driver core updates the link state automatically depending on what happens to the linked devices and for each link state specific actions are taken in addition to that. For example, if the supplier driver unbinds from its device, the driver core will also unbind the drivers of all of its consumers automatically under the assumption that they cannot function properly without the supplier. Analogously, the driver core will only allow the consumer driver to bind to its device if the supplier driver is present and functional (ie. the link is in the AVAILABLE state). If that's not the case, it will rely on the existing deferred probing mechanism to wait for the supplier driver to become available. Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm.h | 1 + 2 files changed, 81 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index bc41e87a969b..9cae2feaf5cb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -707,6 +707,81 @@ struct device_dma_parameters { unsigned long segment_boundary_mask; }; +/** + * enum device_link_state - Device link states. + * @DL_STATE_NONE: The presence of the drivers is not being tracked. + * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. + * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. + * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). + * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. + * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. + */ +enum device_link_state { + DL_STATE_NONE = -1, + DL_STATE_DORMANT = 0, + DL_STATE_AVAILABLE, + DL_STATE_CONSUMER_PROBE, + DL_STATE_ACTIVE, + DL_STATE_SUPPLIER_UNBIND, +}; + +/* + * Device link flags. + * + * STATELESS: The core won't track the presence of supplier/consumer drivers. + * AUTOREMOVE: Remove this link automatically on consumer driver unbind. + */ +#define DL_FLAG_STATELESS BIT(0) +#define DL_FLAG_AUTOREMOVE BIT(1) + +/** + * struct device_link - Device link representation. + * @supplier: The device on the supplier end of the link. + * @s_node: Hook to the supplier device's list of links to consumers. + * @consumer: The device on the consumer end of the link. + * @c_node: Hook to the consumer device's list of links to suppliers. + * @status: The state of the link (with respect to the presence of drivers). + * @flags: Link flags. + * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + */ +struct device_link { + struct device *supplier; + struct list_head s_node; + struct device *consumer; + struct list_head c_node; + enum device_link_state status; + u32 flags; +#ifdef CONFIG_SRCU + struct rcu_head rcu_head; +#endif +}; + +/** + * enum dl_dev_state - Device driver presence tracking information. + * @DL_DEV_NO_DRIVER: There is no driver attached to the device. + * @DL_DEV_PROBING: A driver is probing. + * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. + * @DL_DEV_UNBINDING: The driver is unbinding from the device. + */ +enum dl_dev_state { + DL_DEV_NO_DRIVER = 0, + DL_DEV_PROBING, + DL_DEV_DRIVER_BOUND, + DL_DEV_UNBINDING, +}; + +/** + * struct dev_links_info - Device data related to device links. + * @suppliers: List of links to supplier devices. + * @consumers: List of links to consumer devices. + * @status: Driver status information. + */ +struct dev_links_info { + struct list_head suppliers; + struct list_head consumers; + enum dl_dev_state status; +}; + /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. @@ -799,6 +874,7 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set/get_drvdata */ + struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; @@ -1116,6 +1192,10 @@ extern void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ extern const char *dev_driver_string(const struct device *dev); +/* Device links interface. */ +struct device_link *device_link_add(struct device *consumer, + struct device *supplier, u32 flags); +void device_link_del(struct device_link *link); #ifdef CONFIG_PRINTK diff --git a/include/linux/pm.h b/include/linux/pm.h index 06eb353182ab..721a70241fcd 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -559,6 +559,7 @@ struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; unsigned int async_suspend:1; + bool in_dpm_list:1; /* Owned by the PM core */ bool is_prepared:1; /* Owned by the PM core */ bool is_suspended:1; /* Ditto */ bool is_noirq_suspended:1; -- cgit From 21d5c57b3726166421251e94dabab047baaf8ce4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 30 Oct 2016 17:32:31 +0100 Subject: PM / runtime: Use device links Modify the runtime PM framework to use device links to ensure that supplier devices will not be suspended if any of their consumer devices are active. The idea is to reference count suppliers on the consumer's resume and drop references to them on its suspend. The information on whether or not the supplier has been reference counted by the consumer's (runtime) resume is stored in a new field (rpm_active) in the link object for each link. It may be necessary to clean up those references when the supplier is unbinding and that's why the links whose status is DEVICE_LINK_SUPPLIER_UNBIND are skipped by the runtime suspend and resume code. The above means that if the consumer device is probed in the runtime-active state, the supplier has to be resumed and reference counted by device_link_add() so the code works as expected on its (runtime) suspend. There is a new flag, DEVICE_LINK_RPM_ACTIVE, to tell device_link_add() about that (in which case the caller is responsible for making sure that the consumer really will be runtime-active when runtime PM is enabled for it). The other new link flag, DEVICE_LINK_PM_RUNTIME, tells the core whether or not the link should be used for runtime PM at all. Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 6 ++++++ include/linux/pm_runtime.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9cae2feaf5cb..49f453892ca5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -730,9 +730,13 @@ enum device_link_state { * * STATELESS: The core won't track the presence of supplier/consumer drivers. * AUTOREMOVE: Remove this link automatically on consumer driver unbind. + * PM_RUNTIME: If set, the runtime PM framework will use this link. + * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE BIT(1) +#define DL_FLAG_PM_RUNTIME BIT(2) +#define DL_FLAG_RPM_ACTIVE BIT(3) /** * struct device_link - Device link representation. @@ -742,6 +746,7 @@ enum device_link_state { * @c_node: Hook to the consumer device's list of links to suppliers. * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. + * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. */ struct device_link { @@ -751,6 +756,7 @@ struct device_link { struct list_head c_node; enum device_link_state status; u32 flags; + bool rpm_active; #ifdef CONFIG_SRCU struct rcu_head rcu_head; #endif diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2e14d2667b6c..c2ee87138e4a 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -55,6 +55,9 @@ extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); +extern void pm_runtime_clean_up_links(struct device *dev); +extern void pm_runtime_get_suppliers(struct device *dev); +extern void pm_runtime_put_suppliers(struct device *dev); static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { @@ -186,6 +189,9 @@ static inline unsigned long pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} +static inline void pm_runtime_clean_up_links(struct device *dev) {} +static inline void pm_runtime_get_suppliers(struct device *dev) {} +static inline void pm_runtime_put_suppliers(struct device *dev) {} #endif /* !CONFIG_PM */ -- cgit From baa8809f60971d10220dfe79248f54b2b265f003 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 30 Oct 2016 17:32:43 +0100 Subject: PM / runtime: Optimize the use of device links If the device has no links to suppliers that should be used for runtime PM (links with DEVICE_LINK_PM_RUNTIME set), there is no reason to walk the list of suppliers for that device during runtime suspend and resume. Add a simple mechanism to detect that case and possibly avoid the extra unnecessary overhead. Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- include/linux/pm.h | 1 + include/linux/pm_runtime.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 721a70241fcd..ccfe00ecc7e6 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -597,6 +597,7 @@ struct dev_pm_info { unsigned int use_autosuspend:1; unsigned int timer_autosuspends:1; unsigned int memalloc_noio:1; + unsigned int links_count; enum rpm_request request; enum rpm_status runtime_status; int runtime_error; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index c2ee87138e4a..73814877537d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -58,6 +58,8 @@ extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_clean_up_links(struct device *dev); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); +extern void pm_runtime_new_link(struct device *dev); +extern void pm_runtime_drop_link(struct device *dev); static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { @@ -192,6 +194,8 @@ static inline void pm_runtime_set_memalloc_noio(struct device *dev, static inline void pm_runtime_clean_up_links(struct device *dev) {} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} +static inline void pm_runtime_new_link(struct device *dev) {} +static inline void pm_runtime_drop_link(struct device *dev) {} #endif /* !CONFIG_PM */ -- cgit From 9cf1f6a8c4cbb7836b838b51b3b02ddf32c6c6a0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:43:20 -0400 Subject: net: Move functions for configuring traffic classes out of inline headers The functions for configuring the traffic class to queue mappings have other effects that need to be addressed. Instead of trying to export a bunch of new functions just relocate the functions so that we can instrument them directly with the functionality they will need. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 31 +++---------------------------- 1 file changed, 3 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20ce8df115ac..e05ab3bd48d2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1920,34 +1920,9 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) return 0; } -static inline -void netdev_reset_tc(struct net_device *dev) -{ - dev->num_tc = 0; - memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); - memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); -} - -static inline -int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) -{ - if (tc >= dev->num_tc) - return -EINVAL; - - dev->tc_to_txq[tc].count = count; - dev->tc_to_txq[tc].offset = offset; - return 0; -} - -static inline -int netdev_set_num_tc(struct net_device *dev, u8 num_tc) -{ - if (num_tc > TC_MAX_QUEUE) - return -EINVAL; - - dev->num_tc = num_tc; - return 0; -} +void netdev_reset_tc(struct net_device *dev); +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); +int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline int netdev_get_num_tc(struct net_device *dev) -- cgit From 8d059b0f6f5b1d3acf829454e1087818ad660058 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:43:49 -0400 Subject: net: Add sysfs value to determine queue traffic class Add a sysfs attribute for a Tx queue that allows us to determine the traffic class for a given queue. This will allow us to more easily determine this in the future. It is needed as XPS will take the traffic class for a group of queues into account in order to avoid pulling traffic from one traffic class into another. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e05ab3bd48d2..d91a41860614 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1920,6 +1920,7 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) return 0; } +int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); void netdev_reset_tc(struct net_device *dev); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); -- cgit From 184c449f91fef521042970cca46bd5cdfc0e3a37 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 28 Oct 2016 11:50:13 -0400 Subject: net: Add support for XPS with QoS via traffic classes This patch adds support for setting and using XPS when QoS via traffic classes is enabled. With this change we will factor in the priority and traffic class mapping of the packet and use that information to correctly select the queue. This allows us to define a set of queues for a given traffic class via mqprio and then configure the XPS mapping for those queues so that the traffic flows can avoid head-of-line blocking between the individual CPUs if so desired. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d91a41860614..66fd61c681d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -732,8 +732,8 @@ struct xps_dev_maps { struct rcu_head rcu; struct xps_map __rcu *cpu_map[0]; }; -#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ - (nr_cpu_ids * sizeof(struct xps_map *))) +#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 -- cgit From 0fefbfbaad298162737d5418eb85065879f99b3e Mon Sep 17 00:00:00 2001 From: Sudarsana Kalluru Date: Mon, 31 Oct 2016 07:14:21 +0200 Subject: qed*: Management firmware - notifications and defaults Management firmware is interested in various tidbits about the driver - including the driver state & several configuration related fields [MTU, primtary MAC, etc.]. This adds the necessray logic to update MFW with such configurations, some of which are passed directly via qed while for others APIs are provide so that qede would be able to later configure if needed. This also introduces a new default configuration for MTU which would replace the default inherited by being an ethernet device. Signed-off-by: Sudarsana Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8978a60371f4..5c909cd02764 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -267,6 +267,7 @@ struct qed_dev_info { u8 mf_mode; bool tx_switching; bool rdma_supported; + u16 mtu; }; enum qed_sb_type { @@ -554,6 +555,33 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); + +/** + * @brief update_drv_state - API to inform the change in the driver state. + * + * @param cdev + * @param active + * + */ + int (*update_drv_state)(struct qed_dev *cdev, bool active); + +/** + * @brief update_mac - API to inform the change in the mac address + * + * @param cdev + * @param mac + * + */ + int (*update_mac)(struct qed_dev *cdev, u8 *mac); + +/** + * @brief update_mtu - API to inform the change in the mtu + * + * @param cdev + * @param mtu + * + */ + int (*update_mtu)(struct qed_dev *cdev, u16 mtu); }; #define MASK_FIELD(_name, _value) \ -- cgit From 7a4b21b7d1f0644456501e33d3917c9aaee76a75 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Mon, 31 Oct 2016 07:14:22 +0200 Subject: qed: Add nvram selftest Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5c909cd02764..ffc2d2f5e88f 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -402,6 +402,15 @@ struct qed_selftest_ops { * @return 0 on success, error otherwise. */ int (*selftest_clock)(struct qed_dev *cdev); + +/** + * @brief selftest_nvram - Perform nvram test + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*selftest_nvram) (struct qed_dev *cdev); }; struct qed_common_ops { -- cgit From 14d39648cbfc6289e3f873d30f282b9517ebe860 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Mon, 31 Oct 2016 07:14:23 +0200 Subject: qed*: Add support for WoL Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ffc2d2f5e88f..ea095b4893aa 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -268,6 +268,8 @@ struct qed_dev_info { bool tx_switching; bool rdma_supported; u16 mtu; + + bool wol_support; }; enum qed_sb_type { @@ -591,6 +593,14 @@ struct qed_common_ops { * */ int (*update_mtu)(struct qed_dev *cdev, u16 mtu); + +/** + * @brief update_wol - update of changes in the WoL configuration + * + * @param cdev + * @param enabled - true iff WoL should be enabled. + */ + int (*update_wol) (struct qed_dev *cdev, bool enabled); }; #define MASK_FIELD(_name, _value) \ -- cgit From 2edbff8dcb5da324fd4c4fe953629e4f6ca73c99 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 31 Oct 2016 07:14:27 +0200 Subject: qed: Learn resources from management firmware Currently, each interfaces assumes it receives an equal portion of HW/FW resources, but this is wasteful - different partitions [and specifically, parititions exposing different protocol support] might require different resources. Implement a new resource learning scheme where the information is received directly from the management firmware [which has knowledge of all of the functions and can serve as arbiter]. Signed-off-by: Tomer Tayar Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 15130805d792..9755a3feb52e 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -22,7 +22,7 @@ struct qed_dev_eth_info { u8 num_tc; u8 port_mac[ETH_ALEN]; - u8 num_vlan_filters; + u16 num_vlan_filters; u16 num_mac_filters; /* Legacy VF - this affects the datapath, so qede has to know */ -- cgit From d7c816733d501b59dbdc2483f2cc8e4431fd9160 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Aug 2016 14:42:08 -0700 Subject: list: Split list_add() debug checking into separate function Right now, __list_add() code is repeated either in list.h or in list_debug.c, but the only differences between the two versions are the debug checks. This commit therefore extracts these debug checks into a separate __list_add_valid() function and consolidates __list_add(). Additionally this new __list_add_valid() function will stop list manipulations if a corruption is detected, instead of allowing for further corruption that may lead to even worse conditions. This is slight refactoring of the same hardening done in PaX and Grsecurity. Signed-off-by: Kees Cook Acked-by: Steven Rostedt Signed-off-by: Paul E. McKenney Acked-by: Rik van Riel --- include/linux/list.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 5809e9a2de5b..b6da9b1dce4d 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -28,27 +28,37 @@ static inline void INIT_LIST_HEAD(struct list_head *list) list->prev = list; } +#ifdef CONFIG_DEBUG_LIST +extern bool __list_add_valid(struct list_head *new, + struct list_head *prev, + struct list_head *next); +#else +static inline bool __list_add_valid(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + return true; +} +#endif + /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ -#ifndef CONFIG_DEBUG_LIST static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { + if (!__list_add_valid(new, prev, next)) + return; + next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } -#else -extern void __list_add(struct list_head *new, - struct list_head *prev, - struct list_head *next); -#endif /** * list_add - add a new entry -- cgit From 54acd4397d7e7a725c94101180cd9f38ef701acc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Aug 2016 14:42:09 -0700 Subject: rculist: Consolidate DEBUG_LIST for list_add_rcu() This commit consolidates the debug checking for list_add_rcu() into the new single __list_add_valid() debug function. Notably, this commit fixes the sanity check that was added in commit 17a801f4bfeb ("list_debug: WARN for adding something already in the list"), which wasn't checking RCU-protected lists. Signed-off-by: Kees Cook Acked-by: Steven Rostedt Signed-off-by: Paul E. McKenney Acked-by: Rik van Riel --- include/linux/rculist.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8beb98dcf14f..4f7a9561b8c4 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -45,19 +45,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) * This is only for internal list manipulation where we know * the prev/next entries already! */ -#ifndef CONFIG_DEBUG_LIST static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { + if (!__list_add_valid(new, prev, next)) + return; + new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } -#else -void __list_add_rcu(struct list_head *new, - struct list_head *prev, struct list_head *next); -#endif /** * list_add_rcu - add a new entry to rcu-protected list -- cgit From 0cd340dcb05c4a43742fe156f36737bb2a321bfd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Aug 2016 14:42:10 -0700 Subject: list: Split list_del() debug checking into separate function Similar to the list_add() debug consolidation, this commit consolidates the debug checking performed during CONFIG_DEBUG_LIST into a new __list_del_entry_valid() function, and stops list updates when corruption is found. Refactored from same hardening in PaX and Grsecurity. Signed-off-by: Kees Cook Acked-by: Steven Rostedt Signed-off-by: Paul E. McKenney Acked-by: Rik van Riel --- include/linux/list.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index b6da9b1dce4d..d1039ecaf94f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -32,6 +32,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) extern bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next); +extern bool __list_del_entry_valid(struct list_head *entry); #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, @@ -39,6 +40,10 @@ static inline bool __list_add_valid(struct list_head *new, { return true; } +static inline bool __list_del_entry_valid(struct list_head *entry) +{ + return true; +} #endif /* @@ -106,22 +111,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ -#ifndef CONFIG_DEBUG_LIST static inline void __list_del_entry(struct list_head *entry) { + if (!__list_del_entry_valid(entry)) + return; + __list_del(entry->prev, entry->next); } static inline void list_del(struct list_head *entry) { - __list_del(entry->prev, entry->next); + __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } -#else -extern void __list_del_entry(struct list_head *entry); -extern void list_del(struct list_head *entry); -#endif /** * list_replace - replace old entry by new one -- cgit From de54ebbe26bb371a6f1fbc0593372232f04e3107 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Aug 2016 14:42:11 -0700 Subject: bug: Provide toggle for BUG on data corruption The kernel checks for cases of data structure corruption under some CONFIGs (e.g. CONFIG_DEBUG_LIST). When corruption is detected, some systems may want to BUG() immediately instead of letting the system run with known corruption. Usually these kinds of manipulation primitives can be used by security flaws to gain arbitrary memory write control. This provides a new config CONFIG_BUG_ON_DATA_CORRUPTION and a corresponding macro CHECK_DATA_CORRUPTION for handling these situations. Notably, even if not BUGing, the kernel should not continue processing the corrupted structure. This is inspired by similar hardening by Syed Rameez Mustafa in MSM kernels, and in PaX and Grsecurity, which is likely in response to earlier removal of the BUG calls in commit 924d9addb9b1 ("list debugging: use WARN() instead of BUG()"). Signed-off-by: Kees Cook Acked-by: Steven Rostedt Signed-off-by: Paul E. McKenney Acked-by: Rik van Riel --- include/linux/bug.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bug.h b/include/linux/bug.h index 292d6a10b0c2..baff2e8fc8a8 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -121,4 +121,21 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, } #endif /* CONFIG_GENERIC_BUG */ + +/* + * Since detected data corruption should stop operation on the affected + * structures, this returns false if the corruption condition is found. + */ +#define CHECK_DATA_CORRUPTION(condition, fmt, ...) \ + do { \ + if (unlikely(condition)) { \ + if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \ + pr_err(fmt, ##__VA_ARGS__); \ + BUG(); \ + } else \ + WARN(1, fmt, ##__VA_ARGS__); \ + return false; \ + } \ + } while (0) + #endif /* _LINUX_BUG_H */ -- cgit From 556d299fcb4af8f2e8eacf311c4eee352c746788 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 31 Oct 2016 13:21:02 +0100 Subject: net: pim: add common pimhdr struct and helpers Add the common pimhdr structure and helpers to access it, also cleanup the format of the header file. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/pim.h | 44 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 36 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pim.h b/include/linux/pim.h index e1d756f81348..354235a2691b 100644 --- a/include/linux/pim.h +++ b/include/linux/pim.h @@ -1,6 +1,7 @@ #ifndef __LINUX_PIM_H #define __LINUX_PIM_H +#include #include /* Message types - V1 */ @@ -13,20 +14,47 @@ #define PIM_NULL_REGISTER cpu_to_be32(0x40000000) -static inline bool ipmr_pimsm_enabled(void) -{ - return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2); -} +/* RFC7761, sec 4.9: + * The PIM header common to all PIM messages is: + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |PIM Ver| Type | Reserved | Checksum | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct pimhdr { + __u8 type; + __u8 reserved; + __be16 csum; +}; /* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */ -struct pimreghdr -{ +struct pimreghdr { __u8 type; __u8 reserved; __be16 csum; __be32 flags; }; -struct sk_buff; -extern int pim_rcv_v1(struct sk_buff *); +int pim_rcv_v1(struct sk_buff *skb); + +static inline bool ipmr_pimsm_enabled(void) +{ + return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2); +} + +static inline struct pimhdr *pim_hdr(const struct sk_buff *skb) +{ + return (struct pimhdr *)skb_transport_header(skb); +} + +static inline u8 pim_hdr_version(const struct pimhdr *pimhdr) +{ + return pimhdr->type >> 4; +} + +static inline u8 pim_hdr_type(const struct pimhdr *pimhdr) +{ + return pimhdr->type & 0xf; +} #endif -- cgit From 20bb6ce9879e19eee7539329eaa2408d12b00306 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 31 Oct 2016 13:21:03 +0100 Subject: net: pim: add a helper to check for IPv4 all pim routers address Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/pim.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pim.h b/include/linux/pim.h index 354235a2691b..1b6c0dbba94e 100644 --- a/include/linux/pim.h +++ b/include/linux/pim.h @@ -57,4 +57,10 @@ static inline u8 pim_hdr_type(const struct pimhdr *pimhdr) { return pimhdr->type & 0xf; } + +/* check if the address is 224.0.0.13, RFC7761 sec 4.3.1 */ +static inline bool pim_ipv4_all_pim_routers(__be32 addr) +{ + return addr == htonl(0xE000000D); +} #endif -- cgit From 56245cae19f5ccb371fa63b09bb6b9ce7c0f1266 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 31 Oct 2016 13:21:04 +0100 Subject: net: pim: add all RFC7761 message types Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/pim.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pim.h b/include/linux/pim.h index 1b6c0dbba94e..0e81b2778ae0 100644 --- a/include/linux/pim.h +++ b/include/linux/pim.h @@ -10,7 +10,36 @@ /* Message types - V2 */ #define PIM_VERSION 2 -#define PIM_REGISTER 1 + +/* RFC7761, sec 4.9: + * Type + * Types for specific PIM messages. PIM Types are: + * + * Message Type Destination + * --------------------------------------------------------------------- + * 0 = Hello Multicast to ALL-PIM-ROUTERS + * 1 = Register Unicast to RP + * 2 = Register-Stop Unicast to source of Register + * packet + * 3 = Join/Prune Multicast to ALL-PIM-ROUTERS + * 4 = Bootstrap Multicast to ALL-PIM-ROUTERS + * 5 = Assert Multicast to ALL-PIM-ROUTERS + * 6 = Graft (used in PIM-DM only) Unicast to RPF'(S) + * 7 = Graft-Ack (used in PIM-DM only) Unicast to source of Graft + * packet + * 8 = Candidate-RP-Advertisement Unicast to Domain's BSR + */ +enum { + PIM_TYPE_HELLO, + PIM_TYPE_REGISTER, + PIM_TYPE_REGISTER_STOP, + PIM_TYPE_JOIN_PRUNE, + PIM_TYPE_BOOTSTRAP, + PIM_TYPE_ASSERT, + PIM_TYPE_GRAFT, + PIM_TYPE_GRAFT_ACK, + PIM_TYPE_CANDIDATE_RP_ADV +}; #define PIM_NULL_REGISTER cpu_to_be32(0x40000000) -- cgit From e950604782440c8635d289552bb5db58658fcbe9 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 7 Oct 2016 21:23:12 -0700 Subject: rpmsg: Introduce a driver override mechanism Similar to other subsystems it's useful to provide a mechanism to force a specific driver match on a device, so introduce this. Signed-off-by: Bjorn Andersson --- include/linux/rpmsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 452d393cc8dd..7ad6c205f110 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -64,6 +64,7 @@ struct rpmsg_channel_info { * rpmsg_device - device that belong to the rpmsg bus * @dev: the device struct * @id: device id (used to match between rpmsg drivers and devices) + * @driver_override: driver name to force a match * @src: local address * @dst: destination address * @ept: the rpmsg endpoint of this channel @@ -72,6 +73,7 @@ struct rpmsg_channel_info { struct rpmsg_device { struct device dev; struct rpmsg_device_id id; + char *driver_override; u32 src; u32 dst; struct rpmsg_endpoint *ept; -- cgit From 2c8a57088045a58958372d405586c16e3e12f4e1 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 21 Oct 2016 10:25:37 -0700 Subject: rpmsg: Provide function stubs for API Provide function stubs for the rpmsg API to allow clients to be compile tested without having CONFIG_RPMSG enabled. Signed-off-by: Bjorn Andersson --- include/linux/rpmsg.h | 123 ++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 113 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 7ad6c205f110..18f9e1ae4b7e 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -37,6 +37,7 @@ #include #include +#include #include #include #include @@ -134,6 +135,8 @@ struct rpmsg_driver { int (*callback)(struct rpmsg_device *, void *, int, void *, u32); }; +#if IS_ENABLED(CONFIG_RPMSG) + int register_rpmsg_device(struct rpmsg_device *dev); void unregister_rpmsg_device(struct rpmsg_device *dev); int __register_rpmsg_driver(struct rpmsg_driver *drv, struct module *owner); @@ -143,6 +146,116 @@ struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *, rpmsg_rx_cb_t cb, void *priv, struct rpmsg_channel_info chinfo); +int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len); +int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); +int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, + void *data, int len); + +int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len); +int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); +int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, + void *data, int len); + +#else + +static inline int register_rpmsg_device(struct rpmsg_device *dev) +{ + return -ENXIO; +} + +static inline void unregister_rpmsg_device(struct rpmsg_device *dev) +{ + /* This shouldn't be possible */ + WARN_ON(1); +} + +static inline int __register_rpmsg_driver(struct rpmsg_driver *drv, + struct module *owner) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +static inline void unregister_rpmsg_driver(struct rpmsg_driver *drv) +{ + /* This shouldn't be possible */ + WARN_ON(1); +} + +static inline void rpmsg_destroy_ept(struct rpmsg_endpoint *ept) +{ + /* This shouldn't be possible */ + WARN_ON(1); +} + +static inline struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev, + rpmsg_rx_cb_t cb, + void *priv, + struct rpmsg_channel_info chinfo) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return ERR_PTR(-ENXIO); +} + +static inline int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +static inline int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, + u32 dst) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; + +} + +static inline int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, + u32 dst, void *data, int len) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +static inline int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +static inline int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, + int len, u32 dst) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +static inline int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, + u32 dst, void *data, int len) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + +#endif /* IS_ENABLED(CONFIG_RPMSG) */ + /* use a macro to avoid include chaining to get THIS_MODULE */ #define register_rpmsg_driver(drv) \ __register_rpmsg_driver(drv, THIS_MODULE) @@ -159,14 +272,4 @@ struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *, module_driver(__rpmsg_driver, register_rpmsg_driver, \ unregister_rpmsg_driver) -int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len); -int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); -int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, - void *data, int len); - -int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len); -int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); -int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, - void *data, int len); - #endif /* _LINUX_RPMSG_H */ -- cgit From d71d9ae14a0942fae519d890a743b12679e3d153 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:03 -0600 Subject: blk-cgroup: use op_is_sync to check for synchronous requests Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index ddaf28d0988f..01b62e7bac74 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -599,7 +599,7 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); - if (op & REQ_SYNC) + if (op_is_sync(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; -- cgit From 6f6b29171a192e84b666c816e49d2175afbbb09f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:07 -0600 Subject: block: don't use REQ_SYNC in the READ_SYNC definition Reads are synchronous per definition, don't add another flag for it. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e3e878f12b25..5e0078fceed7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -196,7 +196,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define READ REQ_OP_READ #define WRITE REQ_OP_WRITE -#define READ_SYNC REQ_SYNC +#define READ_SYNC 0 #define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) #define WRITE_ODIRECT REQ_SYNC #define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH) -- cgit From b685d3d65ac791406e0dfd8779cc9b3707fea5a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:08 -0600 Subject: block: treat REQ_FUA and REQ_PREFLUSH as synchronous MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of requiring everyone to specify the REQ_SYNC flag aѕ well. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 +++++++- include/linux/fs.h | 6 +++--- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3fa62cabe8d2..107d23d18096 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -216,9 +216,15 @@ static inline bool op_is_write(unsigned int op) return (op & 1); } +/* + * Reads are always treated as synchronous, as are requests with the FUA or + * PREFLUSH flag. Other operations may be marked as synchronous using the + * REQ_SYNC flag. + */ static inline bool op_is_sync(unsigned int op) { - return (op & REQ_OP_MASK) == REQ_OP_READ || (op & REQ_SYNC); + return (op & REQ_OP_MASK) == REQ_OP_READ || + (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } typedef unsigned int blk_qc_t; diff --git a/include/linux/fs.h b/include/linux/fs.h index 5e0078fceed7..ccedccb28ec8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -199,9 +199,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define READ_SYNC 0 #define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) #define WRITE_ODIRECT REQ_SYNC -#define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH) -#define WRITE_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) +#define WRITE_FLUSH (REQ_NOIDLE | REQ_PREFLUSH) +#define WRITE_FUA (REQ_NOIDLE | REQ_FUA) +#define WRITE_FLUSH_FUA (REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) /* * Attribute flags. These should be or-ed together to figure out what -- cgit From a2b809672ee6fcb4d5756ea815725b3dbaea654e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:09 -0600 Subject: block: replace REQ_NOIDLE with REQ_IDLE Noidle should be the default for writes as seen by all the compounds definitions in fs.h using it. In fact only direct I/O really should be using NODILE, so turn the whole flag around to get the defaults right, which will make our life much easier especially onces the WRITE_* defines go away. This assumes all the existing "raw" users of REQ_SYNC for writes want noidle behavior, which seems to be spot on from a quick audit. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 ++-- include/linux/fs.h | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 107d23d18096..63b750a3b165 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -175,7 +175,7 @@ enum req_flag_bits { __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_NOIDLE, /* don't anticipate more IO after this one */ + __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ @@ -190,7 +190,7 @@ enum req_flag_bits { #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_NOIDLE (1ULL << __REQ_NOIDLE) +#define REQ_IDLE (1ULL << __REQ_IDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) diff --git a/include/linux/fs.h b/include/linux/fs.h index ccedccb28ec8..46a74209917f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -197,11 +197,11 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define WRITE REQ_OP_WRITE #define READ_SYNC 0 -#define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) -#define WRITE_ODIRECT REQ_SYNC -#define WRITE_FLUSH (REQ_NOIDLE | REQ_PREFLUSH) -#define WRITE_FUA (REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) +#define WRITE_SYNC REQ_SYNC +#define WRITE_ODIRECT (REQ_SYNC | REQ_IDLE) +#define WRITE_FLUSH REQ_PREFLUSH +#define WRITE_FUA REQ_FUA +#define WRITE_FLUSH_FUA (REQ_PREFLUSH | REQ_FUA) /* * Attribute flags. These should be or-ed together to figure out what -- cgit From 70fd76140a6cb63262bd47b68d57b42e889c10ee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:10 -0600 Subject: block,fs: use REQ_* flags directly Remove the WRITE_* and READ_SYNC wrappers, and just use the flags directly. Where applicable this also drops usage of the bio_set_op_attrs wrapper. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 47 ----------------------------------------------- 1 file changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 46a74209917f..7a1b78ab7c15 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -151,58 +151,11 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ #define CHECK_IOVEC_ONLY -1 -/* - * The below are the various read and write flags that we support. Some of - * them include behavioral modifiers that send information down to the - * block layer and IO scheduler. They should be used along with a req_op. - * Terminology: - * - * The block layer uses device plugging to defer IO a little bit, in - * the hope that we will see more IO very shortly. This increases - * coalescing of adjacent IO and thus reduces the number of IOs we - * have to send to the device. It also allows for better queuing, - * if the IO isn't mergeable. If the caller is going to be waiting - * for the IO, then he must ensure that the device is unplugged so - * that the IO is dispatched to the driver. - * - * All IO is handled async in Linux. This is fine for background - * writes, but for reads or writes that someone waits for completion - * on, we want to notify the block layer and IO scheduler so that they - * know about it. That allows them to make better scheduling - * decisions. So when the below references 'sync' and 'async', it - * is referencing this priority hint. - * - * With that in mind, the available types are: - * - * READ A normal read operation. Device will be plugged. - * READ_SYNC A synchronous read. Device is not plugged, caller can - * immediately wait on this read without caring about - * unplugging. - * WRITE A normal async write. Device will be plugged. - * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down - * the hint that someone will be waiting on this IO - * shortly. The write equivalent of READ_SYNC. - * WRITE_ODIRECT Special case write for O_DIRECT only. - * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. - * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on - * non-volatile media on completion. - * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded - * by a cache flush and data is guaranteed to be on - * non-volatile media on completion. - * - */ #define RW_MASK REQ_OP_WRITE #define READ REQ_OP_READ #define WRITE REQ_OP_WRITE -#define READ_SYNC 0 -#define WRITE_SYNC REQ_SYNC -#define WRITE_ODIRECT (REQ_SYNC | REQ_IDLE) -#define WRITE_FLUSH REQ_PREFLUSH -#define WRITE_FUA REQ_FUA -#define WRITE_FLUSH_FUA (REQ_PREFLUSH | REQ_FUA) - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! -- cgit From d38499530e5f170d30f32d3841fade204e63081d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:11 -0600 Subject: fs: decouple READ and WRITE from the block layer ops Move READ and WRITE to kernel.h and don't define them in terms of block layer ops; they are our generic data direction indicators these days and have no more resemblance with the block layer ops. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ++++++ include/linux/fs.h | 13 ------------- include/linux/kernel.h | 4 ++++ include/linux/uio.h | 2 +- 4 files changed, 11 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 87ce64dafb93..fe9a17017608 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -62,6 +62,12 @@ #define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) #define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) +/* + * Return the data direction, READ or WRITE. + */ +#define bio_data_dir(bio) \ + (op_is_write(bio_op(bio)) ? WRITE : READ) + /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 7a1b78ab7c15..0ad36e0c7fa7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -151,11 +151,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ #define CHECK_IOVEC_ONLY -1 -#define RW_MASK REQ_OP_WRITE - -#define READ REQ_OP_READ -#define WRITE REQ_OP_WRITE - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -2452,14 +2447,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -/* - * return data direction, READ or WRITE - */ -static inline int bio_data_dir(struct bio *bio) -{ - return op_is_write(bio_op(bio)) ? WRITE : READ; -} - extern void check_disk_size_change(struct gendisk *disk, struct block_device *bdev); extern int revalidate_disk(struct gendisk *); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc6ed52a39b9..01b6b460c34d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -50,6 +50,10 @@ #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) +/* generic data direction definitions */ +#define READ 0 +#define WRITE 1 + #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define u64_to_user_ptr(x) ( \ diff --git a/include/linux/uio.h b/include/linux/uio.h index 6e22b544d039..d5aba1512b8b 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -125,7 +125,7 @@ static inline bool iter_is_iovec(const struct iov_iter *i) * * The ?: is just for type safety. */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & RW_MASK) +#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) /* * Cap the iov_iter by given limit; note that the second argument is -- cgit From 1e3914d4cf4e14653b7917b0e965217465cb7a9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:12 -0600 Subject: block, fs: move submit_bio to bio.h This is where all the other bio operations live, so users must include bio.h anyway. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/fs.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index fe9a17017608..5c604b4914bf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -404,6 +404,8 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) } +extern blk_qc_t submit_bio(struct bio *); + extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) diff --git a/include/linux/fs.h b/include/linux/fs.h index 0ad36e0c7fa7..5b0a9b77534d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2717,7 +2717,6 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); #ifdef CONFIG_BLOCK -extern blk_qc_t submit_bio(struct bio *); extern int bdev_read_only(struct block_device *); #endif extern int set_blocksize(struct block_device *, int); -- cgit From 2f8b544477e627a42e66902e948d87f86554aeca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:13 -0600 Subject: block,fs: untangle fs.h and blk_types.h Nothing in fs.h should require blk_types.h to be included. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- include/linux/swap.h | 1 + include/linux/writeback.h | 2 ++ 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5b0a9b77534d..8533e9d59c29 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include @@ -38,6 +37,7 @@ struct backing_dev_info; struct bdi_writeback; +struct bio; struct export_operations; struct hd_geometry; struct iovec; diff --git a/include/linux/swap.h b/include/linux/swap.h index a56523cefb9b..3a6aebc23001 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -11,6 +11,7 @@ #include #include #include +#include #include struct notifier_block; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 797100e10010..e4c38703bf4e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -10,6 +10,8 @@ #include #include +struct bio; + DECLARE_PER_CPU(int, dirty_throttle_leaks); /* -- cgit From 9f08217120568afdfb59973a89a675e649c0096d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:15 -0600 Subject: ceph: don't include blk_types.h in messenger.h The file only needs the struct bvec_iter delcaration, which is available from bvec.h. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8dbd7879fdc6..67bcef2ecddb 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -1,7 +1,7 @@ #ifndef __FS_CEPH_MESSENGER_H #define __FS_CEPH_MESSENGER_H -#include +#include #include #include #include -- cgit From be297968da22cf40c9c419df51e71ba8856a2ec2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:16 -0600 Subject: mm: only include blk_types in swap.h if CONFIG_SWAP is enabled It's only needed for the CONFIG_SWAP-only use of bio_end_io_t. Because CONFIG_SWAP implies CONFIG_BLOCK this will allow to drop some ifdefs in blk_types.h. Instead we'll need to add a few explicit includes that were implicit before, though. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/swap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 3a6aebc23001..bfee1af1f54f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -11,7 +11,6 @@ #include #include #include -#include #include struct notifier_block; @@ -352,6 +351,9 @@ extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP + +#include /* for bio_end_io_t */ + /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); -- cgit From 7281b4526cefc898d180850b54d1369f38c6b202 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:17 -0600 Subject: block: remove the CONFIG_BLOCK ifdef in blk_types.h Now that we have a separate header for struct bio_vec there is absolutely no excuse for including this header from non-block I/O code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 63b750a3b165..bb921028e7c5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -17,7 +17,6 @@ struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); -#ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) @@ -126,8 +125,6 @@ struct bio { #define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) #define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) -#endif /* CONFIG_BLOCK */ - /* * Operations and flags common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. -- cgit From 1d796d6a9641fbfcd90fcfaf6fb4894a13d0304f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Nov 2016 09:52:57 -0600 Subject: block: add REQ_BACKGROUND This adds a new request flag, REQ_BACKGROUND, that callers can use to tell the block layer that this is background (non-urgent) IO. Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index bb921028e7c5..562ac46cb790 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -177,6 +177,7 @@ enum req_flag_bits { __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ + __REQ_BACKGROUND, /* background IO */ __REQ_NR_BITS, /* stops here */ }; @@ -192,6 +193,7 @@ enum req_flag_bits { #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) +#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -- cgit From 7637241e651ec36e409412869f986dd5f097735f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Nov 2016 10:00:38 -0600 Subject: writeback: add wbc_to_write_flags() Add wbc_to_write_flags(), which returns the write modifier flags to use, based on a struct writeback_control. No functional changes in this patch, but it prepares us for factoring other wbc fields for write type. Signed-off-by: Jens Axboe Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig --- include/linux/writeback.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index e4c38703bf4e..50c96ee8108f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -9,6 +9,7 @@ #include #include #include +#include struct bio; @@ -102,6 +103,14 @@ struct writeback_control { #endif }; +static inline int wbc_to_write_flags(struct writeback_control *wbc) +{ + if (wbc->sync_mode == WB_SYNC_ALL) + return REQ_SYNC; + + return 0; +} + /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global -- cgit From 13edd5e7315a26b448c5f7f33fc7721b1e0c17ef Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Nov 2016 10:01:35 -0600 Subject: writeback: mark background writeback as such If we're doing background type writes, then use the appropriate background write flags for that. Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig --- include/linux/writeback.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 50c96ee8108f..c78f9f0920b5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -107,6 +107,8 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc) { if (wbc->sync_mode == WB_SYNC_ALL) return REQ_SYNC; + else if (wbc->for_kupdate || wbc->for_background) + return REQ_BACKGROUND; return 0; } -- cgit From 2cefe4dbaadf83b236caab46705b4b5a4958e3b6 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 31 Oct 2016 11:59:24 -0600 Subject: block: add bio_iov_iter_get_pages() This is a helper that pins down a range from an iov_iter and adds it to a bio without requiring a separate memory allocation for the page array. It will be used for upcoming direct I/O implementations for block devices and iomap based file systems. Signed-off-by: Kent Overstreet [hch: ported to the iov_iter interface, renamed and added comments. All blame should be directed to me and all fame should go to Kent after this!] Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5c604b4914bf..d367cd37a7f7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -427,6 +427,7 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, const struct iov_iter *, gfp_t); -- cgit From fd00144301d64f1742541a3c5e64cd1c51f39c55 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Oct 2016 17:19:37 -0700 Subject: blk-mq: Introduce blk_mq_queue_stopped() The function blk_queue_stopped() allows to test whether or not a traditional request queue has been stopped. Introduce a helper function that allows block drivers to query easily whether or not one or more hardware contexts of a blk-mq queue have been stopped. Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 535ab2e13d2e..aa930009fcd3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -223,6 +223,7 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs void blk_mq_abort_requeue_list(struct request_queue *q); void blk_mq_complete_request(struct request *rq, int error); +bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); -- cgit From 9b7dd572cc439fa92e120290eb74d0295567c5a0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Oct 2016 17:20:49 -0700 Subject: blk-mq: Remove blk_mq_cancel_requeue_work() Since blk_mq_requeue_work() no longer restarts stopped queues canceling requeue work is no longer needed to prevent that a stopped queue would be restarted. Hence remove this function. Signed-off-by: Bart Van Assche Cc: Mike Snitzer Cc: Keith Busch Cc: Hannes Reinecke Cc: Johannes Thumshirn Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index aa930009fcd3..a85a20f80aaa 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -217,7 +217,6 @@ void __blk_mq_end_request(struct request *rq, int error); void blk_mq_requeue_request(struct request *rq); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); -void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_abort_requeue_list(struct request_queue *q); -- cgit From 6a83e74d214a47a1371cd2e6a783264fcba7d428 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 2 Nov 2016 10:09:51 -0600 Subject: blk-mq: Introduce blk_mq_quiesce_queue() blk_mq_quiesce_queue() waits until ongoing .queue_rq() invocations have finished. This function does *not* wait until all outstanding requests have finished (this means invocation of request.end_io()). The algorithm used by blk_mq_quiesce_queue() is as follows: * Hold either an RCU read lock or an SRCU read lock around .queue_rq() calls. The former is used if .queue_rq() does not block and the latter if .queue_rq() may block. * blk_mq_quiesce_queue() first calls blk_mq_stop_hw_queues() followed by synchronize_srcu() or synchronize_rcu(). The latter call waits for .queue_rq() invocations that started before blk_mq_quiesce_queue() was called. * The blk_mq_hctx_stopped() calls that control whether or not .queue_rq() will be called are called with the (S)RCU read lock held. This is necessary to avoid race conditions against blk_mq_quiesce_queue(). Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Johannes Thumshirn Reviewed-by: Sagi Grimberg Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +++ include/linux/blkdev.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a85a20f80aaa..ed20ac74c62a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -3,6 +3,7 @@ #include #include +#include struct blk_mq_tags; struct blk_flush_queue; @@ -35,6 +36,8 @@ struct blk_mq_hw_ctx { struct blk_mq_tags *tags; + struct srcu_struct queue_rq_srcu; + unsigned long queued; unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8396da2bb698..13d893a69b46 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -918,6 +918,7 @@ extern void __blk_run_queue(struct request_queue *q); extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); +extern void blk_mq_quiesce_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); -- cgit From 2b053aca76b48e681be57b34ca3a8c2c10b275c5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Oct 2016 17:21:41 -0700 Subject: blk-mq: Add a kick_requeue_list argument to blk_mq_requeue_request() Most blk_mq_requeue_request() and blk_mq_add_to_requeue_list() calls are followed by kicking the requeue list. Hence add an argument to these two functions that allows to kick the requeue list. This was proposed by Christoph Hellwig. Signed-off-by: Bart Van Assche Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Cc: Hannes Reinecke Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ed20ac74c62a..35a0af5ede6d 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -218,8 +218,9 @@ void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, int error); void __blk_mq_end_request(struct request *rq, int error); -void blk_mq_requeue_request(struct request *rq); -void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); +void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); +void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, + bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_abort_requeue_list(struct request_queue *q); -- cgit From bc8ee596afe8f35b379f87575c46d800dd8e7e68 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Tue, 1 Nov 2016 16:32:25 +0100 Subject: net: mii: add generic function to support ksetting support The old ethtool api (get_setting and set_setting) has generic mii functions mii_ethtool_sset and mii_ethtool_gset. To support the new ethtool api ({get|set}_link_ksettings), we add two generics mii function mii_ethtool_{get|set}_link_ksettings_get. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- include/linux/mii.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 47492c9631b3..1629a0c32679 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -31,7 +31,11 @@ struct mii_if_info { extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); +extern int mii_ethtool_get_link_ksettings( + struct mii_if_info *mii, struct ethtool_link_ksettings *cmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); +extern int mii_ethtool_set_link_ksettings( + struct mii_if_info *mii, const struct ethtool_link_ksettings *cmd); extern int mii_check_gmii_support(struct mii_if_info *mii); extern void mii_check_link (struct mii_if_info *mii); extern unsigned int mii_check_media (struct mii_if_info *mii, -- cgit From 527c02f66d263d2eeff237a2326c3278cfc03d3b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 27 May 2016 11:56:53 +0200 Subject: soc: renesas: Add R-Car RST driver Add a driver for the Renesas R-Car Gen1 RESET/WDT and R-Car Gen2/Gen3 and RZ/G RST module. For now this driver just provides an API to obtain the state of the mode pins, as latched at reset time. As this is typically called from the probe function of a clock driver, which can run much earlier than any initcall, calling rcar_rst_read_mode_pins() just forces an early initialization of the driver. Despite the current simple and almost identical handling for all supported SoCs, the driver matches against SoC-specific compatible values, as the features provided by the hardware module differ a lot across the various SoC families and members. Signed-off-by: Geert Uytterhoeven Acked-by: Dirk Behme --- include/linux/soc/renesas/rcar-rst.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/soc/renesas/rcar-rst.h (limited to 'include/linux') diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h new file mode 100644 index 000000000000..a18e0783946b --- /dev/null +++ b/include/linux/soc/renesas/rcar-rst.h @@ -0,0 +1,6 @@ +#ifndef __LINUX_SOC_RENESAS_RCAR_RST_H__ +#define __LINUX_SOC_RENESAS_RCAR_RST_H__ + +int rcar_rst_read_mode_pins(u32 *mode); + +#endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */ -- cgit From 7978a78c828ac8d5351b85480e60ada865b9bea9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 1 Jun 2016 15:23:22 +0200 Subject: clk: renesas: r8a7778: Remove obsolete r8a7778_clocks_init() The R-Car M1A board code no longer calls r8a7778_clocks_init(). Signed-off-by: Geert Uytterhoeven Acked-by: Dirk Behme --- include/linux/clk/renesas.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index ba6fa4148515..2b663bba1adc 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -20,7 +20,6 @@ struct device; struct device_node; struct generic_pm_domain; -void r8a7778_clocks_init(u32 mode); void r8a7779_clocks_init(u32 mode); void rcar_gen2_clocks_init(u32 mode); -- cgit From b9fe9421d06653d735df07954730795d907e618d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 1 Jun 2016 15:24:58 +0200 Subject: clk: renesas: r8a7779: Remove obsolete r8a7779_clocks_init() The R-Car H1 board code no longer calls r8a7779_clocks_init(). Signed-off-by: Geert Uytterhoeven Acked-by: Dirk Behme --- include/linux/clk/renesas.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 2b663bba1adc..9e969941f3f6 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -20,7 +20,6 @@ struct device; struct device_node; struct generic_pm_domain; -void r8a7779_clocks_init(u32 mode); void rcar_gen2_clocks_init(u32 mode); void cpg_mstp_add_clk_domain(struct device_node *np); -- cgit From 3e91d07bb592895982400002020d510fd7b6e85f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 1 Jun 2016 15:26:53 +0200 Subject: clk: renesas: rcar-gen2: Remove obsolete rcar_gen2_clocks_init() The R-Car Gen2 board code no longer calls rcar_gen2_clocks_init(). Signed-off-by: Geert Uytterhoeven Acked-by: Dirk Behme --- include/linux/clk/renesas.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 9e969941f3f6..9ebf1f8243bb 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -20,8 +20,6 @@ struct device; struct device_node; struct generic_pm_domain; -void rcar_gen2_clocks_init(u32 mode); - void cpg_mstp_add_clk_domain(struct device_node *np); #ifdef CONFIG_CLK_RENESAS_CPG_MSTP int cpg_mstp_attach_dev(struct generic_pm_domain *unused, struct device *dev); -- cgit From 1610a73c4175e7d63985316b52ac932b65a4dc90 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 3 Nov 2016 10:56:12 +0100 Subject: netfilter: kill NF_HOOK_THRESH() and state->tresh Patch c5136b15ea36 ("netfilter: bridge: add and use br_nf_hook_thresh") introduced br_nf_hook_thresh(). Replace NF_HOOK_THRESH() by br_nf_hook_thresh from br_nf_forward_finish(), so we have no more callers for this macro. As a result, state->thresh and explicit thresh parameter in the hook state structure is not required anymore. And we can get rid of skip-hook-under-thresh loop in nf_iterate() in the core path that is only used by br_netfilter to search for the filter hook. Suggested-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 50 ++++++++++----------------------------- include/linux/netfilter_ingress.h | 2 +- 2 files changed, 14 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index abc7fdcb9eb1..e0d000f6c9bf 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -49,7 +49,6 @@ struct sock; struct nf_hook_state { unsigned int hook; - int thresh; u_int8_t pf; struct net_device *in; struct net_device *out; @@ -84,7 +83,7 @@ struct nf_hook_entry { static inline void nf_hook_state_init(struct nf_hook_state *p, struct nf_hook_entry *hook_entry, unsigned int hook, - int thresh, u_int8_t pf, + u_int8_t pf, struct net_device *indev, struct net_device *outdev, struct sock *sk, @@ -92,7 +91,6 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; - p->thresh = thresh; p->pf = pf; p->in = indev; p->out = outdev; @@ -155,20 +153,16 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); /** - * nf_hook_thresh - call a netfilter hook + * nf_hook - call a netfilter hook * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct net *net, - struct sock *sk, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct net *, struct sock *, struct sk_buff *), - int thresh) +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entry *hook_head; int ret = 1; @@ -185,8 +179,8 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, if (hook_head) { struct nf_hook_state state; - nf_hook_state_init(&state, hook_head, hook, thresh, - pf, indev, outdev, sk, net, okfn); + nf_hook_state_init(&state, hook_head, hook, pf, indev, outdev, + sk, net, okfn); ret = nf_hook_slow(skb, &state); } @@ -195,14 +189,6 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, return ret; } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, - struct sock *sk, struct sk_buff *skb, - struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct net *, struct sock *, struct sk_buff *)) -{ - return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); -} - /* Activate hook; either okfn or kfree_skb called, unless a hook returns NF_STOLEN (in which case, it's up to the hook to deal with the consequences). @@ -220,19 +206,6 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, coders :) */ -static inline int -NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, - struct sk_buff *skb, struct net_device *in, - struct net_device *out, - int (*okfn)(struct net *, struct sock *, struct sk_buff *), - int thresh) -{ - int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); - if (ret == 1) - ret = okfn(net, sk, skb); - return ret; -} - static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, @@ -242,7 +215,7 @@ NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, int ret; if (!cond || - ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) + ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1)) ret = okfn(net, sk, skb); return ret; } @@ -252,7 +225,10 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); + int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); + if (ret == 1) + ret = okfn(net, sk, skb); + return ret; } /* Call setsockopt() */ diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 33e37fb41d5d..fd44e4131710 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -26,7 +26,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) if (unlikely(!e)) return 0; - nf_hook_state_init(&state, e, NF_NETDEV_INGRESS, INT_MIN, + nf_hook_state_init(&state, e, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); -- cgit From 613dbd95723aee7abd16860745691b6c7bda20dc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 3 Nov 2016 10:56:21 +0100 Subject: netfilter: x_tables: move hook state into xt_action_param structure Place pointer to hook state in xt_action_param structure instead of copying the fields that we need. After this change xt_action_param fits into one cacheline. This patch also adds a set of new wrapper functions to fetch relevant hook state structure fields. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 48 ++++++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 2ad1a2b289b5..cd4eaf8df445 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -4,6 +4,7 @@ #include #include +#include #include /* Test a struct->invflags and a boolean for inequality */ @@ -17,14 +18,9 @@ * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data - * @net network namespace through which the action was invoked - * @in: input netdevice - * @out: output netdevice + * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data - * @hook: hook number given packet came from - * @family: Actual NFPROTO_* through which the function is invoked - * (helpful when match->family == NFPROTO_UNSPEC) * * Fields written to by extensions: * @@ -38,15 +34,47 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; - struct net *net; - const struct net_device *in, *out; + const struct nf_hook_state *state; int fragoff; unsigned int thoff; - unsigned int hooknum; - u_int8_t family; bool hotdrop; }; +static inline struct net *xt_net(const struct xt_action_param *par) +{ + return par->state->net; +} + +static inline struct net_device *xt_in(const struct xt_action_param *par) +{ + return par->state->in; +} + +static inline const char *xt_inname(const struct xt_action_param *par) +{ + return par->state->in->name; +} + +static inline struct net_device *xt_out(const struct xt_action_param *par) +{ + return par->state->out; +} + +static inline const char *xt_outname(const struct xt_action_param *par) +{ + return par->state->out->name; +} + +static inline unsigned int xt_hooknum(const struct xt_action_param *par) +{ + return par->state->hook; +} + +static inline u_int8_t xt_family(const struct xt_action_param *par) +{ + return par->state->pf; +} + /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions -- cgit From 01886bd91f1ba418ce669dfe97a06ca9504e482a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 3 Nov 2016 10:56:35 +0100 Subject: netfilter: remove hook_entries field from nf_hook_state This field is only useful for nf_queue, so store it in the nf_queue_entry structure instead, away from the core path. Pass hook_head to nf_hook_slow(). Since we always have a valid entry on the first iteration in nf_iterate(), we can use 'do { ... } while (entry)' loop instead. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 10 ++++------ include/linux/netfilter_ingress.h | 4 ++-- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e0d000f6c9bf..69230140215b 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -54,7 +54,6 @@ struct nf_hook_state { struct net_device *out; struct sock *sk; struct net *net; - struct nf_hook_entry __rcu *hook_entries; int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; @@ -81,7 +80,6 @@ struct nf_hook_entry { }; static inline void nf_hook_state_init(struct nf_hook_state *p, - struct nf_hook_entry *hook_entry, unsigned int hook, u_int8_t pf, struct net_device *indev, @@ -96,7 +94,6 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->out = outdev; p->sk = sk; p->net = net; - RCU_INIT_POINTER(p->hook_entries, hook_entry); p->okfn = okfn; } @@ -150,7 +147,8 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif -int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); +int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, + struct nf_hook_entry *entry); /** * nf_hook - call a netfilter hook @@ -179,10 +177,10 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, if (hook_head) { struct nf_hook_state state; - nf_hook_state_init(&state, hook_head, hook, pf, indev, outdev, + nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); - ret = nf_hook_slow(skb, &state); + ret = nf_hook_slow(skb, &state, hook_head); } rcu_read_unlock(); diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index fd44e4131710..2dc3b49b804a 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -26,10 +26,10 @@ static inline int nf_hook_ingress(struct sk_buff *skb) if (unlikely(!e)) return 0; - nf_hook_state_init(&state, e, NF_NETDEV_INGRESS, + nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); - return nf_hook_slow(skb, &state); + return nf_hook_slow(skb, &state, e); } static inline void nf_hook_ingress_init(struct net_device *dev) -- cgit From 0cc0aa614b4c24b21b2492c0a1753035ee8c6edb Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 2 Nov 2016 11:02:17 -0400 Subject: ipv6: add IPV6_RECVFRAGSIZE cmsg When reading a datagram or raw packet that arrived fragmented, expose the maximum fragment size if recorded to allow applications to estimate receive path MTU. At this point, the field is only recorded when ipv6 connection tracking is enabled. A follow-up patch will record this field also in the ipv6 input path. Tested using the test for IP_RECVFRAGSIZE plus ip netns exec to ip addr add dev veth1 fc07::1/64 ip netns exec from ip addr add dev veth0 fc07::2/64 ip netns exec to ./recv_cmsg_recvfragsize -6 -u -p 6000 & ip netns exec from nc -q 1 -u fc07::1 6000 < payload Both with and without enabling connection tracking ip6tables -A INPUT -m state --state NEW -p udp -j LOG Signed-off-by: Willem de Bruijn Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ca1ad9ebbc92..1afb6e8d35c3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -229,8 +229,9 @@ struct ipv6_pinfo { rxflow:1, rxtclass:1, rxpmtu:1, - rxorigdstaddr:1; - /* 2 bits hole */ + rxorigdstaddr:1, + recvfragsize:1; + /* 1 bits hole */ } bits; __u16 all; } rxopt; -- cgit From 50d24c34403c62ad29e8b6db559d491bae20b4b7 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 3 Nov 2016 17:03:53 -0700 Subject: block: immediately dispatch big size request Currently block plug holds up to 16 non-mergeable requests. This makes sense if the request size is small, eg, reduce lock contention. But if request size is big enough, we don't need to worry about lock contention. Holding such request makes no sense and it lows the disk utilization. In practice, this improves 10% throughput for my raid5 sequential write workload. The size (128k) is arbitrary right now, but it makes sure lock contention is small. This probably could be more intelligent, eg, check average request size holded. Since this is mainly for sequential IO, probably not worthy. V2: check the last request instead of the first request, so as long as there is one big size request we flush the plug. Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 13d893a69b46..9189a2d5c392 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1173,6 +1173,7 @@ struct blk_plug { struct list_head cb_list; /* md requires an unplug callback */ }; #define BLK_MAX_REQUEST_COUNT 16 +#define BLK_PLUG_FLUSH_SIZE (128 * 1024) struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); -- cgit From 1b5b42216469b05ef4b5916cb40b127dfab1da88 Mon Sep 17 00:00:00 2001 From: Axel Haslam Date: Thu, 3 Nov 2016 12:11:42 +0100 Subject: regulator: core: Add new API to poll for error conditions Regulator consumers can receive event notifications when errors are reported to the driver, but currently, there is no way for a regulator consumer to know when the error is over. To allow a regulator consumer to poll for error conditions add a new API: regulator_get_error_flags. Signed-off-by: Axel Haslam Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 26 ++++++++++++++++++++++++++ include/linux/regulator/driver.h | 4 ++++ 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 692108222271..528eb1f5273e 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -120,6 +120,25 @@ struct regmap; #define REGULATOR_EVENT_PRE_DISABLE 0x400 #define REGULATOR_EVENT_ABORT_DISABLE 0x800 +/* + * Regulator errors that can be queried using regulator_get_error_flags + * + * UNDER_VOLTAGE Regulator output is under voltage. + * OVER_CURRENT Regulator output current is too high. + * REGULATION_OUT Regulator output is out of regulation. + * FAIL Regulator output has failed. + * OVER_TEMP Regulator over temp. + * + * NOTE: These errors can be OR'ed together. + */ + +#define REGULATOR_ERROR_UNDER_VOLTAGE BIT(1) +#define REGULATOR_ERROR_OVER_CURRENT BIT(2) +#define REGULATOR_ERROR_REGULATION_OUT BIT(3) +#define REGULATOR_ERROR_FAIL BIT(4) +#define REGULATOR_ERROR_OVER_TEMP BIT(5) + + /** * struct pre_voltage_change_data - Data sent with PRE_VOLTAGE_CHANGE event * @@ -237,6 +256,8 @@ int regulator_get_current_limit(struct regulator *regulator); int regulator_set_mode(struct regulator *regulator, unsigned int mode); unsigned int regulator_get_mode(struct regulator *regulator); +int regulator_get_error_flags(struct regulator *regulator, + unsigned int *flags); int regulator_set_load(struct regulator *regulator, int load_uA); int regulator_allow_bypass(struct regulator *regulator, bool allow); @@ -477,6 +498,11 @@ static inline unsigned int regulator_get_mode(struct regulator *regulator) return REGULATOR_MODE_NORMAL; } +static inline int regulator_get_error_flags(struct regulator *regulator) +{ + return -EINVAL; +} + static inline int regulator_set_load(struct regulator *regulator, int load_uA) { return REGULATOR_MODE_NORMAL; diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 37b532410528..dac8e7b16bc6 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -100,6 +100,7 @@ struct regulator_linear_range { * * @set_mode: Set the configured operating mode for the regulator. * @get_mode: Get the configured operating mode for the regulator. + * @get_error_flags: Get the current error(s) for the regulator. * @get_status: Return actual (not as-configured) status of regulator, as a * REGULATOR_STATUS value (or negative errno) * @get_optimum_mode: Get the most efficient operating mode for the regulator @@ -169,6 +170,9 @@ struct regulator_ops { int (*set_mode) (struct regulator_dev *, unsigned int mode); unsigned int (*get_mode) (struct regulator_dev *); + /* retrieve current error flags on the regulator */ + int (*get_error_flags)(struct regulator_dev *, unsigned int *flags); + /* Time taken to enable or set voltage on the regulator */ int (*enable_time) (struct regulator_dev *); int (*set_ramp_delay) (struct regulator_dev *, int ramp_delay); -- cgit From 68f929ff2654bced015ccb9b5555667f46f88dfa Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 3 Nov 2016 17:12:06 +0000 Subject: debugfs: constify argument to debugfs_real_fops() seq_file users can only access const version of file pointer, because the ->file member of struct seq_operations is marked as such. Make parameter to debugfs_real_fops() const. CC: Greg Kroah-Hartman CC: Nicolai Stange CC: Christian Lamparter CC: LKML Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/debugfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 4d3f0d1aec73..bf1907d96097 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -52,7 +52,8 @@ extern struct srcu_struct debugfs_srcu; * Must only be called under the protection established by * debugfs_use_file_start(). */ -static inline const struct file_operations *debugfs_real_fops(struct file *filp) +static inline const struct file_operations * +debugfs_real_fops(const struct file *filp) __must_hold(&debugfs_srcu) { /* -- cgit From 29f3ad7d8380364c86556eedf4eedd3b3d4921dc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Nov 2016 18:08:11 +0100 Subject: fs: Provide function to unmap metadata for a range of blocks Provide function equivalent to unmap_underlying_metadata() for a range of blocks. We somewhat optimize the function to use pagevec lookups instead of looking up buffer heads one by one and use page lock to pin buffer heads instead of mapping's private_lock to improve scalability. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index ebbacd14d450..9c9c73ce7d4f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -169,6 +169,8 @@ void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void unmap_underlying_metadata(struct block_device *bdev, sector_t block); +void clean_bdev_aliases(struct block_device *bdev, sector_t block, + sector_t len); void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); -- cgit From e64855c6cfaa0a80c1b71c5f647cb792dc436668 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Nov 2016 18:08:15 +0100 Subject: fs: Add helper to clean bdev aliases under a bh and use it Add a helper function that clears buffer heads from a block device aliasing passed bh. Use this helper function from filesystems instead of the original unmap_underlying_metadata() to save some boiler plate code and also have a better name for the functionalily since it is not unmapping anything for a *long* time. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 9c9c73ce7d4f..d1ab91fc6d43 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -171,6 +171,10 @@ int sync_mapping_buffers(struct address_space *mapping); void unmap_underlying_metadata(struct block_device *bdev, sector_t block); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); +static inline void clean_bdev_bh_alias(struct buffer_head *bh) +{ + clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); +} void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); -- cgit From ce98321bf7d274a470642ef99e1d82512673ce7c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Nov 2016 18:08:16 +0100 Subject: fs: Remove unmap_underlying_metadata Nobody is using this function anymore. Remove it. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d1ab91fc6d43..d67ab83823ad 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -168,7 +168,6 @@ int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); -void unmap_underlying_metadata(struct block_device *bdev, sector_t block); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) -- cgit From c9329d8638cfa1a86faf4fb8bd4922a3d9c6c437 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Wed, 5 Oct 2016 14:34:40 +0530 Subject: mfd: ti_am335x_tscadc: store physical address store the physical address of the device in its priv to use it for DMA addressing in the client drivers. Signed-off-by: Mugunthan V N Acked-for-MFD-by: Lee Jones Signed-off-by: Jonathan Cameron --- include/linux/mfd/ti_am335x_tscadc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 7f55b8b41032..e45a208d9944 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -155,6 +155,7 @@ struct ti_tscadc_dev { struct device *dev; struct regmap *regmap; void __iomem *tscadc_base; + phys_addr_t tscadc_phys_base; int irq; int used_cells; /* 1-2 */ int tsc_wires; -- cgit From f438b9da75eb80eb6c4095a5b75324cc9a7f0570 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Wed, 5 Oct 2016 14:34:41 +0530 Subject: drivers: iio: ti_am335x_adc: add dma support This patch adds the required pieces to ti_am335x_adc driver for DMA support Signed-off-by: Mugunthan V N Reviewed-by: Peter Ujfalusi Signed-off-by: Jonathan Cameron --- include/linux/mfd/ti_am335x_tscadc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index e45a208d9944..b9a53e013bff 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -23,6 +23,8 @@ #define REG_IRQENABLE 0x02C #define REG_IRQCLR 0x030 #define REG_IRQWAKEUP 0x034 +#define REG_DMAENABLE_SET 0x038 +#define REG_DMAENABLE_CLEAR 0x03c #define REG_CTRL 0x040 #define REG_ADCFSM 0x044 #define REG_CLKDIV 0x04C @@ -36,6 +38,7 @@ #define REG_FIFO0THR 0xE8 #define REG_FIFO1CNT 0xF0 #define REG_FIFO1THR 0xF4 +#define REG_DMA1REQ 0xF8 #define REG_FIFO0 0x100 #define REG_FIFO1 0x200 @@ -126,6 +129,10 @@ #define FIFOREAD_DATA_MASK (0xfff << 0) #define FIFOREAD_CHNLID_MASK (0xf << 16) +/* DMA ENABLE/CLEAR Register */ +#define DMA_FIFO0 BIT(0) +#define DMA_FIFO1 BIT(1) + /* Sequencer Status */ #define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 -- cgit From d278d4a8892f13b6a9eb6102b356402f0e062324 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Mar 2016 10:21:08 -0600 Subject: block: add code to track actual device queue depth For blk-mq, ->nr_requests does track queue depth, at least at init time. But for the older queue paths, it's simply a soft setting. On top of that, it's generally larger than the hardware setting on purpose, to allow backup of requests for merging. Fill a hole in struct request with a 'queue_depth' member, that drivers can call to more closely inform the block layer of the real queue depth. Signed-off-by: Jens Axboe Reviewed-by: Jan Kara --- include/linux/blkdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9189a2d5c392..d364be6e6959 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -405,6 +405,8 @@ struct request_queue { struct blk_mq_ctx __percpu *queue_ctx; unsigned int nr_queues; + unsigned int queue_depth; + /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; @@ -777,6 +779,14 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) return false; } +static inline unsigned int blk_queue_depth(struct request_queue *q) +{ + if (q->queue_depth) + return q->queue_depth; + + return q->nr_requests; +} + /* * q->prep_rq_fn return values */ @@ -1094,6 +1104,7 @@ extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); +extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, -- cgit From fa32ff6576623616c1751562edaed8c164ca5199 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Sun, 6 Nov 2016 13:14:05 -0800 Subject: Drivers: hv: ring_buffer: count on wrap around mappings in get_next_pkt_raw() (v2) With wrap around mappings in place we can always provide drivers with direct links to packets on the ring buffer, even when they wrap around. Do the required updates to get_next_pkt_raw()/put_pkt_raw() The first version of this commit was reverted (65a532f3d50a) to deal with cross-tree merge issues which are (hopefully) resolved now. Signed-off-by: Vitaly Kuznetsov Signed-off-by: K. Y. Srinivasan Tested-by: Dexuan Cui Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 32 +++++++++++--------------------- 1 file changed, 11 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6824556d37ed..42ae6a5a2538 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1526,31 +1526,23 @@ static inline struct vmpacket_descriptor * get_next_pkt_raw(struct vmbus_channel *channel) { struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 read_loc = ring_info->priv_read_index; + u32 priv_read_loc = ring_info->priv_read_index; void *ring_buffer = hv_get_ring_buffer(ring_info); - struct vmpacket_descriptor *cur_desc; - u32 packetlen; u32 dsize = ring_info->ring_datasize; - u32 delta = read_loc - ring_info->ring_buffer->read_index; + /* + * delta is the difference between what is available to read and + * what was already consumed in place. We commit read index after + * the whole batch is processed. + */ + u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ? + priv_read_loc - ring_info->ring_buffer->read_index : + (dsize - ring_info->ring_buffer->read_index) + priv_read_loc; u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) return NULL; - if ((read_loc + sizeof(*cur_desc)) > dsize) - return NULL; - - cur_desc = ring_buffer + read_loc; - packetlen = cur_desc->len8 << 3; - - /* - * If the packet under consideration is wrapping around, - * return failure. - */ - if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1)) - return NULL; - - return cur_desc; + return ring_buffer + priv_read_loc; } /* @@ -1562,16 +1554,14 @@ static inline void put_pkt_raw(struct vmbus_channel *channel, struct vmpacket_descriptor *desc) { struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 read_loc = ring_info->priv_read_index; u32 packetlen = desc->len8 << 3; u32 dsize = ring_info->ring_datasize; - if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize) - BUG(); /* * Include the packet trailer. */ ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; + ring_info->priv_read_index %= dsize; } /* -- cgit From 1f6ee4e7d83586c8b10bd4f2f4346353d04ce884 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Sun, 6 Nov 2016 13:14:17 -0800 Subject: Drivers: hv: vmbus: On write cleanup the logic to interrupt the host Signal the host when we determine the host is to be signaled. The currrent code determines the need to signal in the ringbuffer code and actually issues the signal elsewhere. This can result in the host viewing this interrupt as spurious since the host may also poll the channel. Make the necessary adjustments. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 42ae6a5a2538..8cf78ed96747 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1454,6 +1454,7 @@ void hv_event_tasklet_enable(struct vmbus_channel *channel); void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); +void vmbus_setevent(struct vmbus_channel *channel); /* * Negotiated version with the Host. */ -- cgit From 3372592a140db69fd63837e81f048ab4abf8111e Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Sun, 6 Nov 2016 13:14:18 -0800 Subject: Drivers: hv: vmbus: On the read path cleanup the logic to interrupt the host Signal the host when we determine the host is to be signaled - on th read path. The currrent code determines the need to signal in the ringbuffer code and actually issues the signal elsewhere. This can result in the host viewing this interrupt as spurious since the host may also poll the channel. Make the necessary adjustments. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 8cf78ed96747..fdb0a87323f3 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1487,10 +1487,11 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) * there is room for the producer to send the pending packet. */ -static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi) +static inline void hv_signal_on_read(struct vmbus_channel *channel) { u32 cur_write_sz; u32 pending_sz; + struct hv_ring_buffer_info *rbi = &channel->inbound; /* * Issue a full memory barrier before making the signaling decision. @@ -1508,14 +1509,14 @@ static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi) pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); /* If the other end is not blocked on write don't bother. */ if (pending_sz == 0) - return false; + return; cur_write_sz = hv_get_bytes_to_write(rbi); if (cur_write_sz >= pending_sz) - return true; + vmbus_setevent(channel); - return false; + return; } /* @@ -1587,8 +1588,7 @@ static inline void commit_rd_index(struct vmbus_channel *channel) virt_rmb(); ring_info->ring_buffer->read_index = ring_info->priv_read_index; - if (hv_need_to_signal_on_read(ring_info)) - vmbus_set_event(channel); + hv_signal_on_read(channel); } -- cgit From e9f66ae23c209eec617130126a23bf547bf7a6d8 Mon Sep 17 00:00:00 2001 From: Sergio Prado Date: Thu, 20 Oct 2016 19:42:44 -0200 Subject: mtd: s3c2410: make ecc mode configurable via platform data Removing CONFIG_MTD_NAND_S3C2410_HWECC option and adding a ecc_mode field in the drivers's platform data structure so it can be selectable via platform data. Also setting this field to NAND_ECC_SOFT in all boards using this driver since none of them had CONFIG_MTD_NAND_S3C2410_HWECC enabled. Signed-off-by: Sergio Prado Acked-by: Krzysztof Kozlowski Signed-off-by: Boris Brezillon --- include/linux/platform_data/mtd-nand-s3c2410.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index c55e42ee57fa..729af13d1773 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -12,9 +12,10 @@ #ifndef __MTD_NAND_S3C2410_H #define __MTD_NAND_S3C2410_H +#include + /** * struct s3c2410_nand_set - define a set of one or more nand chips - * @disable_ecc: Entirely disable ECC - Dangerous * @flash_bbt: Openmoko u-boot can create a Bad Block Table * Setting this flag will allow the kernel to * look for it at boot time and also skip the NAND @@ -31,7 +32,6 @@ * a warning at boot time. */ struct s3c2410_nand_set { - unsigned int disable_ecc:1; unsigned int flash_bbt:1; unsigned int options; @@ -51,6 +51,8 @@ struct s3c2410_platform_nand { unsigned int ignore_unset_ecc:1; + nand_ecc_modes_t ecc_mode; + int nr_sets; struct s3c2410_nand_set *sets; -- cgit From 1c825ad1b8cfe12ccc145dcdba360c52c0272c04 Mon Sep 17 00:00:00 2001 From: Sergio Prado Date: Wed, 26 Oct 2016 21:59:55 -0200 Subject: mtd: s3c2410: parse the device configuration from OF node Allows configuring Samsung's s3c2410 memory controller using a devicetree. Signed-off-by: Sergio Prado Acked-by: Krzysztof Kozlowski Signed-off-by: Boris Brezillon --- include/linux/platform_data/mtd-nand-s3c2410.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index 729af13d1773..f01659026b26 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -40,6 +40,7 @@ struct s3c2410_nand_set { char *name; int *nr_map; struct mtd_partition *partitions; + struct device_node *of_node; }; struct s3c2410_platform_nand { -- cgit From 204e7ecd47e26cc12d9e8e8a7e7a2eeb9573f0ba Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 1 Oct 2016 10:24:02 +0200 Subject: mtd: nand: Add a few more timings to nand_sdr_timings Add the tR_max, tBERS_max, tPROG_max and tCCS_min timings to the nand_sdr_timings struct. Assign default/safe values for the statically defined timings, and extract them from the ONFI parameter table if the NAND is ONFI compliant. Signed-off-by: Boris Brezillon Tested-by: Marc Gonzalez --- include/linux/mtd/nand.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c5d3d5024fc8..6fe83bce83a6 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -584,6 +584,10 @@ struct nand_buffers { * * All these timings are expressed in picoseconds. * + * @tBERS_max: Block erase time + * @tCCS_min: Change column setup time + * @tPROG_max: Page program time + * @tR_max: Page read time * @tALH_min: ALE hold time * @tADL_min: ALE to data loading time * @tALS_min: ALE setup time @@ -621,6 +625,10 @@ struct nand_buffers { * @tWW_min: WP# transition to WE# low */ struct nand_sdr_timings { + u32 tBERS_max; + u32 tCCS_min; + u32 tPROG_max; + u32 tR_max; u32 tALH_min; u32 tADL_min; u32 tALS_min; -- cgit From 6ea40a3ba93e1b14ffb349e276f9dfefc4334b99 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 1 Oct 2016 10:24:03 +0200 Subject: mtd: nand: Wait tCCS after a column change Drivers implementing ->cmd_ctrl() and relying on the default ->cmdfunc() implementation usually don't wait tCCS when a column change (RNDIN or RNDOUT) is requested. Add an option flag to ask the core to do so (note that we keep this as an opt-in to avoid breaking existing implementations), and make use of the ->data_interface information is available (otherwise, wait 500ns). Signed-off-by: Boris Brezillon Tested-by: Marc Gonzalez --- include/linux/mtd/nand.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 6fe83bce83a6..970ceb948835 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -210,6 +210,16 @@ enum nand_ecc_algo { */ #define NAND_USE_BOUNCE_BUFFER 0x00100000 +/* + * In case your controller is implementing ->cmd_ctrl() and is relying on the + * default ->cmdfunc() implementation, you may want to let the core handle the + * tCCS delay which is required when a column change (RNDIN or RNDOUT) is + * requested. + * If your controller already takes care of this delay, you don't need to set + * this flag. + */ +#define NAND_WAIT_TCCS 0x00200000 + /* Options set by nand scan */ /* Nand scan has allocated controller struct */ #define NAND_CONTROLLER_ALLOC 0x80000000 -- cgit From 5b4e2900512321435a5cd7dd77f58f23f3109950 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Fri, 4 Nov 2016 01:10:56 -0400 Subject: net: phy: broadcom: add bcm54xx_auxctl_read Add a helper function to read the AUXCTL register for the BCM54xx. This mirrors the bcm54xx_auxctl_write function already present in the code. Signed-off-by: Jon Mason Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 60def78c4e12..0ed66914b61c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -110,6 +110,7 @@ #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 #define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 +#define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12 #define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 -- cgit From b14995ac2527b43a75c9190fbd4efd43fb1f4562 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Fri, 4 Nov 2016 01:10:58 -0400 Subject: net: phy: broadcom: Add BCM54810 PHY entry The BCM54810 PHY requires some semi-unique configuration, which results in some additional configuration in addition to the standard config. Also, some users of the BCM54810 require the PHY lanes to be swapped. Since there is no way to detect this, add a device tree query to see if it is applicable. Inspired-by: Vikas Soni Signed-off-by: Jon Mason Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 0ed66914b61c..848dc508ef57 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -13,6 +13,7 @@ #define PHY_ID_BCM5241 0x0143bc30 #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 +#define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 #define PHY_ID_BCM5421 0x002060e0 @@ -56,6 +57,7 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 + /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) #define PHY_BRCM_7XXX_PATCH(x) ((x) & 0xff) @@ -111,6 +113,7 @@ #define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 #define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN (1 << 8) #define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 @@ -192,6 +195,12 @@ #define BCM5482_SSD_SGMII_SLAVE_EN 0x0002 /* Slave mode enable */ #define BCM5482_SSD_SGMII_SLAVE_AD 0x0001 /* Slave auto-detection */ +/* BCM54810 Registers */ +#define BCM54810_EXP_BROADREACH_LRE_MISC_CTL (MII_BCM54XX_EXP_SEL_ER + 0x90) +#define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) +#define BCM54810_SHD_CLK_CTL 0x3 +#define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) + /*****************************************************************************/ /* Fast Ethernet Transceiver definitions. */ -- cgit From 7c13f97ffde63cc792c49ec1513f3974f2f05229 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 4 Nov 2016 11:28:59 +0100 Subject: udp: do fwd memory scheduling on dequeue A new argument is added to __skb_recv_datagram to provide an explicit skb destructor, invoked under the receive queue lock. The UDP protocol uses such argument to perform memory reclaiming on dequeue, so that the UDP protocol does not set anymore skb->desctructor. Instead explicit memory reclaiming is performed at close() time and when skbs are removed from the receive queue. The in kernel UDP protocol users now need to call a skb_recv_udp() variant instead of skb_recv_datagram() to properly perform memory accounting on dequeue. Overall, this allows acquiring only once the receive queue lock on dequeue. Tested using pktgen with random src port, 64 bytes packet, wire-speed on a 10G link as sender and udp_sink as the receiver, using an l4 tuple rxhash to stress the contention, and one or more udp_sink instances with reuseport. nr sinks vanilla patched 1 440 560 3 2150 2300 6 3650 3800 9 4450 4600 12 6250 6450 v1 -> v2: - do rmem and allocated memory scheduling under the receive lock - do bulk scheduling in first_packet_length() and in udp_destruct_sock() - avoid the typdef for the dequeue callback Suggested-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cc6e23eaac91..a4aeeca7e805 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3033,9 +3033,13 @@ static inline void skb_frag_list_init(struct sk_buff *skb) int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), int *peeked, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), int *peeked, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); -- cgit From ebcf6f979d55f35dfe36956364f0dce8c738220b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 2 Nov 2016 07:12:31 -0400 Subject: swiotlb: Drop unused functions swiotlb_map_sg and swiotlb_unmap_sg There are no users for swiotlb_map_sg or swiotlb_unmap_sg so we might as well just drop them. Signed-off-by: Alexander Duyck Acked-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5f81f8a187f2..f0d258967869 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -72,14 +72,6 @@ extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); -extern int -swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, - enum dma_data_direction dir); - -extern void -swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - enum dma_data_direction dir); - extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, -- cgit From 0443fa003fa199f41bfbed3012f314d02c5b1f24 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 2 Nov 2016 07:13:02 -0400 Subject: swiotlb: Add support for DMA_ATTR_SKIP_CPU_SYNC As a first step to making DMA_ATTR_SKIP_CPU_SYNC apply to architectures beyond just ARM I need to make it so that the swiotlb will respect the flag. In order to do that I also need to update the swiotlb-xen since it heavily makes use of the functionality. Cc: Konrad Rzeszutek Wilk Signed-off-by: Alexander Duyck Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f0d258967869..183f37c8a5e1 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -44,11 +44,13 @@ enum dma_sync_target { extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr, phys_addr_t phys, size_t size, - enum dma_data_direction dir); + enum dma_data_direction dir, + unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir); + size_t size, enum dma_data_direction dir, + unsigned long attrs); extern void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, -- cgit From 0f78ba96bbcf30a78224fe56f8fd72f87915afdd Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 23 Feb 2016 15:32:14 -0800 Subject: Input: gpio_keys_polled - keep button data constant Commit 633a21d80b4a ("input: gpio_keys_polled: Add support for GPIO descriptors") placed gpio descriptor into gpio_keys_button structure, which is supposed to be part of platform data and not modifiable by the driver. To keep the data constant, let's move the descriptor to gpio_keys_button_data structure instead. Tested-by: Mika Westerberg Signed-off-by: Dmitry Torokhov --- include/linux/gpio_keys.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index ee2d8c6f9130..0b71024c082c 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -2,7 +2,6 @@ #define _GPIO_KEYS_H struct device; -struct gpio_desc; /** * struct gpio_keys_button - configuration parameters @@ -18,7 +17,6 @@ struct gpio_desc; * disable button via sysfs * @value: axis value for %EV_ABS * @irq: Irq number in case of interrupt keys - * @gpiod: GPIO descriptor */ struct gpio_keys_button { unsigned int code; @@ -31,7 +29,6 @@ struct gpio_keys_button { bool can_disable; int value; unsigned int irq; - struct gpio_desc *gpiod; }; /** @@ -46,7 +43,7 @@ struct gpio_keys_button { * @name: input device name */ struct gpio_keys_platform_data { - struct gpio_keys_button *buttons; + const struct gpio_keys_button *buttons; int nbuttons; unsigned int poll_interval; unsigned int rep:1; -- cgit From 63e95b5c4f16e156b98adcf2f7d820ba941c82a3 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 8 Nov 2016 11:32:20 +1100 Subject: dax: coordinate locking for offsets in PMD range DAX radix tree locking currently locks entries based on the unique combination of the 'mapping' pointer and the pgoff_t 'index' for the entry. This works for PTEs, but as we move to PMDs we will need to have all the offsets within the range covered by the PMD to map to the same bit lock. To accomplish this, for ranges covered by a PMD entry we will instead lock based on the page offset of the beginning of the PMD entry. The 'mapping' pointer is still used in the same way. Signed-off-by: Ross Zwisler Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/dax.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index add6c4bc568f..a41a747d6112 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -22,7 +22,7 @@ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, bool wake_all); + pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX struct page *read_dax_sector(struct block_device *bdev, sector_t n); -- cgit From b9fde0462e34a05b25c3d68d344971865659abae Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 8 Nov 2016 11:32:35 +1100 Subject: dax: remove dax_pmd_fault() dax_pmd_fault() is the old struct buffer_head + get_block_t based 2 MiB DAX fault handler. This fault handler has been disabled for several kernel releases, and support for PMDs will be reintroduced using the struct iomap interface instead. Signed-off-by: Ross Zwisler Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/dax.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index a41a747d6112..0f74866edae6 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -48,16 +48,12 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) -int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned int flags, get_block_t); -#else static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, get_block_t gb) { return VM_FAULT_FALLBACK; } -#endif + int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -- cgit From 11c59c92f44d9272db7655a462608658a6d95013 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 8 Nov 2016 11:32:46 +1100 Subject: dax: correct dax iomap code namespace The recently added DAX functions that use the new struct iomap data structure were named iomap_dax_rw(), iomap_dax_fault() and iomap_dax_actor(). These are actually defined in fs/dax.c, though, so should be part of the "dax" namespace and not the "iomap" namespace. Rename them to dax_iomap_rw(), dax_iomap_fault() and dax_iomap_actor() respectively. Signed-off-by: Ross Zwisler Suggested-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/dax.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 0f74866edae6..a3dfee4cb03f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -11,13 +11,13 @@ struct iomap_ops; /* We use lowest available exceptional entry bit for locking */ #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, +ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops); ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, get_block_t, dio_iodone_t, int flags); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); -int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, +int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); -- cgit From fa28f7296a7ce38ed15dc06bd2149e04c8db9d4b Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 8 Nov 2016 11:33:35 +1100 Subject: dax: move RADIX_DAX_* defines to dax.h The RADIX_DAX_* defines currently mostly live in fs/dax.c, with just RADIX_DAX_ENTRY_LOCK being in include/linux/dax.h so it can be used in mm/filemap.c. When we add PMD support, though, mm/filemap.c will also need access to the RADIX_DAX_PTE type so it can properly construct a 4k sized empty entry. Instead of shifting the defines between dax.c and dax.h as they are individually used in other code, just move them wholesale to dax.h so they'll be available when we need them. Signed-off-by: Ross Zwisler Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/dax.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index a3dfee4cb03f..e9ea78c1cf98 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -8,8 +8,21 @@ struct iomap_ops; -/* We use lowest available exceptional entry bit for locking */ +/* + * We use lowest available bit in exceptional entry for locking, other two + * bits to determine entry type. In total 3 special bits. + */ +#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3) #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) +#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) +#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD) +#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK) +#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT)) +#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \ + RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \ + RADIX_TREE_EXCEPTIONAL_ENTRY)) + ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops); -- cgit From 642261ac995e01d7837db1f4b90181496f7e6835 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 8 Nov 2016 11:34:45 +1100 Subject: dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Signed-off-by: Dave Chinner --- include/linux/dax.h | 55 ++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index e9ea78c1cf98..8d1a5c47945f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -9,20 +9,32 @@ struct iomap_ops; /* - * We use lowest available bit in exceptional entry for locking, other two - * bits to determine entry type. In total 3 special bits. + * We use lowest available bit in exceptional entry for locking, one bit for + * the entry size (PMD) and two more to tell us if the entry is a huge zero + * page (HZP) or an empty entry that is just used for locking. In total four + * special bits. + * + * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and + * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem + * block allocation. */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3) +#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD) -#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK) -#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT)) -#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \ - RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \ - RADIX_TREE_EXCEPTIONAL_ENTRY)) +#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) +#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) +static inline unsigned long dax_radix_sector(void *entry) +{ + return (unsigned long)entry >> RADIX_DAX_SHIFT; +} + +static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) +{ + return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | + ((unsigned long)sector << RADIX_DAX_SHIFT) | + RADIX_DAX_ENTRY_LOCK); +} ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops); @@ -67,6 +79,27 @@ static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return VM_FAULT_FALLBACK; } +#ifdef CONFIG_FS_DAX_PMD +static inline unsigned int dax_radix_order(void *entry) +{ + if ((unsigned long)entry & RADIX_DAX_PMD) + return PMD_SHIFT - PAGE_SHIFT; + return 0; +} +int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, unsigned int flags, struct iomap_ops *ops); +#else +static inline unsigned int dax_radix_order(void *entry) +{ + return 0; +} +static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, unsigned int flags, + struct iomap_ops *ops) +{ + return VM_FAULT_FALLBACK; +} +#endif int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -- cgit From b57d74aff9ab92fbfb7c197c384d1adfa2827b2e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 1 Sep 2016 10:20:33 -0600 Subject: writeback: track if we're sleeping on progress in balance_dirty_pages() Note in the bdi_writeback structure whenever a task ends up sleeping waiting for progress. We can use that information in the lower layers to increase the priority of writes. Signed-off-by: Jens Axboe Reviewed-by: Jan Kara --- include/linux/backing-dev-defs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c357f27d5483..dc5f76d7f648 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -116,6 +116,8 @@ struct bdi_writeback { struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ + unsigned long dirty_sleep; /* last wait */ + struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK -- cgit From 7392b4bb702b05749539ff0936e94976248240c9 Mon Sep 17 00:00:00 2001 From: "monk.liu" Date: Fri, 4 Nov 2016 16:16:09 -0400 Subject: dma-buf: return index of the first signaled fence (v2) Return the index of the first signaled fence. This information is useful in some APIs like Vulkan. v2: rebase on drm-next (fence -> dma_fence) Signed-off-by: monk.liu Signed-off-by: Alex Deucher Cc: Sumit Semwal Signed-off-by: Sumit Semwal [sumits: fix warnings] Link: http://patchwork.freedesktop.org/patch/msgid/1478290570-30982-1-git-send-email-alexander.deucher@amd.com --- include/linux/dma-fence.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index ba60c043a5d3..fcf4b1971eba 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -382,7 +382,8 @@ signed long dma_fence_wait_timeout(struct dma_fence *, bool intr, signed long timeout); signed long dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count, - bool intr, signed long timeout); + bool intr, signed long timeout, + uint32_t *idx); /** * dma_fence_wait - sleep until the fence gets signaled -- cgit From 9e5a7e22951bc12ee45cb617919d57b5efce56b5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 08:12:47 -0600 Subject: blk-mq: export blk_mq_map_queues This will allow SCSI to have a single blk_mq_ops structure that either lets the LLDD map the queues to PCIe MSIx vectors or use the default. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 535ab2e13d2e..6c0fb259581f 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -237,6 +237,7 @@ void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); +int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); /* -- cgit From feb3d79800ece19c18b979c5edd1c28755f59d07 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 8 Nov 2016 15:37:48 +0530 Subject: scsi: ufs-qcom: phy/hcd: Refactoring phy clock handling Add phy clock enable code to phy_power_on/off callbacks, and remove explicit calls to enable these phy clocks from the ufs-qcom hcd driver. Signed-off-by: Vivek Gautam Reviewed-by: Subhash Jadavani Signed-off-by: Martin K. Petersen --- include/linux/phy/phy-qcom-ufs.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h index 9d18e9f948e9..35c070ea6ea3 100644 --- a/include/linux/phy/phy-qcom-ufs.h +++ b/include/linux/phy/phy-qcom-ufs.h @@ -17,22 +17,6 @@ #include "phy.h" -/** - * ufs_qcom_phy_enable_ref_clk() - Enable the phy - * ref clock. - * @phy: reference to a generic phy - * - * returns 0 for success, and non-zero for error. - */ -int ufs_qcom_phy_enable_ref_clk(struct phy *phy); - -/** - * ufs_qcom_phy_disable_ref_clk() - Disable the phy - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_disable_ref_clk(struct phy *phy); - /** * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device * ref clock. @@ -47,8 +31,6 @@ void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); */ void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); -int ufs_qcom_phy_enable_iface_clk(struct phy *phy); -void ufs_qcom_phy_disable_iface_clk(struct phy *phy); int ufs_qcom_phy_start_serdes(struct phy *phy); int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); int ufs_qcom_phy_calibrate_phy(struct phy *phy, bool is_rate_B); -- cgit From 3aeed5b573f97b4525841cc07c1e948227af389f Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 8 Nov 2016 16:34:57 -0800 Subject: Input: synaptics-rmi4 - move IRQ handling to rmi_driver The attn IRQ is related to the chip, rather than the transport, so move all handling of interrupts to the core driver. This also makes sure that there are no races between interrupts and availability of the resources used by the core driver. Signed-off-by: Bjorn Andersson Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index e0aca1476001..5944e6c2470d 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -204,9 +204,11 @@ struct rmi_device_platform_data_spi { * @reset_delay_ms - after issuing a reset command to the touch sensor, the * driver waits a few milliseconds to give the firmware a chance to * to re-initialize. You can override the default wait period here. + * @irq: irq associated with the attn gpio line, or negative */ struct rmi_device_platform_data { int reset_delay_ms; + int irq; struct rmi_device_platform_data_spi spi_data; @@ -352,8 +354,7 @@ struct rmi_driver_data { int rmi_register_transport_device(struct rmi_transport_dev *xport); void rmi_unregister_transport_device(struct rmi_transport_dev *xport); -int rmi_process_interrupt_requests(struct rmi_device *rmi_dev); -int rmi_driver_suspend(struct rmi_device *rmi_dev); -int rmi_driver_resume(struct rmi_device *rmi_dev); +int rmi_driver_suspend(struct rmi_device *rmi_dev, bool enable_wake); +int rmi_driver_resume(struct rmi_device *rmi_dev, bool clear_wake); #endif -- cgit From 2775e523246e11c5ce90b69226c5e67aa43e64a5 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Tue, 8 Nov 2016 16:48:48 -0800 Subject: Input: synaptics-rmi4 - add parameters for dribble packets and palm detect gesture The rmi_f11 driver currently disables dribble packets and the palm detect gesture for all devices. This patch creates a parameter in the 2d sensor platform data for controlling this functionality on a per device basis. For more information on dribble packets: Commit 05ba999fcabb ("HID: rmi: disable dribble packets on Synaptics touchpads") For more information on the palm detect gesture: Commit f097deef59a6 ("HID: rmi: disable palm detect gesture when present") Signed-off-by: Andrew Duggan Reviewed-by: Benjamin Tissoires Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 5944e6c2470d..ac904bb439a5 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -99,6 +99,8 @@ struct rmi_2d_sensor_platform_data { bool topbuttonpad; bool kernel_tracking; int dmax; + int dribble; + int palm_detect; }; /** @@ -116,14 +118,17 @@ struct rmi_f30_data { bool disable; }; -/** - * struct rmi_f01_power - override default power management settings. - * + +/* + * Set the state of a register + * DEFAULT - use the default value set by the firmware config + * OFF - explicitly disable the register + * ON - explicitly enable the register */ -enum rmi_f01_nosleep { - RMI_F01_NOSLEEP_DEFAULT = 0, - RMI_F01_NOSLEEP_OFF = 1, - RMI_F01_NOSLEEP_ON = 2 +enum rmi_reg_state { + RMI_REG_STATE_DEFAULT = 0, + RMI_REG_STATE_OFF = 1, + RMI_REG_STATE_ON = 2 }; /** @@ -143,7 +148,7 @@ enum rmi_f01_nosleep { * when the touch sensor is in doze mode, in units of 10ms. */ struct rmi_f01_power_management { - enum rmi_f01_nosleep nosleep; + enum rmi_reg_state nosleep; u8 wakeup_threshold; u8 doze_holdoff; u8 doze_interval; -- cgit From 20e407e195b29a4f5a18d713a61f54a75f992bd5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2016 17:15:01 -0800 Subject: genirq/affinity: Introduce struct irq_affinity Some drivers (various network and RDMA adapter for example) have a MSI-X vector layout where most of the vectors are used for I/O queues and should have CPU affinity assigned to them, but some (usually 1 but sometimes more) at the beginning or end are used for low-performance admin or configuration work and should not have any explicit affinity assigned to them. Add a new irq_affinity structure, which will be passed through a variant of pci_irq_alloc_vectors that allows to specify these requirements (and is extensible to any future quirks in that area) so that the core IRQ affinity algorithm can take this quirks into account. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Acked-by: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/1478654107-7384-2-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 72f0721f75e7..6b5268688a81 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -232,6 +232,18 @@ struct irq_affinity_notify { void (*release)(struct kref *ref); }; +/** + * struct irq_affinity - Description for automatic irq affinity assignements + * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of + * the MSI(-X) vector space + * @post_vectors: Don't apply affinity to @post_vectors at end of + * the MSI(-X) vector space + */ +struct irq_affinity { + int pre_vectors; + int post_vectors; +}; + #if defined(CONFIG_SMP) extern cpumask_var_t irq_default_affinity; -- cgit From 212bd846223c718b6577d4df16fd8d05a55ad914 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2016 17:15:02 -0800 Subject: genirq/affinity: Handle pre/post vectors in irq_calc_affinity_vectors() Only calculate the affinity for the main I/O vectors, and skip the pre or post vectors specified by struct irq_affinity. Also remove the irq_affinity cpumask argument that has never been used. If we ever need it in the future we can pass it through struct irq_affinity. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/1478654107-7384-3-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6b5268688a81..9081f23bc0ff 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -291,7 +291,7 @@ extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct cpumask *irq_create_affinity_masks(const struct cpumask *affinity, int nvec); -int irq_calc_affinity_vectors(const struct cpumask *affinity, int maxvec); +int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ @@ -331,7 +331,7 @@ irq_create_affinity_masks(const struct cpumask *affinity, int nvec) } static inline int -irq_calc_affinity_vectors(const struct cpumask *affinity, int maxvec) +irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd) { return maxvec; } -- cgit From 67c93c218dc5d1b45d547771f1fdb44a381e1faf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2016 17:15:03 -0800 Subject: genirq/affinity: Handle pre/post vectors in irq_create_affinity_masks() Only calculate the affinity for the main I/O vectors, and skip the pre or post vectors specified by struct irq_affinity. Also remove the irq_affinity cpumask argument that has never been used. If we ever need it in the future we can pass it through struct irq_affinity. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Bjorn Helgaas Acked-by: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/1478654107-7384-4-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9081f23bc0ff..53144e78a369 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -290,7 +290,7 @@ extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); -struct cpumask *irq_create_affinity_masks(const struct cpumask *affinity, int nvec); +struct cpumask *irq_create_affinity_masks(int nvec, const struct irq_affinity *affd); int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ @@ -325,7 +325,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) } static inline struct cpumask * -irq_create_affinity_masks(const struct cpumask *affinity, int nvec) +irq_create_affinity_masks(int nvec, const struct irq_affinity *affd) { return NULL; } -- cgit From 402723ad5c625ee052432698ae5e56b02d38d4ec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2016 17:15:05 -0800 Subject: PCI/MSI: Provide pci_alloc_irq_vectors_affinity() This is a variant of pci_alloc_irq_vectors() that allows passing a struct irq_affinity to provide fine-grained IRQ affinity control. For now this means being able to exclude vectors at the beginning or end of the MSI vector space, but it could also be used for any other quirks needed in the future (e.g. more vectors than CPUs, or excluding CPUs from the spreading). Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Acked-by: Bjorn Helgaas Acked-by: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/1478654107-7384-6-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/pci.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e49f70dbd9b..7090f5ff7252 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -244,6 +244,7 @@ struct pci_cap_saved_state { struct pci_cap_saved_data cap; }; +struct irq_affinity; struct pcie_link_state; struct pci_vpd; struct pci_sriov; @@ -1310,8 +1311,10 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev, return rc; return 0; } -int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, - unsigned int max_vecs, unsigned int flags); +int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags, + const struct irq_affinity *affd); + void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); @@ -1339,14 +1342,17 @@ static inline int pci_enable_msix_range(struct pci_dev *dev, static inline int pci_enable_msix_exact(struct pci_dev *dev, struct msix_entry *entries, int nvec) { return -ENOSYS; } -static inline int pci_alloc_irq_vectors(struct pci_dev *dev, - unsigned int min_vecs, unsigned int max_vecs, - unsigned int flags) + +static inline int +pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags, + const struct irq_affinity *aff_desc) { if (min_vecs > 1) return -EINVAL; return 1; } + static inline void pci_free_irq_vectors(struct pci_dev *dev) { } @@ -1364,6 +1370,14 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, } #endif +static inline int +pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags) +{ + return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, flags, + NULL); +} + #ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; extern bool pcie_ports_auto; -- cgit From 0cf71b04467bc34063cecae577f12481da6cc565 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2016 17:15:06 -0800 Subject: PCI: Remove the irq_affinity mask from struct pci_dev This has never been used, and now is totally unreferenced. Nuke it. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Acked-by: Bjorn Helgaas Acked-by: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/1478654107-7384-7-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 7090f5ff7252..f2ba6ac21c75 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -333,7 +333,6 @@ struct pci_dev { * directly, use the values stored here. They might be different! */ unsigned int irq; - struct cpumask *irq_affinity; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ bool match_driver; /* Skip attaching driver */ -- cgit From 67db3e4bfbc90657c7be840aad5585be46240d6f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Nov 2016 11:54:32 -0700 Subject: tcp: no longer hold ehash lock while calling tcp_get_info() We had various problems in the past in tcp_get_info() and used specific synchronization to avoid deadlocks. We would like to add more instrumentation points for TCP, and avoiding grabing socket lock in tcp_getinfo() was too costly. Being able to lock the socket allows to provide consistent set of fields. inet_diag_dump_icsk() can make sure ehash locks are not held any more when tcp_get_info() is called. We can remove syncp added in commit d654976cbf85 ("tcp: fix a potential deadlock in tcp_get_info()"), but we need to use lock_sock_fast() instead of spin_lock_bh() since TCP input path can now be run from process context. Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Acked-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a17ae7b85218..32a7c7e35b71 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -176,8 +176,6 @@ struct tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ - struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */ - u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ -- cgit From 5a3c7805c444d9d55f302a4b3930e8758be13fab Mon Sep 17 00:00:00 2001 From: Joachim Eastwood Date: Sat, 5 Nov 2016 14:04:52 +0100 Subject: Revert "net: stmmac: allow to split suspend/resume from init/exit callbacks" Instead of adding hooks inside stmmac_platform it is better to just use the standard PM callbacks within the specific dwmac-driver. This only used by the dwmac-rk driver. This reverts commit cecbc5563a02 ("stmmac: allow to split suspend/resume from init/exit callbacks"). Signed-off-by: Joachim Eastwood Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 705840e0438f..3537fb33cc90 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -135,8 +135,6 @@ struct plat_stmmacenet_data { void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); - void (*suspend)(struct platform_device *pdev, void *priv); - void (*resume)(struct platform_device *pdev, void *priv); void *bsp_priv; struct stmmac_axi *axi; int has_gmac4; -- cgit From c9f1b073d0d750ccf8b30b272d1d76479f4cccbc Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 7 Nov 2016 15:14:44 +0200 Subject: net/mlx5: Add creation flags when adding new flow table When creating flow tables, allow the caller to specify creation flags. Currently no flags are used and as such this patch doesn't add any new functionality. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0dcd287f4bd0..ab1a5fd2e995 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -42,6 +42,10 @@ enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, }; +enum { + MLX5_FLOW_TABLE_TUNNEL_EN = BIT(0), +}; + #define LEFTOVERS_RULE_NUM 2 static inline void build_leftovers_ft_param(int *priority, int *n_ent, @@ -97,13 +101,15 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, int prio, int num_flow_table_entries, int max_num_groups, - u32 level); + u32 level, + u32 flags); struct mlx5_flow_table * mlx5_create_flow_table(struct mlx5_flow_namespace *ns, int prio, int num_flow_table_entries, - u32 level); + u32 level, + u32 flags); struct mlx5_flow_table * mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, int prio, -- cgit From 66958ed906b87816314c0517f05fe0b5766ec7fe Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 7 Nov 2016 15:14:45 +0200 Subject: net/mlx5: Support encap id when setting new steering entry In order to support steering rules which add encapsulation headers, encap_id parameter is needed. Add new mlx5_flow_act struct which holds action related parameter: action, flow_tag and encap_id. Use mlx5_flow_act struct when adding a new steering rule. This patch doesn't change any functionality. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index ab1a5fd2e995..949b24b6c479 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -130,14 +130,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_flow_act { + u32 action; + u32 flow_tag; + u32 encap_id; +}; + /* Single destination per rule. * Group ID is implied by the match criteria. */ struct mlx5_flow_handle * mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_spec *spec, - u32 action, - u32 flow_tag, + struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, int dest_num); void mlx5_del_flow_rules(struct mlx5_flow_handle *fr); -- cgit From 72478a0cc4025e16f68672844ebebf60524e1668 Mon Sep 17 00:00:00 2001 From: Milo Kim Date: Fri, 28 Oct 2016 21:37:02 +0900 Subject: mfd: tps65217: Fix mismatched interrupt number Enum value of 'tps65217_irq_type' is not matched with DT parsed hwirq number[*]. The MFD driver gets the IRQ data by referencing hwirq, but the value is different. So, irq_to_tps65217_irq() returns mismatched IRQ data. Eventually, the power button driver enables not PB but USB interrupt when it is probed. According to the TPS65217 register map[**], USB interrupt is the LSB. This patch defines synchronized IRQ value. [*] include/dt-bindings/mfd/tps65217.h [**] http://www.ti.com/lit/ds/symlink/tps65217.pdf Signed-off-by: Milo Kim Signed-off-by: Tony Lindgren --- include/linux/mfd/tps65217.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 4ccda8969639..3cbec4b2496a 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -234,12 +234,11 @@ struct tps65217_bl_pdata { int dft_brightness; }; -enum tps65217_irq_type { - TPS65217_IRQ_PB, - TPS65217_IRQ_AC, - TPS65217_IRQ_USB, - TPS65217_NUM_IRQ -}; +/* Interrupt numbers */ +#define TPS65217_IRQ_USB 0 +#define TPS65217_IRQ_AC 1 +#define TPS65217_IRQ_PB 2 +#define TPS65217_NUM_IRQ 3 /** * struct tps65217_board - packages regulator init data -- cgit From fc4d24c9b47150245b3eb5bebc2ad4764c754ef4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:49:57 +0100 Subject: fs/buffer: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: linux-fsdevel@vger.kernel.org Cc: Alexander Viro Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-2-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index afe641c02dca..69b74fa0da60 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -30,6 +30,7 @@ enum cpuhp_state { CPUHP_ACPI_CPUDRV_DEAD, CPUHP_S390_PFAULT_DEAD, CPUHP_BLK_MQ_DEAD, + CPUHP_FS_BUFF_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 90b14889d2f9b29d7e5b4b2d36251c13ce3dd13f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:49:58 +0100 Subject: kernel/printk: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Andrew Morton Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-3-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 69b74fa0da60..4174083280d7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -31,6 +31,7 @@ enum cpuhp_state { CPUHP_S390_PFAULT_DEAD, CPUHP_BLK_MQ_DEAD, CPUHP_FS_BUFF_DEAD, + CPUHP_PRINTK_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 308167fcb330296fc80505a6b11ba0661f38a4cc Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:49:59 +0100 Subject: mm/memcg: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Michal Hocko Cc: linux-mm@kvack.org Cc: rt@linutronix.de Cc: Johannes Weiner Cc: cgroups@vger.kernel.org Link: http://lkml.kernel.org/r/20161103145021.28528-4-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4174083280d7..c622ab349af3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -32,6 +32,7 @@ enum cpuhp_state { CPUHP_BLK_MQ_DEAD, CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, + CPUHP_MM_MEMCQ_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 5588f5afb4cfc33eb377b751ba4b97184373e8d6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:00 +0100 Subject: lib/percpu_counter: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-5-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c622ab349af3..04e5f99ffc70 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -33,6 +33,7 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, + CPUHP_PERCPU_CNT_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From d544abd5ff7d8b07c0c67682a63e4939c3c82914 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:01 +0100 Subject: lib/radix-tree: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Andrew Morton Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-6-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 04e5f99ffc70..89310fb1031d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -34,6 +34,7 @@ enum cpuhp_state { CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, CPUHP_PERCPU_CNT_DEAD, + CPUHP_RADIX_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 005fd4bbef168e9dea896085b001d64369e9834a Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:02 +0100 Subject: mm/page_alloc: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: linux-mm@kvack.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-7-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 89310fb1031d..31c58f6ec3c6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -35,6 +35,7 @@ enum cpuhp_state { CPUHP_MM_MEMCQ_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, + CPUHP_PAGE_ALLOC_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From f0bf90def3528cebed45ebd81d9b5d0fa17d7422 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:04 +0100 Subject: net/dev: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-9-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 31c58f6ec3c6..394eb7ed53be 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -36,6 +36,7 @@ enum cpuhp_state { CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC_DEAD, + CPUHP_NET_DEV_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From a4fc1bfc42062e8bc7b2271a90d17403b096ce5d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:05 +0100 Subject: net/flowcache: Convert to hotplug state machine Install the callbacks via the state machine. Use multi state support to avoid custom list handling for the multiple instances. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Steffen Klassert Cc: Herbert Xu Cc: netdev@vger.kernel.org Cc: rt@linutronix.de Cc: "David S. Miller" Link: http://lkml.kernel.org/r/20161103145021.28528-10-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 394eb7ed53be..86b940f19df8 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -56,6 +56,7 @@ enum cpuhp_state { CPUHP_ARM_SHMOBILE_SCU_PREPARE, CPUHP_SH_SH3X_PREPARE, CPUHP_BLK_MQ_PREPARE, + CPUHP_NET_FLOW_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 38643a0e691ec947d311eb2db011b289cf95014e Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Nov 2016 15:50:09 +0100 Subject: drivers base/topology: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. No functional change Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161103145021.28528-14-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 86b940f19df8..3410d83cc2e2 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -57,6 +57,7 @@ enum cpuhp_state { CPUHP_SH_SH3X_PREPARE, CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, + CPUHP_TOPOLOGY_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 9484ab1bf4464faae695321dd4fa66365beda74e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 10 Nov 2016 10:26:50 +1100 Subject: dax: Introduce IOMAP_FAULT flag Introduce a flag telling iomap operations whether they are handling a fault or other IO. That may influence behavior wrt inode size and similar things. Signed-off-by: Jan Kara Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index e63e288dee83..b9e7b8ec8c1d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -44,6 +44,7 @@ struct iomap { */ #define IOMAP_WRITE (1 << 0) #define IOMAP_ZERO (1 << 1) +#define IOMAP_FAULT (1 << 3) /* mapping for page fault */ struct iomap_ops { /* -- cgit From 1ababeba4a21f3dba3da3523c670b207fb2feb62 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:39 +0100 Subject: ipv6: implement dataplane support for rthdr type 4 (Segment Routing Header) Implement minimal support for processing of SR-enabled packets as described in https://tools.ietf.org/html/draft-ietf-6man-segment-routing-header-02. This patch implements the following operations: - Intermediate segment endpoint: incrementation of active segment and rerouting. - Egress for SR-encapsulated packets: decapsulation of outer IPv6 header + SRH and routing of inner packet. - Cleanup flag support for SR-inlined packets: removal of SRH if we are the penultimate segment endpoint. A per-interface sysctl seg6_enabled is provided, to accept/deny SR-enabled packets. Default is deny. This patch does not provide support for HMAC-signed packets. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/linux/seg6.h | 6 ++++++ 2 files changed, 7 insertions(+) create mode 100644 include/linux/seg6.h (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1afb6e8d35c3..68d3f71f0abf 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -64,6 +64,7 @@ struct ipv6_devconf { } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; + __s32 seg6_enabled; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/seg6.h b/include/linux/seg6.h new file mode 100644 index 000000000000..7a66d2b4c5a6 --- /dev/null +++ b/include/linux/seg6.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_H +#define _LINUX_SEG6_H + +#include + +#endif -- cgit From 915d7e5e5930b4f01d0971d93b9b25ed17d221aa Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:40 +0100 Subject: ipv6: sr: add code base for control plane support of SR-IPv6 This patch adds the necessary hooks and structures to provide support for SR-IPv6 control plane, essentially the Generic Netlink commands that will be used for userspace control over the Segment Routing kernel structures. The genetlink commands provide control over two different structures: tunnel source and HMAC data. The tunnel source is the source address that will be used by default when encapsulating packets into an outer IPv6 header + SRH. If the tunnel source is set to :: then an address of the outgoing interface will be selected as the source. The HMAC commands currently just return ENOTSUPP and will be implemented in a future patch. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_genl.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/seg6_genl.h (limited to 'include/linux') diff --git a/include/linux/seg6_genl.h b/include/linux/seg6_genl.h new file mode 100644 index 000000000000..d6c3fb4f3734 --- /dev/null +++ b/include/linux/seg6_genl.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_GENL_H +#define _LINUX_SEG6_GENL_H + +#include + +#endif -- cgit From 6c8702c60b88651072460f3f4026c7dfe2521d12 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:41 +0100 Subject: ipv6: sr: add support for SRH encapsulation and injection with lwtunnels This patch creates a new type of interfaceless lightweight tunnel (SEG6), enabling the encapsulation and injection of SRH within locally emitted packets and forwarded packets. >From a configuration viewpoint, a seg6 tunnel would be configured as follows: ip -6 ro ad fc00::1/128 encap seg6 mode encap segs fc42::1,fc42::2,fc42::3 dev eth0 Any packet whose destination address is fc00::1 would thus be encapsulated within an outer IPv6 header containing the SRH with three segments, and would actually be routed to the first segment of the list. If `mode inline' was specified instead of `mode encap', then the SRH would be directly inserted after the IPv6 header without outer encapsulation. The inline mode is only available if CONFIG_IPV6_SEG6_INLINE is enabled. This feature was made configurable because direct header insertion may break several mechanisms such as PMTUD or IPSec AH. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_iptunnel.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/seg6_iptunnel.h (limited to 'include/linux') diff --git a/include/linux/seg6_iptunnel.h b/include/linux/seg6_iptunnel.h new file mode 100644 index 000000000000..5377cf6a5a02 --- /dev/null +++ b/include/linux/seg6_iptunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_IPTUNNEL_H +#define _LINUX_SEG6_IPTUNNEL_H + +#include + +#endif -- cgit From bf355b8d2c30a289232042cacc1cfaea4923936c Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Tue, 8 Nov 2016 14:57:42 +0100 Subject: ipv6: sr: add core files for SR HMAC support This patch adds the necessary functions to compute and check the HMAC signature of an SR-enabled packet. Two HMAC algorithms are supported: hmac(sha1) and hmac(sha256). In order to avoid dynamic memory allocation for each HMAC computation, a per-cpu ring buffer is allocated for this purpose. A new per-interface sysctl called seg6_require_hmac is added, allowing a user-defined policy for processing HMAC-signed SR-enabled packets. A value of -1 means that the HMAC field will always be ignored. A value of 0 means that if an HMAC field is present, its validity will be enforced (the packet is dropped is the signature is incorrect). Finally, a value of 1 means that any SR-enabled packet that does not contain an HMAC signature or whose signature is incorrect will be dropped. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +++ include/linux/seg6_hmac.h | 6 ++++++ 2 files changed, 9 insertions(+) create mode 100644 include/linux/seg6_hmac.h (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 68d3f71f0abf..93756585521f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -65,6 +65,9 @@ struct ipv6_devconf { __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; +#ifdef CONFIG_IPV6_SEG6_HMAC + __s32 seg6_require_hmac; +#endif struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/seg6_hmac.h b/include/linux/seg6_hmac.h new file mode 100644 index 000000000000..da437ebdc6cd --- /dev/null +++ b/include/linux/seg6_hmac.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_HMAC_H +#define _LINUX_SEG6_HMAC_H + +#include + +#endif -- cgit From 149d6ad83663b4820ca09c9d40b1eea7f5c22c2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Nov 2016 11:07:28 -0800 Subject: net: napi_hash_add() is no longer exported There are no more users except from net/core/dev.c napi_hash_add() can now be static. Signed-off-by: Eric Dumazet Cc: Michael Chan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 66fd61c681d9..d64135a0ab71 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -467,17 +467,6 @@ static inline void napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } -/** - * napi_hash_add - add a NAPI to global hashtable - * @napi: NAPI context - * - * Generate a new napi_id and store a @napi under it in napi_hash. - * Used for busy polling (CONFIG_NET_RX_BUSY_POLL). - * Note: This is normally automatically done from netif_napi_add(), - * so might disappear in a future Linux version. - */ -void napi_hash_add(struct napi_struct *napi); - /** * napi_hash_del - remove a NAPI from global table * @napi: NAPI context -- cgit From d8d26354191399627bac9cf0da0667b0f5178686 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Tue, 8 Nov 2016 22:49:16 +0100 Subject: ptp: Introduce a high resolution frequency adjustment method. The internal PTP Hardware Clock (PHC) interface limits the resolution for frequency adjustments to one part per billion. However, some hardware devices allow finer adjustment, and making use of the increased resolution improves synchronization measurably on such devices. This patch adds an alternative method that allows finer frequency tuning by passing the scaled ppm value to PHC drivers. This value comes from user space, and it has a resolution of about 0.015 ppb. We also deprecate the older method, anticipating its removal once existing drivers have been converted over. Signed-off-by: Richard Cochran Suggested-by: Ulrik De Bie Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 5ad54fc66cf0..b76d47aba564 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -58,7 +58,14 @@ struct system_device_crosststamp; * * clock operations * + * @adjfine: Adjusts the frequency of the hardware clock. + * parameter scaled_ppm: Desired frequency offset from + * nominal frequency in parts per million, but with a + * 16 bit binary fractional field. + * * @adjfreq: Adjusts the frequency of the hardware clock. + * This method is deprecated. New drivers should implement + * the @adjfine method instead. * parameter delta: Desired frequency offset from nominal frequency * in parts per billion * @@ -108,6 +115,7 @@ struct ptp_clock_info { int n_pins; int pps; struct ptp_pin_desc *pin_config; + int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); -- cgit From 7bdc9650f03604b06ba7434fab694e8ae8ca782d Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 19 Oct 2016 19:40:02 -0700 Subject: remoteproc: Introduce subdevices A subdevice is an abstract entity that can be used to tie actions to the booting and shutting down of a remote processor. The subdevice object is expected to be embedded in concrete implementations, allowing for a variety of use cases to be implemented. Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 940e4cf2ac48..f6d5e66854e4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -400,6 +400,7 @@ enum rproc_crash_type { * @firmware_loading_complete: marks e/o asynchronous firmware loading * @bootaddr: address of first instruction to boot rproc with (optional) * @rvdevs: list of remote virtio devices + * @subdevs: list of subdevices, to following the running state * @notifyids: idr for dynamically assigning rproc-wide unique notify ids * @index: index of this rproc device * @crash_handler: workqueue for handling a crash @@ -431,6 +432,7 @@ struct rproc { struct completion firmware_loading_complete; u32 bootaddr; struct list_head rvdevs; + struct list_head subdevs; struct idr notifyids; int index; struct work_struct crash_handler; @@ -444,6 +446,19 @@ struct rproc { bool auto_boot; }; +/** + * struct rproc_subdev - subdevice tied to a remoteproc + * @node: list node related to the rproc subdevs list + * @probe: probe function, called as the rproc is started + * @remove: remove function, called as the rproc is stopped + */ +struct rproc_subdev { + struct list_head node; + + int (*probe)(struct rproc_subdev *subdev); + void (*remove)(struct rproc_subdev *subdev); +}; + /* we currently support only two vrings per rvdev */ #define RVDEV_NUM_VRINGS 2 @@ -511,4 +526,11 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) return rvdev->rproc; } +void rproc_add_subdev(struct rproc *rproc, + struct rproc_subdev *subdev, + int (*probe)(struct rproc_subdev *subdev), + void (*remove)(struct rproc_subdev *subdev)); + +void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); + #endif /* REMOTEPROC_H */ -- cgit From c97db7cc7778e34a53b42d58c766f0ec0e30d580 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Sep 2016 14:57:19 +0800 Subject: base: soc: Introduce soc_device_match() interface We keep running into cases where device drivers want to know the exact version of the a SoC they are currently running on. In the past, this has usually been done through a vendor specific API that can be called by a driver, or by directly accessing some kind of version register that is not part of the device itself but that belongs to a global register area of the chip. Common reasons for doing this include: - A machine is not using devicetree or similar for passing data about on-chip devices, but just announces their presence using boot-time platform devices, and the machine code itself does not care about the revision. - There is existing firmware or boot loaders with existing DT binaries with generic compatible strings that do not identify the particular revision of each device, but the driver knows which SoC revisions include which part. - A prerelease version of a chip has some quirks and we are using the same version of the bootloader and the DT blob on both the prerelease and the final version. An update of the DT binding seems inappropriate because that would involve maintaining multiple copies of the dts and/or bootloader. This patch introduces the soc_device_match() interface that is meant to work like of_match_node() but instead of identifying the version of a device, it identifies the SoC itself using a vendor-agnostic interface. Unlike of_match_node(), we do not do an exact string compare but instead use glob_match() to allow wildcards in strings. Signed-off-by: Arnd Bergmann Signed-off-by: Yangbo Lu Signed-off-by: Geert Uytterhoeven Acked-by: Greg Kroah-Hartman --- include/linux/sys_soc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sys_soc.h b/include/linux/sys_soc.h index 2739ccb69571..9f5eb06f9fd8 100644 --- a/include/linux/sys_soc.h +++ b/include/linux/sys_soc.h @@ -13,6 +13,7 @@ struct soc_device_attribute { const char *family; const char *revision; const char *soc_id; + const void *data; }; /** @@ -34,4 +35,6 @@ void soc_device_unregister(struct soc_device *soc_dev); */ struct device *soc_device_to_device(struct soc_device *soc); +const struct soc_device_attribute *soc_device_match( + const struct soc_device_attribute *matches); #endif /* __SOC_BUS_H */ -- cgit From da65a1589dacc7ec44ea0557a14d70a39d991f32 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Oct 2016 15:13:15 +0200 Subject: base: soc: Provide a dummy implementation of soc_device_match() Provide a dummy implementation of soc_device_match(), to allow compiling drivers that may be used on SoCs both with and without CONFIG_SOC_BUS, and for compile testing. Signed-off-by: Geert Uytterhoeven --- include/linux/sys_soc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sys_soc.h b/include/linux/sys_soc.h index 9f5eb06f9fd8..bed223b70217 100644 --- a/include/linux/sys_soc.h +++ b/include/linux/sys_soc.h @@ -35,6 +35,12 @@ void soc_device_unregister(struct soc_device *soc_dev); */ struct device *soc_device_to_device(struct soc_device *soc); +#ifdef CONFIG_SOC_BUS const struct soc_device_attribute *soc_device_match( const struct soc_device_attribute *matches); +#else +static inline const struct soc_device_attribute *soc_device_match( + const struct soc_device_attribute *matches) { return NULL; } +#endif + #endif /* __SOC_BUS_H */ -- cgit From 2da16a6948ca8f025e2c226ea4fc32baa6b90f27 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 10 Nov 2016 11:17:25 +0100 Subject: netfilter: ipset: Remove extra whitespaces in ip_set.h Remove unnecessary whitespaces. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 83b9a2e0d8d4..5b1fd090f34b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -336,14 +336,15 @@ ip_set_update_counter(struct ip_set_counter *counter, static inline void ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) { - mext->skbmark = skbinfo->skbmark; - mext->skbmarkmask = skbinfo->skbmarkmask; - mext->skbprio = skbinfo->skbprio; - mext->skbqueue = skbinfo->skbqueue; + mext->skbmark = skbinfo->skbmark; + mext->skbmarkmask = skbinfo->skbmarkmask; + mext->skbprio = skbinfo->skbprio; + mext->skbqueue = skbinfo->skbqueue; } + static inline bool ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo) { -- cgit From da9fbfa76f32a031cb70b11e9fa650e30c85d040 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 10 Nov 2016 11:24:15 +0100 Subject: netfilter: ipset: Mark some helper args as const. Mark some of the helpers arguments as const. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 4 ++-- include/linux/netfilter/ipset/ip_set_comment.h | 2 +- include/linux/netfilter/ipset/ip_set_timeout.h | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 5b1fd090f34b..524467f933bf 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -346,7 +346,7 @@ ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, } static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo) +ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) { /* Send nonzero parameters only */ return ((skbinfo->skbmark || skbinfo->skbmarkmask) && @@ -373,7 +373,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } static inline bool -ip_set_put_counter(struct sk_buff *skb, struct ip_set_counter *counter) +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) { return nla_put_net64(skb, IPSET_ATTR_BYTES, cpu_to_be64(ip_set_get_bytes(counter)), diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8d0248525957..bae5c7609be2 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,7 +43,7 @@ ip_set_init_comment(struct ip_set_comment *comment, /* Used only when dumping a set, protected by rcu_read_lock_bh() */ static inline int -ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment) +ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 1d6a935c1ac5..bfb3531fd88a 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -40,7 +40,7 @@ ip_set_timeout_uget(struct nlattr *tb) } static inline bool -ip_set_timeout_expired(unsigned long *t) +ip_set_timeout_expired(const unsigned long *t) { return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); } @@ -63,7 +63,7 @@ ip_set_timeout_set(unsigned long *timeout, u32 value) } static inline u32 -ip_set_timeout_get(unsigned long *timeout) +ip_set_timeout_get(const unsigned long *timeout) { return *timeout == IPSET_ELEM_PERMANENT ? 0 : jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; -- cgit From 7ffea37957b900422ce8b82e9651f7a0a6fac733 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 10 Nov 2016 11:31:03 +0100 Subject: netfilter: ipset: Headers file cleanup Group counter helper functions together. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 42 +++++++++++++++++----------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 524467f933bf..1ea28e30a6dd 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -334,6 +334,27 @@ ip_set_update_counter(struct ip_set_counter *counter, } } +static inline bool +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter)), + IPSET_ATTR_PAD) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter)), + IPSET_ATTR_PAD); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + static inline void ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext, @@ -372,27 +393,6 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, skbinfo->skbqueue = ext->skbqueue; } -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} - -static inline void -ip_set_init_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext) -{ - if (ext->bytes != ULLONG_MAX) - atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); - if (ext->packets != ULLONG_MAX) - atomic64_set(&(counter)->packets, (long long)(ext->packets)); -} - /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ -- cgit From bec810d973003b30bc477146904af6bd93fd2df8 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 5 May 2015 17:13:28 +0200 Subject: netfilter: ipset: Improve skbinfo get/init helpers Use struct ip_set_skbinfo in struct ip_set_ext instead of open coded fields and assign structure members in get/init helpers instead of copying members one by one. Explicitly note that struct ip_set_skbinfo must be padded to prevent non-aligned access in the extension blob. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 30 +++++++++++------------------- 1 file changed, 11 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 1ea28e30a6dd..780262124632 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -92,17 +92,6 @@ struct ip_set_ext_type { extern const struct ip_set_ext_type ip_set_extensions[]; -struct ip_set_ext { - u64 packets; - u64 bytes; - u32 timeout; - u32 skbmark; - u32 skbmarkmask; - u32 skbprio; - u16 skbqueue; - char *comment; -}; - struct ip_set_counter { atomic64_t bytes; atomic64_t packets; @@ -122,6 +111,15 @@ struct ip_set_skbinfo { u32 skbmarkmask; u32 skbprio; u16 skbqueue; + u16 __pad; +}; + +struct ip_set_ext { + struct ip_set_skbinfo skbinfo; + u64 packets; + u64 bytes; + char *comment; + u32 timeout; }; struct ip_set; @@ -360,10 +358,7 @@ ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { - mext->skbmark = skbinfo->skbmark; - mext->skbmarkmask = skbinfo->skbmarkmask; - mext->skbprio = skbinfo->skbprio; - mext->skbqueue = skbinfo->skbqueue; + mext->skbinfo = *skbinfo; } static inline bool @@ -387,10 +382,7 @@ static inline void ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext) { - skbinfo->skbmark = ext->skbmark; - skbinfo->skbmarkmask = ext->skbmarkmask; - skbinfo->skbprio = ext->skbprio; - skbinfo->skbqueue = ext->skbqueue; + *skbinfo = ext->skbinfo; } /* Netlink CB args */ -- cgit From 1d0d6bd61d495d271b9774a15fbea93e4875474b Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 6 May 2015 07:27:28 +0200 Subject: netfilter: ipset: Use kmalloc() in comment extension helper Allocate memory with kmalloc() rather than kzalloc(): the string is immediately initialized so it is unnecessary to zero out the allocated memory area. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set_comment.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index bae5c7609be2..5444b1bbe656 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -34,7 +34,7 @@ ip_set_init_comment(struct ip_set_comment *comment, return; if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) len = IPSET_MAX_COMMENT_SIZE; - c = kzalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); if (unlikely(!c)) return; strlcpy(c->str, ext->comment, len + 1); -- cgit From 57982edc2739b4473868e7579c0185270468bae1 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 10 Oct 2016 21:34:56 +0200 Subject: netfilter: ipset: Split extensions into separate files Cleanup to separate all extensions into individual files. Ported from a patch proposed by Sergey Popovich . Suggested-by: Sergey Popovich Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 95 +------------------------- include/linux/netfilter/ipset/ip_set_counter.h | 75 ++++++++++++++++++++ include/linux/netfilter/ipset/ip_set_skbinfo.h | 46 +++++++++++++ 3 files changed, 123 insertions(+), 93 deletions(-) create mode 100644 include/linux/netfilter/ipset/ip_set_counter.h create mode 100644 include/linux/netfilter/ipset/ip_set_skbinfo.h (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 780262124632..b5bd0fb3d07b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -292,99 +292,6 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags)); } -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } - if (flags & IPSET_FLAG_MATCH_COUNTERS) { - mext->packets = ip_set_get_packets(counter); - mext->bytes = ip_set_get_bytes(counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} - -static inline void -ip_set_init_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext) -{ - if (ext->bytes != ULLONG_MAX) - atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); - if (ext->packets != ULLONG_MAX) - atomic64_set(&(counter)->packets, (long long)(ext->packets)); -} - -static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - -static inline void -ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext) -{ - *skbinfo = ext->skbinfo; -} - /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ @@ -539,6 +446,8 @@ bitmap_bytes(u32 a, u32 b) #include #include +#include +#include int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h new file mode 100644 index 000000000000..bb6fba480118 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_counter.h @@ -0,0 +1,75 @@ +#ifndef _IP_SET_COUNTER_H +#define _IP_SET_COUNTER_H + +/* Copyright (C) 2015 Jozsef Kadlecsik + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifdef __KERNEL__ + +static inline void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static inline void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static inline u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static inline u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static inline void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } + if (flags & IPSET_FLAG_MATCH_COUNTERS) { + mext->packets = ip_set_get_packets(counter); + mext->bytes = ip_set_get_bytes(counter); + } +} + +static inline bool +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter)), + IPSET_ATTR_PAD) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter)), + IPSET_ATTR_PAD); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + +#endif /* __KERNEL__ */ +#endif /* _IP_SET_COUNTER_H */ diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h new file mode 100644 index 000000000000..29d7ef2bc3fa --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_skbinfo.h @@ -0,0 +1,46 @@ +#ifndef _IP_SET_SKBINFO_H +#define _IP_SET_SKBINFO_H + +/* Copyright (C) 2015 Jozsef Kadlecsik + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifdef __KERNEL__ + +static inline void +ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + mext->skbinfo = *skbinfo; +} + +static inline bool +ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) +{ + /* Send nonzero parameters only */ + return ((skbinfo->skbmark || skbinfo->skbmarkmask) && + nla_put_net64(skb, IPSET_ATTR_SKBMARK, + cpu_to_be64((u64)skbinfo->skbmark << 32 | + skbinfo->skbmarkmask), + IPSET_ATTR_PAD)) || + (skbinfo->skbprio && + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + cpu_to_be32(skbinfo->skbprio))) || + (skbinfo->skbqueue && + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + cpu_to_be16(skbinfo->skbqueue))); +} + +static inline void +ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext) +{ + *skbinfo = ext->skbinfo; +} + +#endif /* __KERNEL__ */ +#endif /* _IP_SET_SKBINFO_H */ -- cgit From 837a90eab67edfa464dcc0ddef193449d23da408 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 10 Oct 2016 21:52:51 +0200 Subject: netfilter: ipset: Regroup ip_set_put_extensions and add extern Cleanup: group ip_set_put_extensions and ip_set_get_extensions together and add missing extern. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index b5bd0fb3d07b..7a218eb74887 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -331,6 +331,8 @@ extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, size_t align); extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext); +extern int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, + const void *e, bool active); static inline int ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) @@ -449,10 +451,6 @@ bitmap_bytes(u32 a, u32 b) #include #include -int -ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, - const void *e, bool active); - #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, \ .timeout = ip_set_adt_opt_timeout(opt, set) } -- cgit From 702b71e7c666a1c9be9d49e8cd173f0d4d1e859f Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 10 Oct 2016 22:07:41 +0200 Subject: netfilter: ipset: Add element count to all set types header It is better to list the set elements for all set types, thus the header information is uniform. Element counts are therefore added to the bitmap and list types. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 2 ++ include/linux/netfilter/ipset/ip_set_bitmap.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 7a218eb74887..4671d740610f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -250,6 +250,8 @@ struct ip_set { u8 flags; /* Default timeout value, if enabled */ u32 timeout; + /* Number of elements (vs timeout) */ + u32 elements; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 5e4662a71e01..366d6c0ea04f 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -6,8 +6,8 @@ #define IPSET_BITMAP_MAX_RANGE 0x0000FFFF enum { + IPSET_ADD_STORE_PLAIN_TIMEOUT = -1, IPSET_ADD_FAILED = 1, - IPSET_ADD_STORE_PLAIN_TIMEOUT, IPSET_ADD_START_STORED_TIMEOUT, }; -- cgit From 9e41f26a505cca04b7122e65053cf6447007ea79 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 10 Nov 2016 12:05:34 +0100 Subject: netfilter: ipset: Count non-static extension memory for userspace Non-static (i.e. comment) extension was not counted into the memory size. A new internal counter is introduced for this. In the case of the hash types the sizes of the arrays are counted there as well so that we can avoid to scan the whole set when just the header data is requested. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 8 ++++++-- include/linux/netfilter/ipset/ip_set_comment.h | 7 +++++-- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 4671d740610f..8e42253e5d4d 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -79,10 +79,12 @@ enum ip_set_ext_id { IPSET_EXT_ID_MAX, }; +struct ip_set; + /* Extension type */ struct ip_set_ext_type { /* Destroy extension private data (can be NULL) */ - void (*destroy)(void *ext); + void (*destroy)(struct ip_set *set, void *ext); enum ip_set_extension type; enum ipset_cadt_flags flag; /* Size and minimal alignment */ @@ -252,6 +254,8 @@ struct ip_set { u32 timeout; /* Number of elements (vs timeout) */ u32 elements; + /* Size of the dynamic extensions (vs timeout) */ + size_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ @@ -268,7 +272,7 @@ ip_set_ext_destroy(struct ip_set *set, void *data) */ if (SET_WITH_COMMENT(set)) ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy( - ext_comment(data, set)); + set, ext_comment(data, set)); } static inline int diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 5444b1bbe656..8e2bab1e8e90 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -20,13 +20,14 @@ ip_set_comment_uget(struct nlattr *tb) * The kadt functions don't use the comment extensions in any way. */ static inline void -ip_set_init_comment(struct ip_set_comment *comment, +ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, const struct ip_set_ext *ext) { struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); size_t len = ext->comment ? strlen(ext->comment) : 0; if (unlikely(c)) { + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; kfree_rcu(c, rcu); rcu_assign_pointer(comment->c, NULL); } @@ -38,6 +39,7 @@ ip_set_init_comment(struct ip_set_comment *comment, if (unlikely(!c)) return; strlcpy(c->str, ext->comment, len + 1); + set->ext_size += sizeof(*c) + strlen(c->str) + 1; rcu_assign_pointer(comment->c, c); } @@ -58,13 +60,14 @@ ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) * of the set data anymore. */ static inline void -ip_set_comment_free(struct ip_set_comment *comment) +ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) { struct ip_set_comment_rcu *c; c = rcu_dereference_protected(comment->c, 1); if (unlikely(!c)) return; + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; kfree_rcu(c, rcu); rcu_assign_pointer(comment->c, NULL); } -- cgit From 39a842e22c1bf3ec3dce36e01fe8ba8ee66c80c8 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Tue, 1 Nov 2016 14:14:22 -0500 Subject: of/overlay: add of overlay notifications This patch add of overlay notifications. When DT overlays are being added, some drivers/subsystems need to see device tree overlays before the changes go into the live tree. This is distinct from reconfig notifiers that are post-apply or post-remove and which issue very granular notifications without providing access to the context of a whole overlay. The following 4 notificatons are issued: OF_OVERLAY_PRE_APPLY OF_OVERLAY_POST_APPLY OF_OVERLAY_PRE_REMOVE OF_OVERLAY_POST_REMOVE In the case of pre-apply notification, if the notifier returns error, the overlay will be rejected. This patch exports two functions for registering/unregistering notifications: of_overlay_notifier_register(struct notifier_block *nb) of_overlay_notifier_unregister(struct notifier_block *nb) The of_mutex is held during these notifications. The notification data includes pointers to the overlay target and the overlay: struct of_overlay_notify_data { struct device_node *overlay; struct device_node *target; }; Signed-off-by: Alan Tull Acked-by: Rob Herring Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 299aeb192727..d72f01009297 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1266,6 +1266,18 @@ static inline bool of_device_is_system_power_controller(const struct device_node * Overlay support */ +enum of_overlay_notify_action { + OF_OVERLAY_PRE_APPLY, + OF_OVERLAY_POST_APPLY, + OF_OVERLAY_PRE_REMOVE, + OF_OVERLAY_POST_REMOVE, +}; + +struct of_overlay_notify_data { + struct device_node *overlay; + struct device_node *target; +}; + #ifdef CONFIG_OF_OVERLAY /* ID based overlays; the API for external users */ @@ -1273,6 +1285,9 @@ int of_overlay_create(struct device_node *tree); int of_overlay_destroy(int id); int of_overlay_destroy_all(void); +int of_overlay_notifier_register(struct notifier_block *nb); +int of_overlay_notifier_unregister(struct notifier_block *nb); + #else static inline int of_overlay_create(struct device_node *tree) @@ -1290,6 +1305,16 @@ static inline int of_overlay_destroy_all(void) return -ENOTSUPP; } +static inline int of_overlay_notifier_register(struct notifier_block *nb) +{ + return 0; +} + +static inline int of_overlay_notifier_unregister(struct notifier_block *nb) +{ + return 0; +} + #endif #endif /* _LINUX_OF_H */ -- cgit From 9dce0287a60d72656a787b075f1b9162ff3cb142 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Tue, 1 Nov 2016 14:14:23 -0500 Subject: fpga: add method to get fpga manager from device The intent is to provide a non-DT method of getting ahold of a FPGA manager to do some FPGA programming. This patch refactors of_fpga_mgr_get() to reuse most of it while adding a new method fpga_mgr_get() for getting a pointer to a fpga manager struct, given the device. Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 0940bf45e2f2..957b5ac9428a 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -117,6 +117,8 @@ int fpga_mgr_firmware_load(struct fpga_manager *mgr, u32 flags, struct fpga_manager *of_fpga_mgr_get(struct device_node *node); +struct fpga_manager *fpga_mgr_get(struct device *dev); + void fpga_mgr_put(struct fpga_manager *mgr); int fpga_mgr_register(struct device *dev, const char *name, -- cgit From 1df2865f8dd9d56cb76aa7aa1298921e7bece2af Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Tue, 1 Nov 2016 14:14:26 -0500 Subject: fpga-mgr: add fpga image information struct This patch adds a minor change in the FPGA Manager API to hold information that is specific to an FPGA image file. This change is expected to bring little, if any, pain. The socfpga and zynq drivers are fixed up in this patch. An FPGA image file will have particulars that affect how the image is programmed to the FPGA. One example is that current 'flags' currently has one bit which shows whether the FPGA image was built for full reconfiguration or partial reconfiguration. Another example is timeout values for enabling or disabling the bridges in the FPGA. As the complexity of the FPGA design increases, the bridges in the FPGA may take longer times to enable or disable. This patch adds a new 'struct fpga_image_info', moves the current 'u32 flags' to it. Two other image-specific u32's are added for the bridge enable/disable timeouts. The FPGA Manager API functions are changed, replacing the 'u32 flag' parameter with a pointer to struct fpga_image_info. Subsequent patches fix the existing low level FPGA manager drivers. Signed-off-by: Alan Tull Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 957b5ac9428a..55803186e0ea 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -68,6 +68,18 @@ enum fpga_mgr_states { */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) +/** + * struct fpga_image_info - information specific to a FPGA image + * @flags: boolean flags as defined above + * @enable_timeout_us: maximum time to enable traffic through bridge (uSec) + * @disable_timeout_us: maximum time to disable traffic through bridge (uSec) + */ +struct fpga_image_info { + u32 flags; + u32 enable_timeout_us; + u32 disable_timeout_us; +}; + /** * struct fpga_manager_ops - ops for low level fpga manager drivers * @state: returns an enum value of the FPGA's state @@ -82,10 +94,12 @@ enum fpga_mgr_states { */ struct fpga_manager_ops { enum fpga_mgr_states (*state)(struct fpga_manager *mgr); - int (*write_init)(struct fpga_manager *mgr, u32 flags, + int (*write_init)(struct fpga_manager *mgr, + struct fpga_image_info *info, const char *buf, size_t count); int (*write)(struct fpga_manager *mgr, const char *buf, size_t count); - int (*write_complete)(struct fpga_manager *mgr, u32 flags); + int (*write_complete)(struct fpga_manager *mgr, + struct fpga_image_info *info); void (*fpga_remove)(struct fpga_manager *mgr); }; @@ -109,10 +123,11 @@ struct fpga_manager { #define to_fpga_manager(d) container_of(d, struct fpga_manager, dev) -int fpga_mgr_buf_load(struct fpga_manager *mgr, u32 flags, +int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info, const char *buf, size_t count); -int fpga_mgr_firmware_load(struct fpga_manager *mgr, u32 flags, +int fpga_mgr_firmware_load(struct fpga_manager *mgr, + struct fpga_image_info *info, const char *image_name); struct fpga_manager *of_fpga_mgr_get(struct device_node *node); -- cgit From 21aeda950c5f84a8351b862816d832120b217a9b Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Tue, 1 Nov 2016 14:14:28 -0500 Subject: fpga: add fpga bridge framework This framework adds API functions for enabling/ disabling FPGA bridges under kernel control. This allows the Linux kernel to disable FPGA bridges during FPGA reprogramming and to enable FPGA bridges when FPGA reprogramming is done. This framework is be manufacturer-agnostic, allowing it to be used in interfaces that use the FPGA Manager Framework to reprogram FPGA's. The functions are: * of_fpga_bridge_get * fpga_bridge_put Get/put an exclusive reference to a FPGA bridge. * fpga_bridge_enable * fpga_bridge_disable Enable/Disable traffic through a bridge. * fpga_bridge_register * fpga_bridge_unregister Register/unregister a device-specific low level FPGA Bridge driver. Get an exclusive reference to a bridge and add it to a list: * fpga_bridge_get_to_list To enable/disable/put a set of bridges that are on a list: * fpga_bridges_enable * fpga_bridges_disable * fpga_bridges_put Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-bridge.h | 60 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) create mode 100644 include/linux/fpga/fpga-bridge.h (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h new file mode 100644 index 000000000000..dba6e3c697c7 --- /dev/null +++ b/include/linux/fpga/fpga-bridge.h @@ -0,0 +1,60 @@ +#include +#include + +#ifndef _LINUX_FPGA_BRIDGE_H +#define _LINUX_FPGA_BRIDGE_H + +struct fpga_bridge; + +/** + * struct fpga_bridge_ops - ops for low level FPGA bridge drivers + * @enable_show: returns the FPGA bridge's status + * @enable_set: set a FPGA bridge as enabled or disabled + * @fpga_bridge_remove: set FPGA into a specific state during driver remove + */ +struct fpga_bridge_ops { + int (*enable_show)(struct fpga_bridge *bridge); + int (*enable_set)(struct fpga_bridge *bridge, bool enable); + void (*fpga_bridge_remove)(struct fpga_bridge *bridge); +}; + +/** + * struct fpga_bridge - FPGA bridge structure + * @name: name of low level FPGA bridge + * @dev: FPGA bridge device + * @mutex: enforces exclusive reference to bridge + * @br_ops: pointer to struct of FPGA bridge ops + * @info: fpga image specific information + * @node: FPGA bridge list node + * @priv: low level driver private date + */ +struct fpga_bridge { + const char *name; + struct device dev; + struct mutex mutex; /* for exclusive reference to bridge */ + const struct fpga_bridge_ops *br_ops; + struct fpga_image_info *info; + struct list_head node; + void *priv; +}; + +#define to_fpga_bridge(d) container_of(d, struct fpga_bridge, dev) + +struct fpga_bridge *of_fpga_bridge_get(struct device_node *node, + struct fpga_image_info *info); +void fpga_bridge_put(struct fpga_bridge *bridge); +int fpga_bridge_enable(struct fpga_bridge *bridge); +int fpga_bridge_disable(struct fpga_bridge *bridge); + +int fpga_bridges_enable(struct list_head *bridge_list); +int fpga_bridges_disable(struct list_head *bridge_list); +void fpga_bridges_put(struct list_head *bridge_list); +int fpga_bridge_get_to_list(struct device_node *np, + struct fpga_image_info *info, + struct list_head *bridge_list); + +int fpga_bridge_register(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv); +void fpga_bridge_unregister(struct device *dev); + +#endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit From 0fa20cdfcc1f68847cdfc47824476301eedc8297 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Tue, 1 Nov 2016 14:14:29 -0500 Subject: fpga: fpga-region: device tree control for FPGA FPGA Regions support programming FPGA under control of the Device Tree. Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 55803186e0ea..96a1a3311649 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -65,8 +65,10 @@ enum fpga_mgr_states { /* * FPGA Manager flags * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported + * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) +#define FPGA_MGR_EXTERNAL_CONFIG BIT(1) /** * struct fpga_image_info - information specific to a FPGA image -- cgit From fac51482577d5e05bbb0efa8d602a3c2111098bf Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 28 Oct 2016 09:45:28 +0100 Subject: drivers: base: cacheinfo: fix x86 with CONFIG_OF enabled With CONFIG_OF enabled on x86, we get the following error on boot: " Failed to find cpu0 device node Unable to detect cache hierarchy from DT for CPU 0 " and the cacheinfo fails to get populated in the corresponding sysfs entries. This is because cache_setup_of_node looks for of_node for setting up the shared cpu_map without checking that it's already populated in the architecture specific callback. In order to indicate that the shared cpu_map is already populated, this patch introduces a boolean `cpu_map_populated` in struct cpu_cacheinfo that can be used by the generic code to skip cache_shared_cpu_map_setup. This patch also sets that boolean for x86. Cc: Greg Kroah-Hartman Signed-off-by: Sudeep Holla Signed-off-by: Greg Kroah-Hartman --- include/linux/cacheinfo.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2189935075b4..a951fd10aaaa 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -71,6 +71,7 @@ struct cpu_cacheinfo { struct cacheinfo *info_list; unsigned int num_levels; unsigned int num_leaves; + bool cpu_map_populated; }; /* -- cgit From d49187e97e94e2eb613cb6fed810356972077cc3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 10 Nov 2016 07:32:33 -0800 Subject: nvme: introduce struct nvme_request This adds a shared per-request structure for all NVMe I/O. This structure is embedded as the first member in all NVMe transport drivers request private data and allows to implement common functionality between the drivers. The first use is to replace the current abuse of the SCSI command passthrough fields in struct request for the NVMe command passthrough, but it will grow a field more fields to allow implementing things like common abort handlers in the future. The passthrough commands are handled by having a pointer to the SQE (struct nvme_command) in struct nvme_request, and the union of the possible result fields, which had to be turned from an anonymous into a named union for that purpose. This avoids having to pass a reference to a full CQE around and thus makes checking the result a lot more lightweight. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7676557ce357..18ce9f7cc881 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -949,11 +949,11 @@ struct nvme_completion { /* * Used by Admin and Fabrics commands to return data: */ - union { - __le16 result16; - __le32 result; - __le64 result64; - }; + union nvme_result { + __le16 u16; + __le32 u32; + __le64 u64; + } result; __le16 sq_head; /* how much of this queue may be reclaimed */ __le16 sq_id; /* submission queue that generated this entry */ __u16 command_id; /* of the command which completed */ -- cgit From cf43e6be865a582ba66ee4747ae27a0513f6bba1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 7 Nov 2016 21:32:37 -0700 Subject: block: add scalable completion tracking of requests For legacy block, we simply track them in the request queue. For blk-mq, we track them on a per-sw queue basis, which we can then sum up through the hardware queues and finally to a per device state. The stats are tracked in, roughly, 0.1s interval windows. Add sysfs files to display the stats. The feature is off by default, to avoid any extra overhead. In-kernel users of it can turn it on by setting QUEUE_FLAG_STATS in the queue flags. We currently don't turn it on if someone just reads any of the stats files, that is something we could add as well. Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 16 ++++++++++++++++ include/linux/blkdev.h | 7 +++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 562ac46cb790..4d0044d09984 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -250,4 +250,20 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } +struct blk_issue_stat { + u64 time; +}; + +#define BLK_RQ_STAT_BATCH 64 + +struct blk_rq_stat { + s64 mean; + u64 min; + u64 max; + s32 nr_samples; + s32 nr_batch; + u64 batch; + s64 time; +}; + #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d364be6e6959..303723a2e5b8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -117,6 +117,8 @@ typedef __u32 __bitwise req_flags_t; #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) +/* IO stats tracking on */ +#define RQF_STATS ((__force req_flags_t)(1 << 17)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ @@ -197,6 +199,7 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; unsigned long start_time; + struct blk_issue_stat issue_stat; #ifdef CONFIG_BLK_CGROUP struct request_list *rl; /* rl this rq is alloced from */ unsigned long long start_time_ns; @@ -492,6 +495,9 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; + + struct blk_rq_stat rq_stats[2]; + /* * Number of active block driver functions for which blk_drain_queue() * must wait. Must be incremented around functions that unlock the @@ -585,6 +591,7 @@ struct request_queue { #define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DAX 26 /* device supports DAX */ +#define QUEUE_FLAG_STATS 27 /* track rq completion times */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ -- cgit From 87760e5eef359788047d6fd54fc12eec74ce0d27 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Nov 2016 12:38:14 -0700 Subject: block: hook up writeback throttling Enable throttling of buffered writeback to make it a lot more smooth, and has way less impact on other system activity. Background writeback should be, by definition, background activity. The fact that we flush huge bundles of it at the time means that it potentially has heavy impacts on foreground workloads, which isn't ideal. We can't easily limit the sizes of writes that we do, since that would impact file system layout in the presence of delayed allocation. So just throttle back buffered writeback, unless someone is waiting for it. The algorithm for when to throttle takes its inspiration in the CoDel networking scheduling algorithm. Like CoDel, blk-wb monitors the minimum latencies of requests over a window of time. In that window of time, if the minimum latency of any request exceeds a given target, then a scale count is incremented and the queue depth is shrunk. The next monitoring window is shrunk accordingly. Unlike CoDel, if we hit a window that exhibits good behavior, then we simply increment the scale count and re-calculate the limits for that scale value. This prevents us from oscillating between a close-to-ideal value and max all the time, instead remaining in the windows where we get good behavior. Unlike CoDel, blk-wb allows the scale count to to negative. This happens if we primarily have writes going on. Unlike positive scale counts, this doesn't change the size of the monitoring window. When the heavy writers finish, blk-bw quickly snaps back to it's stable state of a zero scale count. The patch registers a sysfs entry, 'wb_lat_usec'. This sets the latency target to me met. It defaults to 2 msec for non-rotational storage, and 75 msec for rotational storage. Setting this value to '0' disables blk-wb. Generally, a user would not have to touch this setting. We don't enable WBT on devices that are managed with CFQ, and have a non-root block cgroup attached. If we have a proportional share setup on this particular disk, then the wbt throttling will interfere with that. We don't have a strong need for wbt for that case, since we will rely on CFQ doing that for us. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 303723a2e5b8..15da9e430f90 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -38,6 +38,7 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; +struct rq_wb; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -383,6 +384,8 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + struct rq_wb *rq_wb; + /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg * is used, root blkg allocates from @q->root_rl and all other -- cgit From ee7930ee27fe5240398cc302fa8eb4454725f188 Mon Sep 17 00:00:00 2001 From: Markus Mayer Date: Mon, 7 Nov 2016 10:02:23 -0800 Subject: cpufreq: stats: New sysfs attribute for clearing statistics Allow CPUfreq statistics to be cleared by writing anything to /sys/.../cpufreq/stats/reset. Signed-off-by: Markus Mayer Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 32dc0cbd51ca..40dc2e29f480 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -234,6 +234,10 @@ __ATTR(_name, _perm, show_##_name, NULL) static struct freq_attr _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) +#define cpufreq_freq_attr_wo(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0200, NULL, store_##_name) + struct global_attr { struct attribute attr; ssize_t (*show)(struct kobject *kobj, -- cgit From 53d74d056a4e306a72b8883d325b5d853c0618e6 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 19 Oct 2016 19:28:12 +0100 Subject: thread_info: factor out restart_block Since commit f56141e3e2d9aabf ("all arches, signal: move restart_block to struct task_struct"), thread_info and restart_block have been logically distinct, yet struct restart_block is still defined in . At least one architecture (erroneously) uses restart_block as part of its thread_info, and thus the definition of restart_block must come before the include of . Subsequent patches in this series need to shuffle the order of includes and definitions in , and will make this ordering fragile. This patch moves the definition of restart_block out to its own header. This serves as generic cleanup, logically separating thread_info and restart_block, and also makes it easier to avoid fragility. Signed-off-by: Mark Rutland Reviewed-by: Andy Lutomirski Cc: Andrew Morton Cc: Heiko Carstens Cc: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/restart_block.h | 51 +++++++++++++++++++++++++++++++++++++++++++ include/linux/thread_info.h | 41 +--------------------------------- 2 files changed, 52 insertions(+), 40 deletions(-) create mode 100644 include/linux/restart_block.h (limited to 'include/linux') diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h new file mode 100644 index 000000000000..0d905d8ec553 --- /dev/null +++ b/include/linux/restart_block.h @@ -0,0 +1,51 @@ +/* + * Common syscall restarting data + */ +#ifndef __LINUX_RESTART_BLOCK_H +#define __LINUX_RESTART_BLOCK_H + +#include +#include + +struct timespec; +struct compat_timespec; +struct pollfd; + +/* + * System call restart block. + */ +struct restart_block { + long (*fn)(struct restart_block *); + union { + /* For futex_wait and futex_wait_requeue_pi */ + struct { + u32 __user *uaddr; + u32 val; + u32 flags; + u32 bitset; + u64 time; + u32 __user *uaddr2; + } futex; + /* For nanosleep */ + struct { + clockid_t clockid; + struct timespec __user *rmtp; +#ifdef CONFIG_COMPAT + struct compat_timespec __user *compat_rmtp; +#endif + u64 expires; + } nanosleep; + /* For poll */ + struct { + struct pollfd __user *ufds; + int nfds; + int has_timeout; + unsigned long tv_sec; + unsigned long tv_nsec; + } poll; + }; +}; + +extern long do_no_restart_syscall(struct restart_block *parm); + +#endif /* __LINUX_RESTART_BLOCK_H */ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 2873baf5372a..c75c6ab364ca 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -9,51 +9,12 @@ #include #include - -struct timespec; -struct compat_timespec; +#include #ifdef CONFIG_THREAD_INFO_IN_TASK #define current_thread_info() ((struct thread_info *)current) #endif -/* - * System call restart block. - */ -struct restart_block { - long (*fn)(struct restart_block *); - union { - /* For futex_wait and futex_wait_requeue_pi */ - struct { - u32 __user *uaddr; - u32 val; - u32 flags; - u32 bitset; - u64 time; - u32 __user *uaddr2; - } futex; - /* For nanosleep */ - struct { - clockid_t clockid; - struct timespec __user *rmtp; -#ifdef CONFIG_COMPAT - struct compat_timespec __user *compat_rmtp; -#endif - u64 expires; - } nanosleep; - /* For poll */ - struct { - struct pollfd __user *ufds; - int nfds; - int has_timeout; - unsigned long tv_sec; - unsigned long tv_nsec; - } poll; - }; -}; - -extern long do_no_restart_syscall(struct restart_block *parm); - #include #include -- cgit From dc3d2a679cd8631b8a570fc8ca5f4712d7d25698 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 19 Oct 2016 19:28:13 +0100 Subject: thread_info: include for THREAD_INFO_IN_TASK When CONFIG_THREAD_INFO_IN_TASK is selected, the current_thread_info() macro relies on current having been defined prior to its use. However, not all users of current_thread_info() include , and thus current is not guaranteed to be defined. When CONFIG_THREAD_INFO_IN_TASK is not selected, it's possible that get_current() / current are based upon current_thread_info(), and includes . Thus always including would result in circular dependences on some platforms. To ensure both cases work, this patch includes , but only when CONFIG_THREAD_INFO_IN_TASK is selected. Signed-off-by: Mark Rutland Acked-by: Heiko Carstens Reviewed-by: Andy Lutomirski Cc: Andrew Morton Cc: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/thread_info.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index c75c6ab364ca..58373875e8ee 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -12,6 +12,12 @@ #include #ifdef CONFIG_THREAD_INFO_IN_TASK +/* + * For CONFIG_THREAD_INFO_IN_TASK kernels we need for the + * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, + * including can cause a circular dependency on some platforms. + */ +#include #define current_thread_info() ((struct thread_info *)current) #endif -- cgit From 109704492ef637956265ec2eb72ae7b3b39eb6f4 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 20 Oct 2016 00:34:00 -0700 Subject: pstore: Make spinlock per zone instead of global Currently pstore has a global spinlock for all zones. Since the zones are independent and modify different areas of memory, there's no need to have a global lock, so we should use a per-zone lock as introduced here. Also, when ramoops's ftrace use-case has a FTRACE_PER_CPU flag introduced later, which splits the ftrace memory area into a single zone per CPU, it will eliminate the need for locking. In preparation for this, make the locking optional. Signed-off-by: Joel Fernandes [kees: updated commit message] Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index c668c861c96c..244d2423dbaf 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -40,6 +40,7 @@ struct persistent_ram_zone { void *vaddr; struct persistent_ram_buffer *buffer; size_t buffer_size; + raw_spinlock_t buffer_lock; /* ECC correction */ char *par_buffer; -- cgit From bbd7bb7017d5c2b1e75f3818b4ce88fa58bb0eab Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 4 Nov 2016 09:34:34 -0600 Subject: block: move poll code to blk-mq The poll code is blk-mq specific, let's move it to blk-mq.c. This is a prep patch for improving the polling code. Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 15da9e430f90..bab18ee5810d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -952,7 +952,7 @@ extern int blk_execute_rq(struct request_queue *, struct gendisk *, extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); -bool blk_poll(struct request_queue *q, blk_qc_t cookie); +bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { -- cgit From c540594f864bb4645573c2c0a304919fabb3d7ea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 9 Nov 2016 22:02:34 +0100 Subject: bpf, mlx4: fix prog refcount in mlx4_en_try_alloc_resources error path Commit 67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme") added a bug in that the prog's reference count is not dropped in the error path when mlx4_en_try_alloc_resources() is failing from mlx4_xdp_set(). We previously took bpf_prog_add(prog, priv->rx_ring_num - 1), that we need to release again. Earlier in the call path, dev_change_xdp_fd() itself holds a reference to the prog as well (hence the '- 1' in the bpf_prog_add()), so a simple atomic_sub() is safe to use here. When an error is propagated, then bpf_prog_put() is called eventually from dev_change_xdp_fd() Fixes: 67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index edcd96ded8aa..01c1487277b2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -234,6 +234,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i); +void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); @@ -303,6 +304,10 @@ static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) return ERR_PTR(-EOPNOTSUPP); } +static inline void bpf_prog_sub(struct bpf_prog *prog, int i) +{ +} + static inline void bpf_prog_put(struct bpf_prog *prog) { } -- cgit From 372788f964c95a6fa0f677c43d6153c27896ef42 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Thu, 10 Nov 2016 17:10:46 -0600 Subject: net: phy: expose phy_aneg_done API for use by drivers Make phy_aneg_done() available to drivers so that the result of the auto-negotiation initiated by phy_start_aneg() can be determined. Remove the local implementation of phy_aneg_done() from the Aeroflex driver and use the phy library version. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e7e1fd382564..9880d73a2c3d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -786,6 +786,7 @@ void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); +int phy_aneg_done(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); -- cgit From 636259880a7e7d3446a707dddebc799da94bdd0b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 12 Nov 2016 21:32:31 +0000 Subject: efi: Add support for seeding the RNG from a UEFI config table Specify a Linux specific UEFI configuration table that carries some random bits, and use the contents during early boot to seed the kernel's random number generator. This allows much strong random numbers to be generated early on. The entropy is fed to the kernel using add_device_randomness(), which is documented as being appropriate for being called very early. Since UEFI configuration tables may also be consumed by kexec'd kernels, register a reboot notifier that updates the seed in the table. Note that the config table could be generated by the EFI stub or by any other UEFI driver or application (e.g., GRUB), but the random seed table GUID and the associated functionality should be considered an internal kernel interface (unless it is promoted to ABI later on) Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Reviewed-by: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20161112213237.8804-4-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 2d089487d2da..85e28b138cdd 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -599,6 +599,7 @@ void efi_native_runtime_setup(void); */ #define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, 0xb9, 0x0e, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) +#define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) typedef struct { efi_guid_t guid; @@ -872,6 +873,7 @@ extern struct efi { unsigned long esrt; /* ESRT table */ unsigned long properties_table; /* properties table */ unsigned long mem_attr_table; /* memory attributes table */ + unsigned long rng_seed; /* UEFI firmware random seed */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -1493,4 +1495,10 @@ efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, struct efi_boot_memmap *map, void *priv, efi_exit_boot_map_processing priv_func); + +struct linux_efi_random_seed { + u32 size; + u8 bits[]; +}; + #endif /* _LINUX_EFI_H */ -- cgit From 568bc4e87033d232c5fd00d5b0cd22a2ccc04944 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 12 Nov 2016 21:32:33 +0000 Subject: efi/arm*/libstub: Invoke EFI_RNG_PROTOCOL to seed the UEFI RNG table Invoke the EFI_RNG_PROTOCOL protocol in the context of the stub and install the Linux-specific RNG seed UEFI config table. This will be picked up by the EFI routines in the core kernel to seed the kernel entropy pool. Signed-off-by: Ard Biesheuvel Signed-off-by: Matt Fleming Reviewed-by: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20161112213237.8804-6-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 85e28b138cdd..f5a821d9b90c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -589,6 +589,7 @@ void efi_native_runtime_setup(void); #define DEVICE_TREE_GUID EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0) #define EFI_PROPERTIES_TABLE_GUID EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5) #define EFI_RNG_PROTOCOL_GUID EFI_GUID(0x3152bca5, 0xeade, 0x433d, 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) +#define EFI_RNG_ALGORITHM_RAW EFI_GUID(0xe43176d7, 0xb6e8, 0x4827, 0xb7, 0x84, 0x7f, 0xfd, 0xc4, 0xb6, 0x85, 0x61) #define EFI_MEMORY_ATTRIBUTES_TABLE_GUID EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) -- cgit From 46cd4b75cd0edee76e0096225c2d31f8d90e92a2 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 12 Nov 2016 21:32:34 +0000 Subject: efi: Add device path parser We're about to extended the efistub to retrieve device properties from EFI on Apple Macs. The properties use EFI Device Paths to indicate the device they belong to. This commit adds a parser which, given an EFI Device Path, locates the corresponding struct device and returns a reference to it. Initially only ACPI and PCI Device Path nodes are supported, these are the only types needed for Apple device properties (the corresponding macOS function AppleACPIPlatformExpert::matchEFIDevicePath() does not support any others). Further node types can be added with little to moderate effort. Apple device properties is currently the only use case of this parser, but Peter Jones intends to use it to match up devices with the ConInDev/ConOutDev/ErrOutDev variables and add sysfs attributes to these devices to say the hardware supports using them as console. Thus, make this parser a separate component which can be selected with config option EFI_DEV_PATH_PARSER. It can in principle be compiled as a module if acpi_get_first_physical_node() and acpi_bus_type are exported (and efi_get_device_by_path() itself is exported). The dependency on CONFIG_ACPI is needed for acpi_match_device_ids(). It can be removed if an empty inline stub is added for that function. Signed-off-by: Lukas Wunner Signed-off-by: Matt Fleming Cc: Andreas Noever Cc: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Jones Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20161112213237.8804-7-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index f5a821d9b90c..261767212c47 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1148,6 +1148,26 @@ struct efi_generic_dev_path { u16 length; } __attribute ((packed)); +struct efi_dev_path { + u8 type; /* can be replaced with unnamed */ + u8 sub_type; /* struct efi_generic_dev_path; */ + u16 length; /* once we've moved to -std=c11 */ + union { + struct { + u32 hid; + u32 uid; + } acpi; + struct { + u8 fn; + u8 dev; + } pci; + }; +} __attribute ((packed)); + +#if IS_ENABLED(CONFIG_EFI_DEV_PATH_PARSER) +struct device *efi_get_device_by_path(struct efi_dev_path **node, size_t *len); +#endif + static inline void memrange_efi_to_native(u64 *addr, u64 *npages) { *npages = PFN_UP(*addr + (*npages< Date: Sat, 12 Nov 2016 21:32:36 +0000 Subject: x86/efi: Retrieve and assign Apple device properties MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apple's EFI drivers supply device properties which are needed to support Macs optimally. They contain vital information which cannot be obtained any other way (e.g. Thunderbolt Device ROM). They're also used to convey the current device state so that OS drivers can pick up where EFI drivers left (e.g. GPU mode setting). There's an EFI driver dubbed "AAPL,PathProperties" which implements a per-device key/value store. Other EFI drivers populate it using a custom protocol. The macOS bootloader /System/Library/CoreServices/boot.efi retrieves the properties with the same protocol. The kernel extension AppleACPIPlatform.kext subsequently merges them into the I/O Kit registry (see ioreg(8)) where they can be queried by other kernel extensions and user space. This commit extends the efistub to retrieve the device properties before ExitBootServices is called. It assigns them to devices in an fs_initcall so that they can be queried with the API in . Note that the device properties will only be available if the kernel is booted with the efistub. Distros should adjust their installers to always use the efistub on Macs. grub with the "linux" directive will not work unless the functionality of this commit is duplicated in grub. (The "linuxefi" directive should work but is not included upstream as of this writing.) The custom protocol has GUID 91BD12FE-F6C3-44FB-A5B7-5122AB303AE0 and looks like this: typedef struct { unsigned long version; /* 0x10000 */ efi_status_t (*get) ( IN struct apple_properties_protocol *this, IN struct efi_dev_path *device, IN efi_char16_t *property_name, OUT void *buffer, IN OUT u32 *buffer_len); /* EFI_SUCCESS, EFI_NOT_FOUND, EFI_BUFFER_TOO_SMALL */ efi_status_t (*set) ( IN struct apple_properties_protocol *this, IN struct efi_dev_path *device, IN efi_char16_t *property_name, IN void *property_value, IN u32 property_value_len); /* allocates copies of property name and value */ /* EFI_SUCCESS, EFI_OUT_OF_RESOURCES */ efi_status_t (*del) ( IN struct apple_properties_protocol *this, IN struct efi_dev_path *device, IN efi_char16_t *property_name); /* EFI_SUCCESS, EFI_NOT_FOUND */ efi_status_t (*get_all) ( IN struct apple_properties_protocol *this, OUT void *buffer, IN OUT u32 *buffer_len); /* EFI_SUCCESS, EFI_BUFFER_TOO_SMALL */ } apple_properties_protocol; Thanks to Pedro Vilaça for this blog post which was helpful in reverse engineering Apple's EFI drivers and bootloader: https://reverse.put.as/2016/06/25/apple-efi-firmware-passwords-and-the-scbo-myth/ If someone at Apple is reading this, please note there's a memory leak in your implementation of the del() function as the property struct is freed but the name and value allocations are not. Neither the macOS bootloader nor Apple's EFI drivers check the protocol version, but we do to avoid breakage if it's ever changed. It's been the same since at least OS X 10.6 (2009). The get_all() function conveniently fills a buffer with all properties in marshalled form which can be passed to the kernel as a setup_data payload. The number of device properties is dynamic and can change between a first invocation of get_all() (to determine the buffer size) and a second invocation (to retrieve the actual buffer), hence the peculiar loop which does not finish until the buffer size settles. The macOS bootloader does the same. The setup_data payload is later on unmarshalled in an fs_initcall. The idea is that most buses instantiate devices in "subsys" initcall level and drivers are usually bound to these devices in "device" initcall level, so we assign the properties in-between, i.e. in "fs" initcall level. This assumes that devices to which properties pertain are instantiated from a "subsys" initcall or earlier. That should always be the case since on macOS, AppleACPIPlatformExpert::matchEFIDevicePath() only supports ACPI and PCI nodes and we've fully scanned those buses during "subsys" initcall level. The second assumption is that properties are only needed from a "device" initcall or later. Seems reasonable to me, but should this ever not work out, an alternative approach would be to store the property sets e.g. in a btree early during boot. Then whenever device_add() is called, an EFI Device Path would have to be constructed for the newly added device, and looked up in the btree. That way, the property set could be assigned to the device immediately on instantiation. And this would also work for devices instantiated in a deferred fashion. It seems like this approach would be more complicated and require more code. That doesn't seem justified without a specific use case. For comparison, the strategy on macOS is to assign properties to objects in the ACPI namespace (AppleACPIPlatformExpert::mergeEFIProperties()). That approach is definitely wrong as it fails for devices not present in the namespace: The NHI EFI driver supplies properties for attached Thunderbolt devices, yet on Macs with Thunderbolt 1 only one device level behind the host controller is described in the namespace. Consequently macOS cannot assign properties for chained devices. With Thunderbolt 2 they started to describe three device levels behind host controllers in the namespace but this grossly inflates the SSDT and still fails if the user daisy-chained more than three devices. We copy the property names and values from the setup_data payload to swappable virtual memory and afterwards make the payload available to the page allocator. This is just for the sake of good housekeeping, it wouldn't occupy a meaningful amount of physical memory (4444 bytes on my machine). Only the payload is freed, not the setup_data header since otherwise we'd break the list linkage and we cannot safely update the predecessor's ->next link because there's no locking for the list. The payload is currently not passed on to kexec'ed kernels, same for PCI ROMs retrieved by setup_efi_pci(). This can be added later if there is demand by amending setup_efi_state(). The payload can then no longer be made available to the page allocator of course. Tested-by: Lukas Wunner [MacBookPro9,1] Tested-by: Pierre Moreau [MacBookPro11,3] Signed-off-by: Lukas Wunner Signed-off-by: Matt Fleming Cc: Andreas Noever Cc: Ard Biesheuvel Cc: Linus Torvalds Cc: Pedro Vilaça Cc: Peter Jones Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: grub-devel@gnu.org Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20161112213237.8804-9-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 261767212c47..a07a476178cd 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -443,6 +443,22 @@ typedef struct { #define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO_16 0x20000 #define EFI_PCI_IO_ATTRIBUTE_VGA_IO_16 0x40000 +typedef struct { + u32 version; + u32 get; + u32 set; + u32 del; + u32 get_all; +} apple_properties_protocol_32_t; + +typedef struct { + u64 version; + u64 get; + u64 set; + u64 del; + u64 get_all; +} apple_properties_protocol_64_t; + /* * Types and defines for EFI ResetSystem */ @@ -592,6 +608,7 @@ void efi_native_runtime_setup(void); #define EFI_RNG_ALGORITHM_RAW EFI_GUID(0xe43176d7, 0xb6e8, 0x4827, 0xb7, 0x84, 0x7f, 0xfd, 0xc4, 0xb6, 0x85, 0x61) #define EFI_MEMORY_ATTRIBUTES_TABLE_GUID EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) /* * This GUID is used to pass to the kernel proper the struct screen_info -- cgit From 51239600074bc9979b0a0e83b72c726d7dcc3132 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 8 Nov 2016 12:58:51 +0100 Subject: iio:core: add a callback to allow drivers to provide _available attributes A large number of attributes can only take a limited range of values. Currently in IIO this is handled by directly registering additional *_available attributes thus providing this information to userspace. It is desirable to provide this information via the core for much the same reason this was done for the actual channel information attributes in the first place. If it isn't there, then it can only really be accessed from userspace. Other in kernel IIO consumers have no access to what valid parameters are. Two forms are currently supported: * list of values in one particular IIO_VAL_* format. e.g. 1.300000 1.500000 1.730000 * range specification with a step size: e.g. [1.000000 0.500000 2.500000] equivalent to 1.000000 1.5000000 2.000000 2.500000 An addition set of masks are used to allow different sharing rules for the *_available attributes generated. This allows for example: in_accel_x_offset in_accel_y_offset in_accel_offset_available. We could have gone with having a specification for each and every info_mask element but that would have meant changing the existing userspace ABI. This approach does not. Signed-off-by: Jonathan Cameron [forward ported, added some docs and fixed buffer overflows /peda] Acked-by: Daniel Baluta Signed-off-by: Peter Rosin Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 29 +++++++++++++++++++++++++++++ include/linux/iio/types.h | 5 +++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 4591d8ea41bd..849d524645e8 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -225,12 +225,22 @@ struct iio_event_spec { * endianness: little or big endian * @info_mask_separate: What information is to be exported that is specific to * this channel. + * @info_mask_separate_available: What availability information is to be + * exported that is specific to this channel. * @info_mask_shared_by_type: What information is to be exported that is shared * by all channels of the same type. + * @info_mask_shared_by_type_available: What availability information is to be + * exported that is shared by all channels of the same + * type. * @info_mask_shared_by_dir: What information is to be exported that is shared * by all channels of the same direction. + * @info_mask_shared_by_dir_available: What availability information is to be + * exported that is shared by all channels of the same + * direction. * @info_mask_shared_by_all: What information is to be exported that is shared * by all channels. + * @info_mask_shared_by_all_available: What availability information is to be + * exported that is shared by all channels. * @event_spec: Array of events which should be registered for this * channel. * @num_event_specs: Size of the event_spec array. @@ -269,9 +279,13 @@ struct iio_chan_spec { enum iio_endian endianness; } scan_type; long info_mask_separate; + long info_mask_separate_available; long info_mask_shared_by_type; + long info_mask_shared_by_type_available; long info_mask_shared_by_dir; + long info_mask_shared_by_dir_available; long info_mask_shared_by_all; + long info_mask_shared_by_all_available; const struct iio_event_spec *event_spec; unsigned int num_event_specs; const struct iio_chan_spec_ext_info *ext_info; @@ -349,6 +363,14 @@ struct iio_dev; * max_len specifies maximum number of elements * vals pointer can contain. val_len is used to return * length of valid elements in vals. + * @read_avail: function to return the available values from the device. + * mask specifies which value. Note 0 means the available + * values for the channel in question. Return value + * specifies if a IIO_AVAIL_LIST or a IIO_AVAIL_RANGE is + * returned in vals. The type of the vals are returned in + * type and the number of vals is returned in length. For + * ranges, there are always three vals returned; min, step + * and max. For lists, all possible values are enumerated. * @write_raw: function to write a value to the device. * Parameters are the same as for read_raw. * @write_raw_get_fmt: callback function to query the expected @@ -397,6 +419,13 @@ struct iio_info { int *val_len, long mask); + int (*read_avail)(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, + int *type, + int *length, + long mask); + int (*write_raw)(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 32b579525004..2aa7b6384d64 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -29,4 +29,9 @@ enum iio_event_info { #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 +enum iio_available_type { + IIO_AVAIL_LIST, + IIO_AVAIL_RANGE, +}; + #endif /* _IIO_TYPES_H_ */ -- cgit From 00c5f80c2fad5368cd5bfa6c9d90e75a9041ac16 Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Tue, 8 Nov 2016 12:58:52 +0100 Subject: iio: inkern: add helpers to query available values from channels Specifically a helper for reading the available maximum raw value of a channel and a helper for forwarding read_avail requests for raw values from one iio driver to an iio channel that is consumed. These rather specific helpers are in turn built with generic helpers making it easy to build more helpers for available values as needed. Signed-off-by: Peter Rosin Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 28 ++++++++++++++++++++++++++++ include/linux/iio/iio.h | 17 +++++++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 638157234357..47eeec3218b5 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -225,6 +225,34 @@ int iio_read_channel_processed(struct iio_channel *chan, int *val); */ int iio_write_channel_raw(struct iio_channel *chan, int val); +/** + * iio_read_max_channel_raw() - read maximum available raw value from a given + * channel, i.e. the maximum possible value. + * @chan: The channel being queried. + * @val: Value read back. + * + * Note raw reads from iio channels are in adc counts and hence + * scale will need to be applied if standard units are required. + */ +int iio_read_max_channel_raw(struct iio_channel *chan, int *val); + +/** + * iio_read_avail_channel_raw() - read available raw values from a given channel + * @chan: The channel being queried. + * @vals: Available values read back. + * @length: Number of entries in vals. + * + * Returns an error code, IIO_AVAIL_RANGE or IIO_AVAIL_LIST. + * + * For ranges, three vals are always returned; min, step and max. + * For lists, all the possible values are enumerated. + * + * Note raw available values from iio channels are in adc counts and + * hence scale will need to be applied if standard units are required. + */ +int iio_read_avail_channel_raw(struct iio_channel *chan, + const int **vals, int *length); + /** * iio_get_channel_type() - get the type of a channel * @channel: The channel being queried. diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 849d524645e8..3f5ea2e9a39e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -315,6 +315,23 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, (chan->info_mask_shared_by_all & BIT(type)); } +/** + * iio_channel_has_available() - Checks if a channel has an available attribute + * @chan: The channel to be queried + * @type: Type of the available attribute to be checked + * + * Returns true if the channel supports reporting available values for the + * given attribute type, false otherwise. + */ +static inline bool iio_channel_has_available(const struct iio_chan_spec *chan, + enum iio_chan_info_enum type) +{ + return (chan->info_mask_separate_available & BIT(type)) | + (chan->info_mask_shared_by_type_available & BIT(type)) | + (chan->info_mask_shared_by_dir_available & BIT(type)) | + (chan->info_mask_shared_by_all_available & BIT(type)); +} + #define IIO_CHAN_SOFT_TIMESTAMP(_si) { \ .type = IIO_TIMESTAMP, \ .channel = -1, \ -- cgit From 1c7dcf69eea3224474fe884a03b3e19b82d1101e Mon Sep 17 00:00:00 2001 From: David Gstir Date: Sun, 13 Nov 2016 22:20:44 +0100 Subject: fscrypt: Add in-place encryption mode ext4 and f2fs require a bounce page when encrypting pages. However, not all filesystems will need that (eg. UBIFS). This is handled via a flag on fscrypt_operations where a fs implementation can select in-place encryption over using a bounce page (which is the default). Signed-off-by: David Gstir Signed-off-by: Richard Weinberger Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index ff8b11b26f31..5a65b0e3773f 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -153,10 +153,16 @@ struct fscrypt_name { #define fname_name(p) ((p)->disk_name.name) #define fname_len(p) ((p)->disk_name.len) +/* + * fscrypt superblock flags + */ +#define FS_CFLG_INPLACE_ENCRYPTION (1U << 1) + /* * crypto opertions for filesystems */ struct fscrypt_operations { + unsigned int flags; int (*get_context)(struct inode *, void *, size_t); int (*key_prefix)(struct inode *, u8 **); int (*prepare_context)(struct inode *); -- cgit From b50f7b268bad8088dfe7579a65cd910d8cc5c40f Mon Sep 17 00:00:00 2001 From: David Gstir Date: Sun, 13 Nov 2016 22:20:45 +0100 Subject: fscrypt: Allow fscrypt_decrypt_page() to function with non-writeback pages Some filesystem might pass pages which do not have page->mapping->host set to the encrypted inode. We want the caller to explicitly pass the corresponding inode. Signed-off-by: David Gstir Signed-off-by: Richard Weinberger Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 5a65b0e3773f..8be8e9657c63 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -249,7 +249,7 @@ int fscrypt_initialize(void); extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t); -extern int fscrypt_decrypt_page(struct page *); +extern int fscrypt_decrypt_page(struct inode *, struct page *); extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); extern void fscrypt_pullback_bio_page(struct page **, bool); extern void fscrypt_restore_control_page(struct page *); @@ -298,7 +298,8 @@ static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, return ERR_PTR(-EOPNOTSUPP); } -static inline int fscrypt_notsupp_decrypt_page(struct page *p) +static inline int fscrypt_notsupp_decrypt_page(struct inode *i, + struct page *p) { return -EOPNOTSUPP; } -- cgit From 7821d4dd4589ce5af54f3e46d04a29439ba3c2e5 Mon Sep 17 00:00:00 2001 From: David Gstir Date: Sun, 13 Nov 2016 22:20:46 +0100 Subject: fscrypt: Enable partial page encryption Not all filesystems work on full pages, thus we should allow them to hand partial pages to fscrypt for en/decryption. Signed-off-by: David Gstir Signed-off-by: Richard Weinberger Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 8be8e9657c63..e05931272cea 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -248,8 +248,11 @@ int fscrypt_initialize(void); extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); -extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t); -extern int fscrypt_decrypt_page(struct inode *, struct page *); +extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, + unsigned int, unsigned int, + gfp_t); +extern int fscrypt_decrypt_page(struct inode *, struct page *, unsigned int, + unsigned int); extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); extern void fscrypt_pullback_bio_page(struct page **, bool); extern void fscrypt_restore_control_page(struct page *); @@ -293,13 +296,16 @@ static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c) } static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, - struct page *p, gfp_t f) + struct page *p, + unsigned int len, + unsigned int offs, + gfp_t f) { return ERR_PTR(-EOPNOTSUPP); } -static inline int fscrypt_notsupp_decrypt_page(struct inode *i, - struct page *p) +static inline int fscrypt_notsupp_decrypt_page(struct inode *i, struct page *p, + unsigned int len, unsigned int offs) { return -EOPNOTSUPP; } -- cgit From 0b93e1b94b86f826d18a2aaf219a53e271274d49 Mon Sep 17 00:00:00 2001 From: David Gstir Date: Sun, 13 Nov 2016 22:20:47 +0100 Subject: fscrypt: Constify struct inode pointer Some filesystems, such as UBIFS, maintain a const pointer for struct inode. Signed-off-by: David Gstir Signed-off-by: Richard Weinberger Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index e05931272cea..e9be944a324c 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -212,7 +212,7 @@ static inline struct page *fscrypt_control_page(struct page *page) #endif } -static inline int fscrypt_has_encryption_key(struct inode *inode) +static inline int fscrypt_has_encryption_key(const struct inode *inode) { #if IS_ENABLED(CONFIG_FS_ENCRYPTION) return (inode->i_crypt_info != NULL); @@ -246,17 +246,17 @@ static inline void fscrypt_set_d_op(struct dentry *dentry) extern struct kmem_cache *fscrypt_info_cachep; int fscrypt_initialize(void); -extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t); +extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); -extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, +extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, unsigned int, unsigned int, gfp_t); -extern int fscrypt_decrypt_page(struct inode *, struct page *, unsigned int, +extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, unsigned int); extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); extern void fscrypt_pullback_bio_page(struct page **, bool); extern void fscrypt_restore_control_page(struct page *); -extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, +extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); /* policy.c */ extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); @@ -273,8 +273,8 @@ extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); extern int fscrypt_setup_filename(struct inode *, const struct qstr *, int lookup, struct fscrypt_name *); extern void fscrypt_free_filename(struct fscrypt_name *); -extern u32 fscrypt_fname_encrypted_size(struct inode *, u32); -extern int fscrypt_fname_alloc_buffer(struct inode *, u32, +extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); +extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, struct fscrypt_str *); extern void fscrypt_fname_free_buffer(struct fscrypt_str *); extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, @@ -284,7 +284,7 @@ extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, #endif /* crypto.c */ -static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i, +static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(const struct inode *i, gfp_t f) { return ERR_PTR(-EOPNOTSUPP); @@ -295,7 +295,7 @@ static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c) return; } -static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, +static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i, struct page *p, unsigned int len, unsigned int offs, @@ -304,7 +304,7 @@ static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, return ERR_PTR(-EOPNOTSUPP); } -static inline int fscrypt_notsupp_decrypt_page(struct inode *i, struct page *p, +static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p, unsigned int len, unsigned int offs) { return -EOPNOTSUPP; @@ -326,7 +326,7 @@ static inline void fscrypt_notsupp_restore_control_page(struct page *p) return; } -static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, +static inline int fscrypt_notsupp_zeroout_range(const struct inode *i, pgoff_t p, sector_t s, unsigned int f) { return -EOPNOTSUPP; -- cgit From 9c4bb8a3a9b4de21753053d667310c2b7cb39916 Mon Sep 17 00:00:00 2001 From: David Gstir Date: Sun, 13 Nov 2016 22:20:48 +0100 Subject: fscrypt: Let fs select encryption index/tweak Avoid re-use of page index as tweak for AES-XTS when multiple parts of same page are encrypted. This will happen on multiple (partial) calls of fscrypt_encrypt_page on same page. page->index is only valid for writeback pages. Signed-off-by: David Gstir Signed-off-by: Richard Weinberger Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index e9be944a324c..98c71e973a96 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -250,9 +250,9 @@ extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, unsigned int, unsigned int, - gfp_t); + pgoff_t, gfp_t); extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, - unsigned int); + unsigned int, pgoff_t); extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); extern void fscrypt_pullback_bio_page(struct page **, bool); extern void fscrypt_restore_control_page(struct page *); @@ -299,13 +299,14 @@ static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i, struct page *p, unsigned int len, unsigned int offs, - gfp_t f) + pgoff_t index, gfp_t f) { return ERR_PTR(-EOPNOTSUPP); } static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p, - unsigned int len, unsigned int offs) + unsigned int len, unsigned int offs, + pgoff_t index) { return -EOPNOTSUPP; } -- cgit From e29bd6f26703088930a5b3595623cf155ddea600 Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Wed, 2 Nov 2016 11:55:33 +0000 Subject: KVM: arm64: vgic-its: Fix compatibility with 32-bit Evaluate GITS_BASER_ENTRY_SIZE once as an int data (GITS_BASER's Entry Size is 5-bit wide only), so when used as divider no reference to __aeabi_uldivmod is generated when build for AArch32. Use unsigned long long for GITS_BASER_PAGE_SIZE_* since they are used in conjunction with 64-bit data. Signed-off-by: Vladimir Murzin Reviewed-by: Andre Przywara Reviewed-by: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index b7e34313cdfe..0deea34494e7 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -295,10 +295,10 @@ #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) #define GITS_BASER_PAGE_SIZE_SHIFT (8) -#define GITS_BASER_PAGE_SIZE_4K (0UL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_16K (1UL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_64K (2UL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_MASK (3UL << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_4K (0ULL << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_16K (1ULL << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_64K (2ULL << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_MASK (3ULL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGES_MAX 256 #define GITS_BASER_PAGES_SHIFT (0) #define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1) -- cgit From 51f8cc9e818a9e6df376db7aeb5822d43e58cfb3 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 14 Nov 2016 12:16:26 +0000 Subject: iommu/dma: Implement dma_{map,unmap}_resource() With the new dma_{map,unmap}_resource() functions added to the DMA API for the benefit of cases like slave DMA, add suitable implementations to the arsenal of our generic layer. Since cache maintenance should not be a concern, these can both be standalone callback implementations without the need for arch code wrappers. CC: Joerg Roedel Signed-off-by: Robin Murphy Reviewed-by: Catalin Marinas Signed-off-by: Joerg Roedel --- include/linux/dma-iommu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 32c589062bd9..7f7e9a7e3839 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -61,6 +61,10 @@ void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs); void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, unsigned long attrs); int iommu_dma_supported(struct device *dev, u64 mask); int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); -- cgit From 9a1dc3891255afd836f355b117fd6b975d0b1eb2 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Mon, 14 Nov 2016 15:21:14 -0600 Subject: of/pci: Add of_pci_get_max_link_speed() to parse max-link-speed from DT This new helper function could be used by host drivers to get the limitaion of max link speed provided by DT. If the property isn't assigned or is invalid, it will return -EINVAL to the caller. Signed-off-by: Shawn Lin Signed-off-by: Bjorn Helgaas Acked-by: Rob Herring --- include/linux/of_pci.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 7fd5cfce9140..0e0974eceb80 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -16,6 +16,7 @@ int of_pci_get_devfn(struct device_node *np); int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); +int of_pci_get_max_link_speed(struct device_node *node); void of_pci_check_probe_only(void); int of_pci_map_rid(struct device_node *np, u32 rid, const char *map_name, const char *map_mask_name, @@ -62,6 +63,12 @@ static inline int of_pci_map_rid(struct device_node *np, u32 rid, return -EINVAL; } +static inline int +of_pci_get_max_link_speed(struct device_node *node) +{ + return -EINVAL; +} + static inline void of_pci_check_probe_only(void) { } #endif -- cgit From 8fc947230fbc5da1d6d198c758b894f847bf2a28 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 19 Oct 2016 19:40:03 -0700 Subject: rpmsg: smd: Expose edge registration functions The edge registration functions is to be used from a remoteproc driver to register and unregister an edge as the remote processor comes and goes. Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_smd.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 include/linux/rpmsg/qcom_smd.h (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h new file mode 100644 index 000000000000..e674b2e3074b --- /dev/null +++ b/include/linux/rpmsg/qcom_smd.h @@ -0,0 +1,33 @@ + +#ifndef _LINUX_RPMSG_QCOM_SMD_H +#define _LINUX_RPMSG_QCOM_SMD_H + +#include + +struct qcom_smd_edge; + +#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) || IS_ENABLED(CONFIG_QCOM_SMD) + +struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, + struct device_node *node); +int qcom_smd_unregister_edge(struct qcom_smd_edge *edge); + +#else + +static inline struct qcom_smd_edge * +qcom_smd_register_edge(struct device *parent, + struct device_node *node) +{ + return ERR_PTR(-ENXIO); +} + +static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge) +{ + /* This shouldn't be possible */ + WARN_ON(1); + return -ENXIO; +} + +#endif + +#endif -- cgit From aab8d8022304b646fbf6eed5f6ac9bc21d54d2fd Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 19 Oct 2016 19:40:06 -0700 Subject: remoteproc: Assign kref to rproc_vdev No functional change Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index f6d5e66854e4..5def5c84b9c0 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -487,6 +487,7 @@ struct rproc_vring { /** * struct rproc_vdev - remoteproc state for a supported virtio device + * @refcount: reference counter for the vdev and vring allocations * @node: list node * @rproc: the rproc handle * @vdev: the virio device @@ -494,6 +495,8 @@ struct rproc_vring { * @rsc_offset: offset of the vdev's resource entry */ struct rproc_vdev { + struct kref refcount; + struct list_head node; struct rproc *rproc; struct virtio_device vdev; -- cgit From f5bcb35387efc994cfd88f87039d7cdb6c1a06a2 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 19 Oct 2016 19:40:09 -0700 Subject: remoteproc: Decouple vdev resources and devices Represent the virtio device part of the vdev resources as remoteproc subdevices to finalize the decoupling of the virtio resource and device handling. Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 5def5c84b9c0..8265d351c9f0 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -488,6 +488,8 @@ struct rproc_vring { /** * struct rproc_vdev - remoteproc state for a supported virtio device * @refcount: reference counter for the vdev and vring allocations + * @subdev: handle for registering the vdev as a rproc subdevice + * @id: virtio device id (as in virtio_ids.h) * @node: list node * @rproc: the rproc handle * @vdev: the virio device @@ -497,6 +499,9 @@ struct rproc_vring { struct rproc_vdev { struct kref refcount; + struct rproc_subdev subdev; + + unsigned int id; struct list_head node; struct rproc *rproc; struct virtio_device vdev; -- cgit From cda8529346935fc86f476999ac4fbfe4e17abf11 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 19 Oct 2016 19:40:12 -0700 Subject: remoteproc: Merge table_ptr and cached_table pointers As all vdev resources are allocated before we boot the remote processor we no longer need to support modifying the resource table while the remote is running. This saves us from the table_ptr dance, but more importantly allow the remote processor to enable security lock down of the loaded table memory region. Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8265d351c9f0..e2f3a3281d8f 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -408,8 +408,7 @@ enum rproc_crash_type { * @crash_comp: completion used to sync crash handler and the rproc reload * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. - * @table_ptr: pointer to the resource table in effect - * @cached_table: copy of the resource table + * @table_ptr: our copy of the resource table * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { @@ -441,7 +440,6 @@ struct rproc { bool recovery_disabled; int max_notifyid; struct resource_table *table_ptr; - struct resource_table *cached_table; bool has_iommu; bool auto_boot; }; -- cgit From 6bfec6d94556683c91c937a20576118183af9e1d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 14 Nov 2016 11:55:40 +0000 Subject: dma-buf: Use fence_get_rcu_safe() for retrieving the exclusive fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current code is subject to a race where we may try to acquire a reference on a stale fence: [13703.335118] WARNING: CPU: 1 PID: 14975 at ./include/linux/kref.h:46 i915_gem_object_wait+0x1a3/0x1c0 [13703.335184] Modules linked in: [13703.335202] CPU: 1 PID: 14975 Comm: gem_concurrent_ Not tainted 4.9.0-rc4+ #26 [13703.335216] Hardware name: / , BIOS PYBSWCEL.86A.0027.2015.0507.1758 05/07/2015 [13703.335233] ffffc90002f5bcc8 ffffffff812807de 0000000000000000 0000000000000000 [13703.335257] ffffc90002f5bd08 ffffffff81073811 0000002e80000000 ffff88026bf7c780 [13703.335279] 7fffffffffffffff 0000000000000001 ffff88027045a550 ffff88026bf7c780 [13703.335301] Call Trace: [13703.335316] [] dump_stack+0x4d/0x6f [13703.335331] [] __warn+0xc1/0xe0 [13703.335343] [] warn_slowpath_null+0x18/0x20 [13703.335355] [] i915_gem_object_wait+0x1a3/0x1c0 [13703.335367] [] i915_gem_set_domain_ioctl+0xcc/0x330 [13703.335386] [] drm_ioctl+0x1cb/0x410 [13703.335400] [] ? i915_gem_obj_prepare_shmem_write+0x1d0/0x1d0 [13703.335416] [] ? drm_ioctl+0x2bb/0x410 [13703.335429] [] do_vfs_ioctl+0x8f/0x5c0 [13703.335442] [] SyS_ioctl+0x3c/0x70 [13703.335456] [] entry_SYSCALL_64_fastpath+0x17/0x98 [13703.335558] ---[ end trace fd24176416ba6981 ]--- [13703.382778] general protection fault: 0000 [#1] SMP [13703.382802] Modules linked in: [13703.382816] CPU: 1 PID: 14967 Comm: gem_concurrent_ Tainted: G W 4.9.0-rc4+ #26 [13703.382828] Hardware name: / , BIOS PYBSWCEL.86A.0027.2015.0507.1758 05/07/2015 [13703.382841] task: ffff880275458000 task.stack: ffffc90002f18000 [13703.382849] RIP: 0010:[] [] i915_gem_request_retire+0x2b4/0x320 [13703.382870] RSP: 0018:ffffc90002f1bbc8 EFLAGS: 00010293 [13703.382878] RAX: dead000000000200 RBX: ffff88026bf7dce8 RCX: dead000000000100 [13703.382887] RDX: dead000000000100 RSI: ffff88026bf7c930 RDI: ffff88026bf7dd00 [13703.382897] RBP: ffffc90002f1bbf8 R08: 00000000ffffffff R09: ffff88026b89a000 [13703.382905] R10: 0000000000000001 R11: ffff88026bbe8fe0 R12: ffff88026bf7c000 [13703.382913] R13: ffff880275af8000 R14: ffff88026bf7c180 R15: dead000000000200 [13703.382922] FS: 00007f89e787d740(0000) GS:ffff88027fd00000(0000) knlGS:0000000000000000 [13703.382934] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13703.382942] CR2: 00007f9053d2e000 CR3: 000000026d414000 CR4: 00000000001006e0 [13703.382951] Stack: [13703.382958] ffff880275413000 ffffc90002f1bde8 ffff880275af8000 ffff880274e8a600 [13703.382976] ffff880276a06000 ffffc90002f1bde8 ffffc90002f1bc38 ffffffff813b48c5 [13703.382995] ffffc90002f1bc00 ffffc90002f1bde8 ffff88026972a440 0000000000000000 [13703.383021] Call Trace: [13703.383032] [] i915_gem_request_alloc+0xa5/0x350 [13703.383043] [] i915_gem_do_execbuffer.isra.41+0x7b3/0x18b0 [13703.383055] [] ? i915_gem_object_get_sg+0x25c/0x2b0 [13703.383065] [] ? i915_gem_object_get_page+0x1d/0x50 [13703.383076] [] ? i915_gem_pwrite_ioctl+0x66c/0x6d0 [13703.383086] [] i915_gem_execbuffer2+0x95/0x1e0 [13703.383096] [] drm_ioctl+0x1cb/0x410 [13703.383105] [] ? i915_gem_execbuffer+0x2d0/0x2d0 [13703.383117] [] ? hrtimer_start_range_ns+0x1a0/0x310 [13703.383128] [] do_vfs_ioctl+0x8f/0x5c0 [13703.383140] [] ? SyS_timer_settime+0x118/0x1a0 [13703.383150] [] SyS_ioctl+0x3c/0x70 [13703.383162] [] entry_SYSCALL_64_fastpath+0x17/0x98 [13703.383172] Code: 49 39 c6 48 8d 70 e8 48 8d 5f e8 75 16 eb 47 48 8d 43 18 48 8b 53 18 48 89 de 49 39 c6 48 8d 5a e8 74 33 48 8b 56 08 48 8b 46 10 <48> 89 42 08 48 89 10 f6 46 38 01 48 89 4e 08 4c 89 7e 10 74 cf [13703.383557] RIP [] i915_gem_request_retire+0x2b4/0x320 [13703.383570] RSP [13703.383586] ---[ end trace fd24176416ba6982 ]--- This is fixed by using the kref_get_unless_zero() as a full memory barrier to validate the fence is still the current exclusive fence before returning it back to the caller. (Note the fix only requires using dma_fence_get_rcu() and correct handling, but we may as well use the helper rather than inline equivalent code.) Note: Issue can only be hit with the i915 driver. Signed-off-by: Chris Wilson Cc: Sumit Semwal . Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161114115540.31155-1-chris@chris-wilson.co.uk --- include/linux/reservation.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 2e313cca08f0..d9706a6f5ae2 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -177,17 +177,14 @@ static inline struct dma_fence * reservation_object_get_excl_rcu(struct reservation_object *obj) { struct dma_fence *fence; - unsigned seq; -retry: - seq = read_seqcount_begin(&obj->seq); + + if (!rcu_access_pointer(obj->fence_excl)) + return NULL; + rcu_read_lock(); - fence = rcu_dereference(obj->fence_excl); - if (read_seqcount_retry(&obj->seq, seq)) { - rcu_read_unlock(); - goto retry; - } - fence = dma_fence_get(fence); + fence = dma_fence_get_rcu_safe(&obj->fence_excl); rcu_read_unlock(); + return fence; } -- cgit From 40565b5aedd6d0ca88b7dfd3859d709d2f6f8cf9 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 15 Nov 2016 03:06:51 +0100 Subject: sched/cputime, powerpc, s390: Make scaled cputime arch specific Only s390 and powerpc have hardware facilities allowing to measure cputimes scaled by frequency. On all other architectures utimescaled/stimescaled are equal to utime/stime (however they are accounted separately). Remove {u,s}timescaled accounting on all architectures except powerpc and s390, where those values are explicitly accounted in the proper places. Signed-off-by: Stanislaw Gruszka Signed-off-by: Frederic Weisbecker Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Paul Mackerras Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161031162143.GB12646@redhat.com Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 4 ++-- include/linux/sched.h | 23 +++++++++++++++++------ 2 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 44fda64ad434..00f776816aa3 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -78,8 +78,8 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) return kstat_cpu(cpu).irqs_sum; } -extern void account_user_time(struct task_struct *, cputime_t, cputime_t); -extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t); +extern void account_user_time(struct task_struct *, cputime_t); +extern void account_system_time(struct task_struct *, int, cputime_t); extern void account_steal_time(cputime_t); extern void account_idle_time(cputime_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 3762fe4e3a80..f72e81395dac 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1647,7 +1647,10 @@ struct task_struct { int __user *set_child_tid; /* CLONE_CHILD_SETTID */ int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ - cputime_t utime, stime, utimescaled, stimescaled; + cputime_t utime, stime; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME + cputime_t utimescaled, stimescaled; +#endif cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -2240,8 +2243,6 @@ struct task_struct *try_get_task_struct(struct task_struct **ptask); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime); -extern void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, cputime_t *stimescaled); extern cputime_t task_gtime(struct task_struct *t); #else static inline void task_cputime(struct task_struct *t, @@ -2253,6 +2254,13 @@ static inline void task_cputime(struct task_struct *t, *stime = t->stime; } +static inline cputime_t task_gtime(struct task_struct *t) +{ + return t->gtime; +} +#endif + +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME static inline void task_cputime_scaled(struct task_struct *t, cputime_t *utimescaled, cputime_t *stimescaled) @@ -2262,12 +2270,15 @@ static inline void task_cputime_scaled(struct task_struct *t, if (stimescaled) *stimescaled = t->stimescaled; } - -static inline cputime_t task_gtime(struct task_struct *t) +#else +static inline void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, + cputime_t *stimescaled) { - return t->gtime; + task_cputime(t, utimescaled, stimescaled); } #endif + extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); -- cgit From 353c50ebe329daaf2c94dc41c1c481cbba2a31fd Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 15 Nov 2016 03:06:52 +0100 Subject: sched/cputime: Simplify task_cputime() Now since fetch_task_cputime() has no other users than task_cputime(), its code could be used directly in task_cputime(). Moreover since only 2 task_cputime() calls of 17 use a NULL argument, we can add dummy variables to those calls and remove NULL checks from task_cputimes(). Also remove NULL checks from task_cputimes_scaled(). Signed-off-by: Stanislaw Gruszka Signed-off-by: Frederic Weisbecker Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Paul Mackerras Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1479175612-14718-5-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f72e81395dac..fe3ce46cfd03 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2248,10 +2248,8 @@ extern cputime_t task_gtime(struct task_struct *t); static inline void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) { - if (utime) - *utime = t->utime; - if (stime) - *stime = t->stime; + *utime = t->utime; + *stime = t->stime; } static inline cputime_t task_gtime(struct task_struct *t) @@ -2265,10 +2263,8 @@ static inline void task_cputime_scaled(struct task_struct *t, cputime_t *utimescaled, cputime_t *stimescaled) { - if (utimescaled) - *utimescaled = t->utimescaled; - if (stimescaled) - *stimescaled = t->stimescaled; + *utimescaled = t->utimescaled; + *stimescaled = t->stimescaled; } #else static inline void task_cputime_scaled(struct task_struct *t, -- cgit From 13f59a78c6d69a9bf4c8989dd5f3396f54a2fe41 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 11 Nov 2016 17:59:21 +0000 Subject: iommu: Allow taking a reference on a group directly iommu_group_get_for_dev() expects that the IOMMU driver's device_group callback return a group with a reference held for the given device. Whilst allocating a new group is fine, and pci_device_group() correctly handles reusing an existing group, there is no general means for IOMMU drivers doing their own group lookup to take additional references on an existing group pointer without having to also store device pointers or resort to elaborate trickery. Add an IOMMU-driver-specific function to fill the hole. Acked-by: Sricharan R Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 436dc21318af..431638110c6a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -253,6 +253,7 @@ extern void iommu_group_remove_device(struct device *dev); extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, int (*fn)(struct device *, void *)); extern struct iommu_group *iommu_group_get(struct device *dev); +extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); extern int iommu_group_register_notifier(struct iommu_group *group, struct notifier_block *nb); -- cgit From 8a5846bf5d4756db1d4e03305217189c1c0e7160 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 14 Nov 2016 12:58:18 +0100 Subject: doc/dma-buf: Fix up include directives MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Would be great if everony could add $ make DOCBOOKS="" htmldocs to their build scripts to catch these. 0day should also report them, not sure why it failed to spot this. Fixes: f54d1867005c ("dma-buf: Rename struct fence to dma_fence") Cc: Chris Wilson Cc: Gustavo Padovan Cc: Sumit Semwal Cc: Christian König Reviewed-by: Chris Wilson Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161114115825.22050-4-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index fcf4b1971eba..d51a7d23c358 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -225,7 +225,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence) /** * dma_fence_get_rcu_safe - acquire a reference to an RCU tracked fence - * @fence: [in] pointer to fence to increase refcount of + * @fencep: [in] pointer to fence to increase refcount of * * Function returns NULL if no refcount could be obtained, or the fence. * This function handles acquiring a reference to a fence that may be -- cgit From 0f5225b024d4bffd682aab008c35862e8fdc1865 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 7 Oct 2016 17:43:51 +0200 Subject: locking/mutex, drm: Introduce mutex_trylock_recursive() By popular DRM demand, introduce mutex_trylock_recursive() to fix up the two GEM users. Without this it is very easy for these drivers to get stuck in low-memory situations and trigger OOM. Work is in progress to remove the need for this in at least i915. Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Davidlohr Bueso Cc: Ding Tianhong Cc: Imre Deak Cc: Jason Low Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rob Clark Cc: Terry Rudd Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 4d3bccabbea5..6a902f0a2148 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -189,4 +189,35 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +/* + * These values are chosen such that FAIL and SUCCESS match the + * values of the regular mutex_trylock(). + */ +enum mutex_trylock_recursive_enum { + MUTEX_TRYLOCK_FAILED = 0, + MUTEX_TRYLOCK_SUCCESS = 1, + MUTEX_TRYLOCK_RECURSIVE, +}; + +/** + * mutex_trylock_recursive - trylock variant that allows recursive locking + * @lock: mutex to be locked + * + * This function should not be used, _ever_. It is purely for hysterical GEM + * raisins, and once those are gone this will be removed. + * + * Returns: + * MUTEX_TRYLOCK_FAILED - trylock failed, + * MUTEX_TRYLOCK_SUCCESS - lock acquired, + * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. + */ +static inline __deprecated __must_check enum mutex_trylock_recursive_enum +mutex_trylock_recursive(struct mutex *lock) +{ + if (unlikely(__mutex_owner(lock) == current)) + return MUTEX_TRYLOCK_RECURSIVE; + + return mutex_trylock(lock); +} + #endif /* __LINUX_MUTEX_H */ -- cgit From 4a4f86cc7d6bc74522f581341a2cae3119d5a0f5 Mon Sep 17 00:00:00 2001 From: pravin shelar Date: Sun, 13 Nov 2016 20:43:52 -0800 Subject: vxlan: avoid vlan processing in vxlan device. VxLan device does not have special handling for vlan taging on egress. Therefore it does not make sense to expose vlan offloading feature. This patch does not change vxlan functinality. Signed-off-by: Pravin B Shelar Acked-by: Jiri Benc Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3319d97d789d..8d5fcd6284ce 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -399,22 +399,6 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) skb->vlan_tci = 0; return skb; } -/* - * vlan_hwaccel_push_inside - pushes vlan tag to the payload - * @skb: skbuff to tag - * - * Checks is tag is present in @skb->vlan_tci and if it is, it pushes the - * VLAN tag from @skb->vlan_tci inside to the payload. - * - * Following the skb_unshare() example, in case of error, the calling function - * doesn't have to worry about freeing the original skb. - */ -static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb) -{ - if (skb_vlan_tag_present(skb)) - skb = __vlan_hwaccel_push_inside(skb); - return skb; -} /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting -- cgit From e86a8987e458a1826f509c41494b0b29a61144a7 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 15 Nov 2016 10:06:30 -0800 Subject: net: phy: Add phy_ethtool_nway_reset This function just calls into genphy_restart_aneg() to perform an autonegotation restart. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9880d73a2c3d..b9bd3b4f4ea1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -860,6 +860,7 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); +int phy_ethtool_nway_reset(struct net_device *ndev); int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit From 663deb47880f2283809669563c5a52ac7c6aef1a Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 20 Oct 2016 00:34:01 -0700 Subject: pstore: Allow prz to control need for locking In preparation of not locking at all for certain buffers depending on if there's contention, make locking optional depending on the initialization of the prz. Signed-off-by: Joel Fernandes [kees: moved locking flag into prz instead of via caller arguments] Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 244d2423dbaf..4058bf991868 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -24,6 +24,13 @@ #include #include +/* + * Choose whether access to the RAM zone requires locking or not. If a zone + * can be written to from different CPUs like with ftrace for example, then + * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required. + */ +#define PRZ_FLAG_NO_LOCK BIT(0) + struct persistent_ram_buffer; struct rs_control; @@ -40,6 +47,7 @@ struct persistent_ram_zone { void *vaddr; struct persistent_ram_buffer *buffer; size_t buffer_size; + u32 flags; raw_spinlock_t buffer_lock; /* ECC correction */ @@ -56,7 +64,7 @@ struct persistent_ram_zone { struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype); + unsigned int memtype, u32 flags); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); -- cgit From a1cf53ac6d156721afa86453d5e8423461881231 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 20 Oct 2016 00:34:04 -0700 Subject: ramoops: Split ftrace buffer space into per-CPU zones If the RAMOOPS_FLAG_FTRACE_PER_CPU flag is passed to ramoops pdata, split the ftrace space into multiple zones depending on the number of CPUs. This speeds up the performance of function tracing by about 280% in my tests as we avoid the locking. The trade off being lesser space available per CPU. Let the ramoops user decide which option they want based on pdata flag. Signed-off-by: Joel Fernandes [kees: added max_ftrace_cnt to track size, added DT logic and docs] Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 4058bf991868..9395f06e8372 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -86,6 +86,8 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, * @mem_address physical memory address to contain ramoops */ +#define RAMOOPS_FLAG_FTRACE_PER_CPU BIT(0) + struct ramoops_platform_data { unsigned long mem_size; phys_addr_t mem_address; @@ -95,6 +97,7 @@ struct ramoops_platform_data { unsigned long ftrace_size; unsigned long pmsg_size; int dump_oops; + u32 flags; struct persistent_ram_ecc_info ecc_info; }; -- cgit From fbccdeb8d77d6830556bc4079eeed80298cc97dc Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 20 Oct 2016 00:34:05 -0700 Subject: pstore: Add ftrace timestamp counter In preparation for merging the per CPU buffers into one buffer when we retrieve the pstore ftrace data, we store the timestamp as a counter in the ftrace pstore record. We store the CPU number as well if !PSTORE_CPU_IN_IP, in this case we shift the counter and may lose ordering there but we preserve the same record size. The timestamp counter is also racy, and not doing any locking or synchronization here results in the benefit of lower overhead. Since we don't care much here for exact ordering of function traces across CPUs, we don't synchronize and may lose some counter updates but I'm ok with that. Using trace_clock() results in much lower performance so avoid using it since we don't want accuracy in timestamp and need a rough ordering to perform merge. Signed-off-by: Joel Fernandes [kees: updated commit message, added comments] Signed-off-by: Kees Cook --- include/linux/pstore.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 92013cc9cc8c..0da29cae009b 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -89,4 +89,80 @@ extern int pstore_register(struct pstore_info *); extern void pstore_unregister(struct pstore_info *); extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason); +struct pstore_ftrace_record { + unsigned long ip; + unsigned long parent_ip; + u64 ts; +}; + +/* + * ftrace related stuff: Both backends and frontends need these so expose + * them here. + */ + +#if NR_CPUS <= 2 && defined(CONFIG_ARM_THUMB) +#define PSTORE_CPU_IN_IP 0x1 +#elif NR_CPUS <= 4 && defined(CONFIG_ARM) +#define PSTORE_CPU_IN_IP 0x3 +#endif + +#define TS_CPU_SHIFT 8 +#define TS_CPU_MASK (BIT(TS_CPU_SHIFT) - 1) + +/* + * If CPU number can be stored in IP, store it there, otherwise store it in + * the time stamp. This means more timestamp resolution is available when + * the CPU can be stored in the IP. + */ +#ifdef PSTORE_CPU_IN_IP +static inline void +pstore_ftrace_encode_cpu(struct pstore_ftrace_record *rec, unsigned int cpu) +{ + rec->ip |= cpu; +} + +static inline unsigned int +pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec) +{ + return rec->ip & PSTORE_CPU_IN_IP; +} + +static inline u64 +pstore_ftrace_read_timestamp(struct pstore_ftrace_record *rec) +{ + return rec->ts; +} + +static inline void +pstore_ftrace_write_timestamp(struct pstore_ftrace_record *rec, u64 val) +{ + rec->ts = val; +} +#else +static inline void +pstore_ftrace_encode_cpu(struct pstore_ftrace_record *rec, unsigned int cpu) +{ + rec->ts &= ~(TS_CPU_MASK); + rec->ts |= cpu; +} + +static inline unsigned int +pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec) +{ + return rec->ts & TS_CPU_MASK; +} + +static inline u64 +pstore_ftrace_read_timestamp(struct pstore_ftrace_record *rec) +{ + return rec->ts >> TS_CPU_SHIFT; +} + +static inline void +pstore_ftrace_write_timestamp(struct pstore_ftrace_record *rec, u64 val) +{ + rec->ts = (rec->ts & TS_CPU_MASK) | (val << TS_CPU_SHIFT); +} +#endif + #endif /*_LINUX_PSTORE_H*/ -- cgit From d032ae8921ea792c1e6b2abb44022b2403f651f6 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Tue, 15 Nov 2016 12:31:20 -0800 Subject: ftrace: Provide API to use global filtering for ftrace ops Currently the global_ops filtering hash is not available to outside users registering for function tracing. Provide an API for those users to be able to choose global filtering. This is in preparation for pstore's ftrace feature to be able to use the global filters. Suggested-by: Steven Rostedt Cc: Anton Vorontsov Cc: Colin Cross Cc: Kees Cook Cc: Tony Luck Signed-off-by: Joel Fernandes Acked-by: Steven Rostedt Signed-off-by: Kees Cook --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b3d34d3e0e7e..d4a884db16a3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -398,6 +398,7 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, void ftrace_set_global_filter(unsigned char *buf, int len, int reset); void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); void ftrace_free_filter(struct ftrace_ops *ops); +void ftrace_ops_set_global_filter(struct ftrace_ops *ops); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); @@ -645,6 +646,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) +#define ftrace_ops_set_global_filter(ops) do { } while (0) static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { return -ENODEV; } -- cgit From ff86aae3b4112b85d2231c23bccbc49589df1c06 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Tue, 15 Nov 2016 10:41:01 +0200 Subject: devres: add devm_alloc_percpu() Introduce managed counterparts for alloc_percpu() and free_percpu(). Add devm_alloc_percpu() and devm_free_percpu() into the managed interfaces list. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- include/linux/device.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index bc41e87a969b..a00105cf795e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -698,6 +698,25 @@ static inline int devm_add_action_or_reset(struct device *dev, return ret; } +/** + * devm_alloc_percpu - Resource-managed alloc_percpu + * @dev: Device to allocate per-cpu memory for + * @type: Type to allocate per-cpu memory for + * + * Managed alloc_percpu. Per-cpu memory allocated with this function is + * automatically freed on driver detach. + * + * RETURNS: + * Pointer to allocated memory on success, NULL on failure. + */ +#define devm_alloc_percpu(dev, type) \ + ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ + __alignof__(type))) + +void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, + size_t align); +void devm_free_percpu(struct device *dev, void __percpu *pdata); + struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about -- cgit From d1cbfd771ce8297fa11e89f315392de6056a2181 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Fri, 11 Nov 2016 00:10:07 -0500 Subject: ptp_clock: Allow for it to be optional In order to break the hard dependency between the PTP clock subsystem and ethernet drivers capable of being clock providers, this patch provides simple PTP stub functions to allow linkage of those drivers into the kernel even when the PTP subsystem is configured out. Drivers must be ready to accept NULL from ptp_clock_register() in that case. And to make it possible for PTP to be configured out, the select statement in those driver's Kconfig menu entries is converted to the new "imply" statement. This way the PTP subsystem may have Kconfig dependencies of its own, such as POSIX_TIMERS, without having to make those ethernet drivers unavailable if POSIX timers are cconfigured out. And when support for POSIX timers is selected again then the default config option for PTP clock support will automatically be adjusted accordingly. The pch_gbe driver is a bit special as it relies on extra code in drivers/ptp/ptp_pch.c. Therefore we let the make process descend into drivers/ptp/ even if PTP_1588_CLOCK is unselected. Signed-off-by: Nicolas Pitre Acked-by: Richard Cochran Acked-by: Edward Cree Acked-by: Thomas Gleixner Acked-by: John Stultz Reviewed-by: Josh Triplett Cc: Paul Bolle Cc: linux-kbuild@vger.kernel.org Cc: netdev@vger.kernel.org Cc: Michal Marek Link: http://lkml.kernel.org/r/1478841010-28605-4-git-send-email-nicolas.pitre@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/ptp_clock_kernel.h | 65 +++++++++++++++++++++++++--------------- 1 file changed, 41 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 5ad54fc66cf0..96699526d342 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -122,30 +122,6 @@ struct ptp_clock_info { struct ptp_clock; -/** - * ptp_clock_register() - register a PTP hardware clock driver - * - * @info: Structure describing the new clock. - * @parent: Pointer to the parent device of the new clock. - * - * Returns a valid pointer on success or PTR_ERR on failure. If PHC - * support is missing at the configuration level, this function - * returns NULL, and drivers are expected to gracefully handle that - * case separately. - */ - -extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, - struct device *parent); - -/** - * ptp_clock_unregister() - unregister a PTP hardware clock driver - * - * @ptp: The clock to remove from service. - */ - -extern int ptp_clock_unregister(struct ptp_clock *ptp); - - enum ptp_clock_events { PTP_CLOCK_ALARM, PTP_CLOCK_EXTTS, @@ -171,6 +147,31 @@ struct ptp_clock_event { }; }; +#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) + +/** + * ptp_clock_register() - register a PTP hardware clock driver + * + * @info: Structure describing the new clock. + * @parent: Pointer to the parent device of the new clock. + * + * Returns a valid pointer on success or PTR_ERR on failure. If PHC + * support is missing at the configuration level, this function + * returns NULL, and drivers are expected to gracefully handle that + * case separately. + */ + +extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent); + +/** + * ptp_clock_unregister() - unregister a PTP hardware clock driver + * + * @ptp: The clock to remove from service. + */ + +extern int ptp_clock_unregister(struct ptp_clock *ptp); + /** * ptp_clock_event() - notify the PTP layer about an event * @@ -202,4 +203,20 @@ extern int ptp_clock_index(struct ptp_clock *ptp); int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan); +#else +static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent) +{ return NULL; } +static inline int ptp_clock_unregister(struct ptp_clock *ptp) +{ return 0; } +static inline void ptp_clock_event(struct ptp_clock *ptp, + struct ptp_clock_event *event) +{ } +static inline int ptp_clock_index(struct ptp_clock *ptp) +{ return -1; } +static inline int ptp_find_pin(struct ptp_clock *ptp, + enum ptp_pin_function func, unsigned int chan) +{ return -1; } +#endif + #endif -- cgit From 74ba181e61c6accf9066d6980f44588de2f854f6 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Fri, 11 Nov 2016 00:10:08 -0500 Subject: timer: Move sys_alarm from timer.c to itimer.c Move the only user of alarm_setitimer to itimer.c where it is defined. This allows for making alarm_setitimer static, and dropping it from the build when __ARCH_WANT_SYS_ALARM is not defined. Signed-off-by: Nicolas Pitre Acked-by: John Stultz Cc: Paul Bolle Cc: linux-kbuild@vger.kernel.org Cc: netdev@vger.kernel.org Cc: Richard Cochran Cc: Josh Triplett Cc: Michal Marek Cc: Edward Cree Link: http://lkml.kernel.org/r/1478841010-28605-5-git-send-email-nicolas.pitre@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/time.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 4cea09d94208..23f0f5ce3090 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -172,8 +172,6 @@ extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); extern int do_getitimer(int which, struct itimerval *value); -extern unsigned int alarm_setitimer(unsigned int seconds); - extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct tms; -- cgit From 0e285d36bd2bfee0b95433ccc9065c878164f5b2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 10 Nov 2016 18:44:47 +0100 Subject: x86/mcheck: Move CPU_DEAD to hotplug state machine This moves the last piece of the old hotplug notifier code in MCE to the new hotplug state machine. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Borislav Petkov Cc: Tony Luck Cc: rt@linutronix.de Cc: linux-edac@vger.kernel.org Link: http://lkml.kernel.org/r/20161110174447.11848-8-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3410d83cc2e2..79b96f647d64 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -16,6 +16,7 @@ enum cpuhp_state { CPUHP_PERF_SUPERH, CPUHP_X86_HPET_DEAD, CPUHP_X86_APB_DEAD, + CPUHP_X86_MCE_DEAD, CPUHP_VIRT_NET_DEAD, CPUHP_SLUB_DEAD, CPUHP_MM_WRITEBACK_DEAD, -- cgit From 43496d35513b25ad468bef91e51a39d61a0d8464 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 16 Nov 2016 10:36:05 +0100 Subject: locking/mutex: Don't mark mutex_trylock_recursive() as deprecated, temporarily MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Until the DRM drivers are fixed to not use mutex_trylock_recursive(), allyes/modconfig builds will emit an API deprecation warning: drivers/gpu/drm/i915/i915_gem_shrinker.c: In function ‘i915_gem_shrinker_lock’: drivers/gpu/drm/i915/i915_gem_shrinker.c:230:2: warning: ‘mutex_trylock_recursive’ is deprecated [-Wdeprecated-declarations] switch (mutex_trylock_recursive(&dev->struct_mutex)) { ^ Don't pollute the kernel log until the DRM code is fixed. Hopefully the checkpatch warning is enough to keep people from using this new API, and we'll be NAK-ing new users as well. Cc: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Davidlohr Bueso Cc: Ding Tianhong Cc: Imre Deak Cc: Jason Low Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rob Clark Cc: Terry Rudd Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 6a902f0a2148..b97870f2debd 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -211,7 +211,7 @@ enum mutex_trylock_recursive_enum { * MUTEX_TRYLOCK_SUCCESS - lock acquired, * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. */ -static inline __deprecated __must_check enum mutex_trylock_recursive_enum +static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum mutex_trylock_recursive(struct mutex *lock) { if (unlikely(__mutex_owner(lock) == current)) -- cgit From 98838d95075a5295f3478ceba18bcccf472e30f4 Mon Sep 17 00:00:00 2001 From: Ed Blake Date: Thu, 10 Nov 2016 18:07:54 +0000 Subject: serial: 8250: Add IrDA to UART capabilities Add an IrDA UART capability flag and change the type of uart_8250_port.capabilities to be u32 rather than unsigned short to accommodate the additional flag. Signed-off-by: Ed Blake Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 48ec7651989b..04185e03d7be 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -94,7 +94,7 @@ struct uart_8250_port { struct uart_port port; struct timer_list timer; /* "no irq" timer */ struct list_head list; /* ports on this IRQ */ - unsigned short capabilities; /* port capabilities */ + u32 capabilities; /* port capabilities */ unsigned short bugs; /* port bugs */ bool fifo_bug; /* min RX trigger if enabled */ unsigned int tx_loadsz; /* transmit fifo load size */ @@ -168,6 +168,6 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe); extern void serial8250_set_isa_configurator(void (*v) (int port, struct uart_port *up, - unsigned short *capabilities)); + u32 *capabilities)); #endif -- cgit From db405a8f8bf70daf57ed88808a2bf9c5fe308c70 Mon Sep 17 00:00:00 2001 From: Ed Blake Date: Thu, 10 Nov 2016 18:07:55 +0000 Subject: serial: 8250: Expose set_ldisc function Expose set_ldisc() function so that it can be overridden with a platform specific implementation. Signed-off-by: Ed Blake Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 4 ++++ include/linux/serial_core.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 04185e03d7be..61fbb440449c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -36,6 +36,8 @@ struct plat_serial8250_port { void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + void (*set_ldisc)(struct uart_port *, + struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, @@ -149,6 +151,8 @@ extern int early_serial8250_setup(struct earlycon_device *device, const char *options); extern void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old); +extern void serial8250_do_set_ldisc(struct uart_port *port, + struct ktermios *termios); extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); extern int serial8250_do_startup(struct uart_port *port); extern void serial8250_do_shutdown(struct uart_port *port); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 344201437017..5d494888a612 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -123,6 +123,8 @@ struct uart_port { void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + void (*set_ldisc)(struct uart_port *, + struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); int (*startup)(struct uart_port *port); -- cgit From f4062625ede8f0280d8246437f4070c8eb7fe9f3 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 1 Nov 2016 07:59:34 -0200 Subject: [media] cec: add flag to cec_log_addrs to enable RC passthrough By default the CEC_MSG_USER_CONTROL_PRESSED/RELEASED messages are passed on to the follower(s) only. If the new CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU flag is set in the flags field of struct cec_log_addrs then these messages are also passed on to the remote control input subsystem and they will appear as keystrokes. This used to be the default behavior, but now you have to explicitly enable it. This is done to force the caller to think about possible security issues (e.g. if these messages are used to enter passwords). Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cec.h b/include/linux/cec.h index 851968e803fa..825455fae3cc 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -391,6 +391,8 @@ struct cec_log_addrs { /* Allow a fallback to unregistered */ #define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) +/* Passthrough RC messages to the input subsystem */ +#define CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU (1 << 1) /* Events */ -- cgit From adc0c622783978ab0c740af77f98fc8f65c87d66 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 1 Nov 2016 08:55:05 -0200 Subject: [media] cec: add CEC_MSG_FL_REPLY_TO_FOLLOWERS Give the caller more control over how replies to a transmit are handled. By default the reply will only go to the filehandle that called CEC_TRANSMIT. If this new flag is set, then the reply will also go to all followers. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cec.h b/include/linux/cec.h index 825455fae3cc..3f2f076027b1 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -175,7 +175,10 @@ static inline void cec_msg_set_reply_to(struct cec_msg *msg, msg->reply = msg->timeout = 0; } -/* cec status field */ +/* cec_msg flags field */ +#define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) + +/* cec_msg tx/rx_status field */ #define CEC_TX_STATUS_OK (1 << 0) #define CEC_TX_STATUS_ARB_LOST (1 << 1) #define CEC_TX_STATUS_NACK (1 << 2) -- cgit From a69a168a1bd470cb8a8c5f2ff4b54463de615226 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 2 Nov 2016 07:41:41 -0200 Subject: [media] cec: add proper support for CDC-Only CEC devices CDC-Only CEC devices are CEC devices that can only handle CDC messages, all other messages are ignored. Add a flag to signal that this is a CDC-Only device and act accordingly. Also add helper functions to identify if a CEC device is configured as a CDC-Only device, a second TV, a switch or a processor, since these variations cannot be determined by the logical address alone. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cec.h b/include/linux/cec.h index 3f2f076027b1..9c87711c0e1c 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -396,6 +396,8 @@ struct cec_log_addrs { #define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) /* Passthrough RC messages to the input subsystem */ #define CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU (1 << 1) +/* CDC-Only device: supports only CDC messages */ +#define CEC_LOG_ADDRS_FL_CDC_ONLY (1 << 2) /* Events */ @@ -1016,4 +1018,54 @@ struct cec_event { #define CEC_OP_HPD_ERROR_OTHER 3 #define CEC_OP_HPD_ERROR_NONE_NO_VIDEO 4 +/* End of Messages */ + +/* Helper functions to identify the 'special' CEC devices */ + +static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) +{ + /* + * It is a second TV if the logical address is 14 or 15 and the + * primary device type is a TV. + */ + return las->num_log_addrs && + las->log_addr[0] >= CEC_LOG_ADDR_SPECIFIC && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_TV; +} + +static inline bool cec_is_processor(const struct cec_log_addrs *las) +{ + /* + * It is a processor if the logical address is 12-15 and the + * primary device type is a Processor. + */ + return las->num_log_addrs && + las->log_addr[0] >= CEC_LOG_ADDR_BACKUP_1 && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_PROCESSOR; +} + +static inline bool cec_is_switch(const struct cec_log_addrs *las) +{ + /* + * It is a switch if the logical address is 15 and the + * primary device type is a Switch and the CDC-Only flag is not set. + */ + return las->num_log_addrs == 1 && + las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && + !(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); +} + +static inline bool cec_is_cdc_only(const struct cec_log_addrs *las) +{ + /* + * It is a CDC-only device if the logical address is 15 and the + * primary device type is a Switch and the CDC-Only flag is set. + */ + return las->num_log_addrs == 1 && + las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && + las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && + (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); +} + #endif -- cgit From 0dbacebede1e4e44bf500f94d692fad05eb2c293 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 2 Nov 2016 08:25:28 -0200 Subject: [media] cec: move the CEC framework out of staging and to media The last open issues have been addressed, so it is time to move this out of staging and into the mainline and to move the public cec headers to include/uapi/linux. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 1971 --------------------------------------------- include/linux/cec.h | 1071 ------------------------ 2 files changed, 3042 deletions(-) delete mode 100644 include/linux/cec-funcs.h delete mode 100644 include/linux/cec.h (limited to 'include/linux') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h deleted file mode 100644 index 138bbf721e70..000000000000 --- a/include/linux/cec-funcs.h +++ /dev/null @@ -1,1971 +0,0 @@ -/* - * cec - HDMI Consumer Electronics Control message functions - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -/* - * Note: this framework is still in staging and it is likely the API - * will change before it goes out of staging. - * - * Once it is moved out of staging this header will move to uapi. - */ -#ifndef _CEC_UAPI_FUNCS_H -#define _CEC_UAPI_FUNCS_H - -#include - -/* One Touch Play Feature */ -static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_active_source(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_image_view_on(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_IMAGE_VIEW_ON; -} - -static inline void cec_msg_text_view_on(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TEXT_VIEW_ON; -} - - -/* Routing Control Feature */ -static inline void cec_msg_inactive_source(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_INACTIVE_SOURCE; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_inactive_source(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_request_active_source(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; - msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; -} - -static inline void cec_msg_routing_information(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_routing_information(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_routing_change(struct cec_msg *msg, - bool reply, - __u16 orig_phys_addr, - __u16 new_phys_addr) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_ROUTING_CHANGE; - msg->msg[2] = orig_phys_addr >> 8; - msg->msg[3] = orig_phys_addr & 0xff; - msg->msg[4] = new_phys_addr >> 8; - msg->msg[5] = new_phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_ROUTING_INFORMATION : 0; -} - -static inline void cec_ops_routing_change(const struct cec_msg *msg, - __u16 *orig_phys_addr, - __u16 *new_phys_addr) -{ - *orig_phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *new_phys_addr = (msg->msg[4] << 8) | msg->msg[5]; -} - -static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_SET_STREAM_PATH; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; -} - -static inline void cec_ops_set_stream_path(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - - -/* Standby Feature */ -static inline void cec_msg_standby(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_STANDBY; -} - - -/* One Touch Record Feature */ -static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_RECORD_OFF; - msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; -} - -struct cec_op_arib_data { - __u16 transport_id; - __u16 service_id; - __u16 orig_network_id; -}; - -struct cec_op_atsc_data { - __u16 transport_id; - __u16 program_number; -}; - -struct cec_op_dvb_data { - __u16 transport_id; - __u16 service_id; - __u16 orig_network_id; -}; - -struct cec_op_channel_data { - __u8 channel_number_fmt; - __u16 major; - __u16 minor; -}; - -struct cec_op_digital_service_id { - __u8 service_id_method; - __u8 dig_bcast_system; - union { - struct cec_op_arib_data arib; - struct cec_op_atsc_data atsc; - struct cec_op_dvb_data dvb; - struct cec_op_channel_data channel; - }; -}; - -struct cec_op_record_src { - __u8 type; - union { - struct cec_op_digital_service_id digital; - struct { - __u8 ana_bcast_type; - __u16 ana_freq; - __u8 bcast_system; - } analog; - struct { - __u8 plug; - } ext_plug; - struct { - __u16 phys_addr; - } ext_phys_addr; - }; -}; - -static inline void cec_set_digital_service_id(__u8 *msg, - const struct cec_op_digital_service_id *digital) -{ - *msg++ = (digital->service_id_method << 7) | digital->dig_bcast_system; - if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { - *msg++ = (digital->channel.channel_number_fmt << 2) | - (digital->channel.major >> 8); - *msg++ = digital->channel.major & 0xff; - *msg++ = digital->channel.minor >> 8; - *msg++ = digital->channel.minor & 0xff; - *msg++ = 0; - *msg++ = 0; - return; - } - switch (digital->dig_bcast_system) { - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT: - case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T: - *msg++ = digital->atsc.transport_id >> 8; - *msg++ = digital->atsc.transport_id & 0xff; - *msg++ = digital->atsc.program_number >> 8; - *msg++ = digital->atsc.program_number & 0xff; - *msg++ = 0; - *msg++ = 0; - break; - default: - *msg++ = digital->dvb.transport_id >> 8; - *msg++ = digital->dvb.transport_id & 0xff; - *msg++ = digital->dvb.service_id >> 8; - *msg++ = digital->dvb.service_id & 0xff; - *msg++ = digital->dvb.orig_network_id >> 8; - *msg++ = digital->dvb.orig_network_id & 0xff; - break; - } -} - -static inline void cec_get_digital_service_id(const __u8 *msg, - struct cec_op_digital_service_id *digital) -{ - digital->service_id_method = msg[0] >> 7; - digital->dig_bcast_system = msg[0] & 0x7f; - if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { - digital->channel.channel_number_fmt = msg[1] >> 2; - digital->channel.major = ((msg[1] & 3) << 6) | msg[2]; - digital->channel.minor = (msg[3] << 8) | msg[4]; - return; - } - digital->dvb.transport_id = (msg[1] << 8) | msg[2]; - digital->dvb.service_id = (msg[3] << 8) | msg[4]; - digital->dvb.orig_network_id = (msg[5] << 8) | msg[6]; -} - -static inline void cec_msg_record_on_own(struct cec_msg *msg) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_OWN; -} - -static inline void cec_msg_record_on_digital(struct cec_msg *msg, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 10; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_DIGITAL; - cec_set_digital_service_id(msg->msg + 3, digital); -} - -static inline void cec_msg_record_on_analog(struct cec_msg *msg, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 7; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_ANALOG; - msg->msg[3] = ana_bcast_type; - msg->msg[4] = ana_freq >> 8; - msg->msg[5] = ana_freq & 0xff; - msg->msg[6] = bcast_system; -} - -static inline void cec_msg_record_on_plug(struct cec_msg *msg, - __u8 plug) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PLUG; - msg->msg[3] = plug; -} - -static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, - __u16 phys_addr) -{ - msg->len = 5; - msg->msg[1] = CEC_MSG_RECORD_ON; - msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PHYS_ADDR; - msg->msg[3] = phys_addr >> 8; - msg->msg[4] = phys_addr & 0xff; -} - -static inline void cec_msg_record_on(struct cec_msg *msg, - bool reply, - const struct cec_op_record_src *rec_src) -{ - switch (rec_src->type) { - case CEC_OP_RECORD_SRC_OWN: - cec_msg_record_on_own(msg); - break; - case CEC_OP_RECORD_SRC_DIGITAL: - cec_msg_record_on_digital(msg, &rec_src->digital); - break; - case CEC_OP_RECORD_SRC_ANALOG: - cec_msg_record_on_analog(msg, - rec_src->analog.ana_bcast_type, - rec_src->analog.ana_freq, - rec_src->analog.bcast_system); - break; - case CEC_OP_RECORD_SRC_EXT_PLUG: - cec_msg_record_on_plug(msg, rec_src->ext_plug.plug); - break; - case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: - cec_msg_record_on_phys_addr(msg, - rec_src->ext_phys_addr.phys_addr); - break; - } - msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; -} - -static inline void cec_ops_record_on(const struct cec_msg *msg, - struct cec_op_record_src *rec_src) -{ - rec_src->type = msg->msg[2]; - switch (rec_src->type) { - case CEC_OP_RECORD_SRC_OWN: - break; - case CEC_OP_RECORD_SRC_DIGITAL: - cec_get_digital_service_id(msg->msg + 3, &rec_src->digital); - break; - case CEC_OP_RECORD_SRC_ANALOG: - rec_src->analog.ana_bcast_type = msg->msg[3]; - rec_src->analog.ana_freq = - (msg->msg[4] << 8) | msg->msg[5]; - rec_src->analog.bcast_system = msg->msg[6]; - break; - case CEC_OP_RECORD_SRC_EXT_PLUG: - rec_src->ext_plug.plug = msg->msg[3]; - break; - case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: - rec_src->ext_phys_addr.phys_addr = - (msg->msg[3] << 8) | msg->msg[4]; - break; - } -} - -static inline void cec_msg_record_status(struct cec_msg *msg, __u8 rec_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_RECORD_STATUS; - msg->msg[2] = rec_status; -} - -static inline void cec_ops_record_status(const struct cec_msg *msg, - __u8 *rec_status) -{ - *rec_status = msg->msg[2]; -} - -static inline void cec_msg_record_tv_screen(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN; - msg->reply = reply ? CEC_MSG_RECORD_ON : 0; -} - - -/* Timer Programming Feature */ -static inline void cec_msg_timer_status(struct cec_msg *msg, - __u8 timer_overlap_warning, - __u8 media_info, - __u8 prog_info, - __u8 prog_error, - __u8 duration_hr, - __u8 duration_min) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_TIMER_STATUS; - msg->msg[2] = (timer_overlap_warning << 7) | - (media_info << 5) | - (prog_info ? 0x10 : 0) | - (prog_info ? prog_info : prog_error); - if (prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || - prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || - prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { - msg->len += 2; - msg->msg[3] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[4] = ((duration_min / 10) << 4) | (duration_min % 10); - } -} - -static inline void cec_ops_timer_status(const struct cec_msg *msg, - __u8 *timer_overlap_warning, - __u8 *media_info, - __u8 *prog_info, - __u8 *prog_error, - __u8 *duration_hr, - __u8 *duration_min) -{ - *timer_overlap_warning = msg->msg[2] >> 7; - *media_info = (msg->msg[2] >> 5) & 3; - if (msg->msg[2] & 0x10) { - *prog_info = msg->msg[2] & 0xf; - *prog_error = 0; - } else { - *prog_info = 0; - *prog_error = msg->msg[2] & 0xf; - } - if (*prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || - *prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || - *prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { - *duration_hr = (msg->msg[3] >> 4) * 10 + (msg->msg[3] & 0xf); - *duration_min = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - } else { - *duration_hr = *duration_min = 0; - } -} - -static inline void cec_msg_timer_cleared_status(struct cec_msg *msg, - __u8 timer_cleared_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_TIMER_CLEARED_STATUS; - msg->msg[2] = timer_cleared_status; -} - -static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg, - __u8 *timer_cleared_status) -{ - *timer_cleared_status = msg->msg[2]; -} - -static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_CLEAR_ANALOGUE_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ana_bcast_type; - msg->msg[10] = ana_freq >> 8; - msg->msg[11] = ana_freq & 0xff; - msg->msg[12] = bcast_system; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; -} - -static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ana_bcast_type = msg->msg[9]; - *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; - *bcast_system = msg->msg[12]; -} - -static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 16; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; - msg->msg[1] = CEC_MSG_CLEAR_DIGITAL_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - cec_set_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - struct cec_op_digital_service_id *digital) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - cec_get_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ext_src_spec, - __u8 plug, - __u16 phys_addr) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_CLEAR_EXT_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ext_src_spec; - msg->msg[10] = plug; - msg->msg[11] = phys_addr >> 8; - msg->msg[12] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; -} - -static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ext_src_spec, - __u8 *plug, - __u16 *phys_addr) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ext_src_spec = msg->msg[9]; - *plug = msg->msg[10]; - *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; -} - -static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_SET_ANALOGUE_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ana_bcast_type; - msg->msg[10] = ana_freq >> 8; - msg->msg[11] = ana_freq & 0xff; - msg->msg[12] = bcast_system; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; -} - -static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ana_bcast_type = msg->msg[9]; - *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; - *bcast_system = msg->msg[12]; -} - -static inline void cec_msg_set_digital_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 16; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; - msg->msg[1] = CEC_MSG_SET_DIGITAL_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - cec_set_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_ops_set_digital_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - struct cec_op_digital_service_id *digital) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - cec_get_digital_service_id(msg->msg + 9, digital); -} - -static inline void cec_msg_set_ext_timer(struct cec_msg *msg, - bool reply, - __u8 day, - __u8 month, - __u8 start_hr, - __u8 start_min, - __u8 duration_hr, - __u8 duration_min, - __u8 recording_seq, - __u8 ext_src_spec, - __u8 plug, - __u16 phys_addr) -{ - msg->len = 13; - msg->msg[1] = CEC_MSG_SET_EXT_TIMER; - msg->msg[2] = day; - msg->msg[3] = month; - /* Hours and minutes are in BCD format */ - msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); - msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); - msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); - msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); - msg->msg[8] = recording_seq; - msg->msg[9] = ext_src_spec; - msg->msg[10] = plug; - msg->msg[11] = phys_addr >> 8; - msg->msg[12] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; -} - -static inline void cec_ops_set_ext_timer(const struct cec_msg *msg, - __u8 *day, - __u8 *month, - __u8 *start_hr, - __u8 *start_min, - __u8 *duration_hr, - __u8 *duration_min, - __u8 *recording_seq, - __u8 *ext_src_spec, - __u8 *plug, - __u16 *phys_addr) -{ - *day = msg->msg[2]; - *month = msg->msg[3]; - /* Hours and minutes are in BCD format */ - *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); - *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); - *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); - *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); - *recording_seq = msg->msg[8]; - *ext_src_spec = msg->msg[9]; - *plug = msg->msg[10]; - *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; -} - -static inline void cec_msg_set_timer_program_title(struct cec_msg *msg, - const char *prog_title) -{ - unsigned int len = strlen(prog_title); - - if (len > 14) - len = 14; - msg->len = 2 + len; - msg->msg[1] = CEC_MSG_SET_TIMER_PROGRAM_TITLE; - memcpy(msg->msg + 2, prog_title, len); -} - -static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg, - char *prog_title) -{ - unsigned int len = msg->len > 2 ? msg->len - 2 : 0; - - if (len > 14) - len = 14; - memcpy(prog_title, msg->msg + 2, len); - prog_title[len] = '\0'; -} - -/* System Information Feature */ -static inline void cec_msg_cec_version(struct cec_msg *msg, __u8 cec_version) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_CEC_VERSION; - msg->msg[2] = cec_version; -} - -static inline void cec_ops_cec_version(const struct cec_msg *msg, - __u8 *cec_version) -{ - *cec_version = msg->msg[2]; -} - -static inline void cec_msg_get_cec_version(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GET_CEC_VERSION; - msg->reply = reply ? CEC_MSG_CEC_VERSION : 0; -} - -static inline void cec_msg_report_physical_addr(struct cec_msg *msg, - __u16 phys_addr, __u8 prim_devtype) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->msg[4] = prim_devtype; -} - -static inline void cec_ops_report_physical_addr(const struct cec_msg *msg, - __u16 *phys_addr, __u8 *prim_devtype) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *prim_devtype = msg->msg[4]; -} - -static inline void cec_msg_give_physical_addr(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR; - msg->reply = reply ? CEC_MSG_REPORT_PHYSICAL_ADDR : 0; -} - -static inline void cec_msg_set_menu_language(struct cec_msg *msg, - const char *language) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; - memcpy(msg->msg + 2, language, 3); -} - -static inline void cec_ops_set_menu_language(const struct cec_msg *msg, - char *language) -{ - memcpy(language, msg->msg + 2, 3); - language[3] = '\0'; -} - -static inline void cec_msg_get_menu_language(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE; - msg->reply = reply ? CEC_MSG_SET_MENU_LANGUAGE : 0; -} - -/* - * Assumes a single RC Profile byte and a single Device Features byte, - * i.e. no extended features are supported by this helper function. - * - * As of CEC 2.0 no extended features are defined, should those be added - * in the future, then this function needs to be adapted or a new function - * should be added. - */ -static inline void cec_msg_report_features(struct cec_msg *msg, - __u8 cec_version, __u8 all_device_types, - __u8 rc_profile, __u8 dev_features) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_FEATURES; - msg->msg[2] = cec_version; - msg->msg[3] = all_device_types; - msg->msg[4] = rc_profile; - msg->msg[5] = dev_features; -} - -static inline void cec_ops_report_features(const struct cec_msg *msg, - __u8 *cec_version, __u8 *all_device_types, - const __u8 **rc_profile, const __u8 **dev_features) -{ - const __u8 *p = &msg->msg[4]; - - *cec_version = msg->msg[2]; - *all_device_types = msg->msg[3]; - *rc_profile = p; - while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT)) - p++; - if (!(*p & CEC_OP_FEAT_EXT)) { - *dev_features = p + 1; - while (p < &msg->msg[15] && (*p & CEC_OP_FEAT_EXT)) - p++; - } - if (*p & CEC_OP_FEAT_EXT) - *rc_profile = *dev_features = NULL; -} - -static inline void cec_msg_give_features(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_FEATURES; - msg->reply = reply ? CEC_MSG_REPORT_FEATURES : 0; -} - -/* Deck Control Feature */ -static inline void cec_msg_deck_control(struct cec_msg *msg, - __u8 deck_control_mode) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_DECK_CONTROL; - msg->msg[2] = deck_control_mode; -} - -static inline void cec_ops_deck_control(const struct cec_msg *msg, - __u8 *deck_control_mode) -{ - *deck_control_mode = msg->msg[2]; -} - -static inline void cec_msg_deck_status(struct cec_msg *msg, - __u8 deck_info) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_DECK_STATUS; - msg->msg[2] = deck_info; -} - -static inline void cec_ops_deck_status(const struct cec_msg *msg, - __u8 *deck_info) -{ - *deck_info = msg->msg[2]; -} - -static inline void cec_msg_give_deck_status(struct cec_msg *msg, - bool reply, - __u8 status_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS; - msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; -} - -static inline void cec_ops_give_deck_status(const struct cec_msg *msg, - __u8 *status_req) -{ - *status_req = msg->msg[2]; -} - -static inline void cec_msg_play(struct cec_msg *msg, - __u8 play_mode) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_PLAY; - msg->msg[2] = play_mode; -} - -static inline void cec_ops_play(const struct cec_msg *msg, - __u8 *play_mode) -{ - *play_mode = msg->msg[2]; -} - - -/* Tuner Control Feature */ -struct cec_op_tuner_device_info { - __u8 rec_flag; - __u8 tuner_display_info; - bool is_analog; - union { - struct cec_op_digital_service_id digital; - struct { - __u8 ana_bcast_type; - __u16 ana_freq; - __u8 bcast_system; - } analog; - }; -}; - -static inline void cec_msg_tuner_device_status_analog(struct cec_msg *msg, - __u8 rec_flag, - __u8 tuner_display_info, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 7; - msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; - msg->msg[2] = (rec_flag << 7) | tuner_display_info; - msg->msg[3] = ana_bcast_type; - msg->msg[4] = ana_freq >> 8; - msg->msg[5] = ana_freq & 0xff; - msg->msg[6] = bcast_system; -} - -static inline void cec_msg_tuner_device_status_digital(struct cec_msg *msg, - __u8 rec_flag, __u8 tuner_display_info, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 10; - msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; - msg->msg[2] = (rec_flag << 7) | tuner_display_info; - cec_set_digital_service_id(msg->msg + 3, digital); -} - -static inline void cec_msg_tuner_device_status(struct cec_msg *msg, - const struct cec_op_tuner_device_info *tuner_dev_info) -{ - if (tuner_dev_info->is_analog) - cec_msg_tuner_device_status_analog(msg, - tuner_dev_info->rec_flag, - tuner_dev_info->tuner_display_info, - tuner_dev_info->analog.ana_bcast_type, - tuner_dev_info->analog.ana_freq, - tuner_dev_info->analog.bcast_system); - else - cec_msg_tuner_device_status_digital(msg, - tuner_dev_info->rec_flag, - tuner_dev_info->tuner_display_info, - &tuner_dev_info->digital); -} - -static inline void cec_ops_tuner_device_status(const struct cec_msg *msg, - struct cec_op_tuner_device_info *tuner_dev_info) -{ - tuner_dev_info->is_analog = msg->len < 10; - tuner_dev_info->rec_flag = msg->msg[2] >> 7; - tuner_dev_info->tuner_display_info = msg->msg[2] & 0x7f; - if (tuner_dev_info->is_analog) { - tuner_dev_info->analog.ana_bcast_type = msg->msg[3]; - tuner_dev_info->analog.ana_freq = (msg->msg[4] << 8) | msg->msg[5]; - tuner_dev_info->analog.bcast_system = msg->msg[6]; - return; - } - cec_get_digital_service_id(msg->msg + 3, &tuner_dev_info->digital); -} - -static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, - bool reply, - __u8 status_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS; - msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; -} - -static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg, - __u8 *status_req) -{ - *status_req = msg->msg[2]; -} - -static inline void cec_msg_select_analogue_service(struct cec_msg *msg, - __u8 ana_bcast_type, - __u16 ana_freq, - __u8 bcast_system) -{ - msg->len = 6; - msg->msg[1] = CEC_MSG_SELECT_ANALOGUE_SERVICE; - msg->msg[2] = ana_bcast_type; - msg->msg[3] = ana_freq >> 8; - msg->msg[4] = ana_freq & 0xff; - msg->msg[5] = bcast_system; -} - -static inline void cec_ops_select_analogue_service(const struct cec_msg *msg, - __u8 *ana_bcast_type, - __u16 *ana_freq, - __u8 *bcast_system) -{ - *ana_bcast_type = msg->msg[2]; - *ana_freq = (msg->msg[3] << 8) | msg->msg[4]; - *bcast_system = msg->msg[5]; -} - -static inline void cec_msg_select_digital_service(struct cec_msg *msg, - const struct cec_op_digital_service_id *digital) -{ - msg->len = 9; - msg->msg[1] = CEC_MSG_SELECT_DIGITAL_SERVICE; - cec_set_digital_service_id(msg->msg + 2, digital); -} - -static inline void cec_ops_select_digital_service(const struct cec_msg *msg, - struct cec_op_digital_service_id *digital) -{ - cec_get_digital_service_id(msg->msg + 2, digital); -} - -static inline void cec_msg_tuner_step_decrement(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TUNER_STEP_DECREMENT; -} - -static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TUNER_STEP_INCREMENT; -} - - -/* Vendor Specific Commands Feature */ -static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; - msg->msg[2] = vendor_id >> 16; - msg->msg[3] = (vendor_id >> 8) & 0xff; - msg->msg[4] = vendor_id & 0xff; -} - -static inline void cec_ops_device_vendor_id(const struct cec_msg *msg, - __u32 *vendor_id) -{ - *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; -} - -static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID; - msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; -} - -static inline void cec_msg_vendor_command(struct cec_msg *msg, - __u8 size, const __u8 *vendor_cmd) -{ - if (size > 14) - size = 14; - msg->len = 2 + size; - msg->msg[1] = CEC_MSG_VENDOR_COMMAND; - memcpy(msg->msg + 2, vendor_cmd, size); -} - -static inline void cec_ops_vendor_command(const struct cec_msg *msg, - __u8 *size, - const __u8 **vendor_cmd) -{ - *size = msg->len - 2; - - if (*size > 14) - *size = 14; - *vendor_cmd = msg->msg + 2; -} - -static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg, - __u32 vendor_id, __u8 size, - const __u8 *vendor_cmd) -{ - if (size > 11) - size = 11; - msg->len = 5 + size; - msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID; - msg->msg[2] = vendor_id >> 16; - msg->msg[3] = (vendor_id >> 8) & 0xff; - msg->msg[4] = vendor_id & 0xff; - memcpy(msg->msg + 5, vendor_cmd, size); -} - -static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg, - __u32 *vendor_id, __u8 *size, - const __u8 **vendor_cmd) -{ - *size = msg->len - 5; - - if (*size > 11) - *size = 11; - *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; - *vendor_cmd = msg->msg + 5; -} - -static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg, - __u8 size, - const __u8 *rc_code) -{ - if (size > 14) - size = 14; - msg->len = 2 + size; - msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN; - memcpy(msg->msg + 2, rc_code, size); -} - -static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg, - __u8 *size, - const __u8 **rc_code) -{ - *size = msg->len - 2; - - if (*size > 14) - *size = 14; - *rc_code = msg->msg + 2; -} - -static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_UP; -} - - -/* OSD Display Feature */ -static inline void cec_msg_set_osd_string(struct cec_msg *msg, - __u8 disp_ctl, - const char *osd) -{ - unsigned int len = strlen(osd); - - if (len > 13) - len = 13; - msg->len = 3 + len; - msg->msg[1] = CEC_MSG_SET_OSD_STRING; - msg->msg[2] = disp_ctl; - memcpy(msg->msg + 3, osd, len); -} - -static inline void cec_ops_set_osd_string(const struct cec_msg *msg, - __u8 *disp_ctl, - char *osd) -{ - unsigned int len = msg->len > 3 ? msg->len - 3 : 0; - - *disp_ctl = msg->msg[2]; - if (len > 13) - len = 13; - memcpy(osd, msg->msg + 3, len); - osd[len] = '\0'; -} - - -/* Device OSD Transfer Feature */ -static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name) -{ - unsigned int len = strlen(name); - - if (len > 14) - len = 14; - msg->len = 2 + len; - msg->msg[1] = CEC_MSG_SET_OSD_NAME; - memcpy(msg->msg + 2, name, len); -} - -static inline void cec_ops_set_osd_name(const struct cec_msg *msg, - char *name) -{ - unsigned int len = msg->len > 2 ? msg->len - 2 : 0; - - if (len > 14) - len = 14; - memcpy(name, msg->msg + 2, len); - name[len] = '\0'; -} - -static inline void cec_msg_give_osd_name(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_OSD_NAME; - msg->reply = reply ? CEC_MSG_SET_OSD_NAME : 0; -} - - -/* Device Menu Control Feature */ -static inline void cec_msg_menu_status(struct cec_msg *msg, - __u8 menu_state) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_MENU_STATUS; - msg->msg[2] = menu_state; -} - -static inline void cec_ops_menu_status(const struct cec_msg *msg, - __u8 *menu_state) -{ - *menu_state = msg->msg[2]; -} - -static inline void cec_msg_menu_request(struct cec_msg *msg, - bool reply, - __u8 menu_req) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_MENU_REQUEST; - msg->msg[2] = menu_req; - msg->reply = reply ? CEC_MSG_MENU_STATUS : 0; -} - -static inline void cec_ops_menu_request(const struct cec_msg *msg, - __u8 *menu_req) -{ - *menu_req = msg->msg[2]; -} - -struct cec_op_ui_command { - __u8 ui_cmd; - bool has_opt_arg; - union { - struct cec_op_channel_data channel_identifier; - __u8 ui_broadcast_type; - __u8 ui_sound_presentation_control; - __u8 play_mode; - __u8 ui_function_media; - __u8 ui_function_select_av_input; - __u8 ui_function_select_audio_input; - }; -}; - -static inline void cec_msg_user_control_pressed(struct cec_msg *msg, - const struct cec_op_ui_command *ui_cmd) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_USER_CONTROL_PRESSED; - msg->msg[2] = ui_cmd->ui_cmd; - if (!ui_cmd->has_opt_arg) - return; - switch (ui_cmd->ui_cmd) { - case 0x56: - case 0x57: - case 0x60: - case 0x68: - case 0x69: - case 0x6a: - /* The optional operand is one byte for all these ui commands */ - msg->len++; - msg->msg[3] = ui_cmd->play_mode; - break; - case 0x67: - msg->len += 4; - msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | - (ui_cmd->channel_identifier.major >> 8); - msg->msg[4] = ui_cmd->channel_identifier.major & 0xff; - msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; - msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; - break; - } -} - -static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, - struct cec_op_ui_command *ui_cmd) -{ - ui_cmd->ui_cmd = msg->msg[2]; - ui_cmd->has_opt_arg = false; - if (msg->len == 3) - return; - switch (ui_cmd->ui_cmd) { - case 0x56: - case 0x57: - case 0x60: - case 0x68: - case 0x69: - case 0x6a: - /* The optional operand is one byte for all these ui commands */ - ui_cmd->play_mode = msg->msg[3]; - ui_cmd->has_opt_arg = true; - break; - case 0x67: - if (msg->len < 7) - break; - ui_cmd->has_opt_arg = true; - ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2; - ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4]; - ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6]; - break; - } -} - -static inline void cec_msg_user_control_released(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_USER_CONTROL_RELEASED; -} - -/* Remote Control Passthrough Feature */ - -/* Power Status Feature */ -static inline void cec_msg_report_power_status(struct cec_msg *msg, - __u8 pwr_state) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_REPORT_POWER_STATUS; - msg->msg[2] = pwr_state; -} - -static inline void cec_ops_report_power_status(const struct cec_msg *msg, - __u8 *pwr_state) -{ - *pwr_state = msg->msg[2]; -} - -static inline void cec_msg_give_device_power_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS; - msg->reply = reply ? CEC_MSG_REPORT_POWER_STATUS : 0; -} - -/* General Protocol Messages */ -static inline void cec_msg_feature_abort(struct cec_msg *msg, - __u8 abort_msg, __u8 reason) -{ - msg->len = 4; - msg->msg[1] = CEC_MSG_FEATURE_ABORT; - msg->msg[2] = abort_msg; - msg->msg[3] = reason; -} - -static inline void cec_ops_feature_abort(const struct cec_msg *msg, - __u8 *abort_msg, __u8 *reason) -{ - *abort_msg = msg->msg[2]; - *reason = msg->msg[3]; -} - -/* This changes the current message into a feature abort message */ -static inline void cec_msg_reply_feature_abort(struct cec_msg *msg, __u8 reason) -{ - cec_msg_set_reply_to(msg, msg); - msg->len = 4; - msg->msg[2] = msg->msg[1]; - msg->msg[3] = reason; - msg->msg[1] = CEC_MSG_FEATURE_ABORT; -} - -static inline void cec_msg_abort(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_ABORT; -} - - -/* System Audio Control Feature */ -static inline void cec_msg_report_audio_status(struct cec_msg *msg, - __u8 aud_mute_status, - __u8 aud_vol_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_REPORT_AUDIO_STATUS; - msg->msg[2] = (aud_mute_status << 7) | (aud_vol_status & 0x7f); -} - -static inline void cec_ops_report_audio_status(const struct cec_msg *msg, - __u8 *aud_mute_status, - __u8 *aud_vol_status) -{ - *aud_mute_status = msg->msg[2] >> 7; - *aud_vol_status = msg->msg[2] & 0x7f; -} - -static inline void cec_msg_give_audio_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS; - msg->reply = reply ? CEC_MSG_REPORT_AUDIO_STATUS : 0; -} - -static inline void cec_msg_set_system_audio_mode(struct cec_msg *msg, - __u8 sys_aud_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SET_SYSTEM_AUDIO_MODE; - msg->msg[2] = sys_aud_status; -} - -static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg, - __u8 *sys_aud_status) -{ - *sys_aud_status = msg->msg[2]; -} - -static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg, - bool reply, - __u16 phys_addr) -{ - msg->len = phys_addr == 0xffff ? 2 : 4; - msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_SET_SYSTEM_AUDIO_MODE : 0; - -} - -static inline void cec_ops_system_audio_mode_request(const struct cec_msg *msg, - __u16 *phys_addr) -{ - if (msg->len < 4) - *phys_addr = 0xffff; - else - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_system_audio_mode_status(struct cec_msg *msg, - __u8 sys_aud_status) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_STATUS; - msg->msg[2] = sys_aud_status; -} - -static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg, - __u8 *sys_aud_status) -{ - *sys_aud_status = msg->msg[2]; -} - -static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS; - msg->reply = reply ? CEC_MSG_SYSTEM_AUDIO_MODE_STATUS : 0; -} - -static inline void cec_msg_report_short_audio_descriptor(struct cec_msg *msg, - __u8 num_descriptors, - const __u32 *descriptors) -{ - unsigned int i; - - if (num_descriptors > 4) - num_descriptors = 4; - msg->len = 2 + num_descriptors * 3; - msg->msg[1] = CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR; - for (i = 0; i < num_descriptors; i++) { - msg->msg[2 + i * 3] = (descriptors[i] >> 16) & 0xff; - msg->msg[3 + i * 3] = (descriptors[i] >> 8) & 0xff; - msg->msg[4 + i * 3] = descriptors[i] & 0xff; - } -} - -static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *msg, - __u8 *num_descriptors, - __u32 *descriptors) -{ - unsigned int i; - - *num_descriptors = (msg->len - 2) / 3; - if (*num_descriptors > 4) - *num_descriptors = 4; - for (i = 0; i < *num_descriptors; i++) - descriptors[i] = (msg->msg[2 + i * 3] << 16) | - (msg->msg[3 + i * 3] << 8) | - msg->msg[4 + i * 3]; -} - -static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, - bool reply, - __u8 num_descriptors, - const __u8 *audio_format_id, - const __u8 *audio_format_code) -{ - unsigned int i; - - if (num_descriptors > 4) - num_descriptors = 4; - msg->len = 2 + num_descriptors; - msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR; - msg->reply = reply ? CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR : 0; - for (i = 0; i < num_descriptors; i++) - msg->msg[2 + i] = (audio_format_id[i] << 6) | - (audio_format_code[i] & 0x3f); -} - -static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg *msg, - __u8 *num_descriptors, - __u8 *audio_format_id, - __u8 *audio_format_code) -{ - unsigned int i; - - *num_descriptors = msg->len - 2; - if (*num_descriptors > 4) - *num_descriptors = 4; - for (i = 0; i < *num_descriptors; i++) { - audio_format_id[i] = msg->msg[2 + i] >> 6; - audio_format_code[i] = msg->msg[2 + i] & 0x3f; - } -} - - -/* Audio Rate Control Feature */ -static inline void cec_msg_set_audio_rate(struct cec_msg *msg, - __u8 audio_rate) -{ - msg->len = 3; - msg->msg[1] = CEC_MSG_SET_AUDIO_RATE; - msg->msg[2] = audio_rate; -} - -static inline void cec_ops_set_audio_rate(const struct cec_msg *msg, - __u8 *audio_rate) -{ - *audio_rate = msg->msg[2]; -} - - -/* Audio Return Channel Control Feature */ -static inline void cec_msg_report_arc_initiated(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REPORT_ARC_INITIATED; -} - -static inline void cec_msg_initiate_arc(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_INITIATE_ARC; - msg->reply = reply ? CEC_MSG_REPORT_ARC_INITIATED : 0; -} - -static inline void cec_msg_request_arc_initiation(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION; - msg->reply = reply ? CEC_MSG_INITIATE_ARC : 0; -} - -static inline void cec_msg_report_arc_terminated(struct cec_msg *msg) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REPORT_ARC_TERMINATED; -} - -static inline void cec_msg_terminate_arc(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_TERMINATE_ARC; - msg->reply = reply ? CEC_MSG_REPORT_ARC_TERMINATED : 0; -} - -static inline void cec_msg_request_arc_termination(struct cec_msg *msg, - bool reply) -{ - msg->len = 2; - msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION; - msg->reply = reply ? CEC_MSG_TERMINATE_ARC : 0; -} - - -/* Dynamic Audio Lipsync Feature */ -/* Only for CEC 2.0 and up */ -static inline void cec_msg_report_current_latency(struct cec_msg *msg, - __u16 phys_addr, - __u8 video_latency, - __u8 low_latency_mode, - __u8 audio_out_compensated, - __u8 audio_out_delay) -{ - msg->len = 7; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->msg[4] = video_latency; - msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; - msg->msg[6] = audio_out_delay; -} - -static inline void cec_ops_report_current_latency(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *video_latency, - __u8 *low_latency_mode, - __u8 *audio_out_compensated, - __u8 *audio_out_delay) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *video_latency = msg->msg[4]; - *low_latency_mode = (msg->msg[5] >> 2) & 1; - *audio_out_compensated = msg->msg[5] & 3; - *audio_out_delay = msg->msg[6]; -} - -static inline void cec_msg_request_current_latency(struct cec_msg *msg, - bool reply, - __u16 phys_addr) -{ - msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; - msg->msg[2] = phys_addr >> 8; - msg->msg[3] = phys_addr & 0xff; - msg->reply = reply ? CEC_MSG_REPORT_CURRENT_LATENCY : 0; -} - -static inline void cec_ops_request_current_latency(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - - -/* Capability Discovery and Control Feature */ -static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2) -{ - msg->len = 9; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; -} - -static inline void cec_ops_cdc_hec_inquire_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; -} - -static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, - __u16 target_phys_addr, - __u8 hec_func_state, - __u8 host_func_state, - __u8 enc_func_state, - __u8 cdc_errcode, - __u8 has_field, - __u16 hec_field) -{ - msg->len = has_field ? 10 : 8; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; - msg->msg[5] = target_phys_addr >> 8; - msg->msg[6] = target_phys_addr & 0xff; - msg->msg[7] = (hec_func_state << 6) | - (host_func_state << 4) | - (enc_func_state << 2) | - cdc_errcode; - if (has_field) { - msg->msg[8] = hec_field >> 8; - msg->msg[9] = hec_field & 0xff; - } -} - -static inline void cec_ops_cdc_hec_report_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *target_phys_addr, - __u8 *hec_func_state, - __u8 *host_func_state, - __u8 *enc_func_state, - __u8 *cdc_errcode, - __u8 *has_field, - __u16 *hec_field) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *target_phys_addr = (msg->msg[5] << 8) | msg->msg[6]; - *hec_func_state = msg->msg[7] >> 6; - *host_func_state = (msg->msg[7] >> 4) & 3; - *enc_func_state = (msg->msg[7] >> 4) & 3; - *cdc_errcode = msg->msg[7] & 3; - *has_field = msg->len >= 10; - *hec_field = *has_field ? ((msg->msg[8] << 8) | msg->msg[9]) : 0; -} - -static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2, - __u8 hec_set_state, - __u16 phys_addr3, - __u16 phys_addr4, - __u16 phys_addr5) -{ - msg->len = 10; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; - msg->msg[9] = hec_set_state; - if (phys_addr3 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr3 >> 8; - msg->msg[msg->len++] = phys_addr3 & 0xff; - if (phys_addr4 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr4 >> 8; - msg->msg[msg->len++] = phys_addr4 & 0xff; - if (phys_addr5 != CEC_PHYS_ADDR_INVALID) { - msg->msg[msg->len++] = phys_addr5 >> 8; - msg->msg[msg->len++] = phys_addr5 & 0xff; - } - } - } -} - -static inline void cec_ops_cdc_hec_set_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2, - __u8 *hec_set_state, - __u16 *phys_addr3, - __u16 *phys_addr4, - __u16 *phys_addr5) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; - *hec_set_state = msg->msg[9]; - *phys_addr3 = *phys_addr4 = *phys_addr5 = CEC_PHYS_ADDR_INVALID; - if (msg->len >= 12) - *phys_addr3 = (msg->msg[10] << 8) | msg->msg[11]; - if (msg->len >= 14) - *phys_addr4 = (msg->msg[12] << 8) | msg->msg[13]; - if (msg->len >= 16) - *phys_addr5 = (msg->msg[14] << 8) | msg->msg[15]; -} - -static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, - __u16 phys_addr1, - __u8 hec_set_state) -{ - msg->len = 8; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = hec_set_state; -} - -static inline void cec_ops_cdc_hec_set_state_adjacent(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u8 *hec_set_state) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *hec_set_state = msg->msg[7]; -} - -static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, - __u16 phys_addr1, - __u16 phys_addr2, - __u16 phys_addr3) -{ - msg->len = 11; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; - msg->msg[5] = phys_addr1 >> 8; - msg->msg[6] = phys_addr1 & 0xff; - msg->msg[7] = phys_addr2 >> 8; - msg->msg[8] = phys_addr2 & 0xff; - msg->msg[9] = phys_addr3 >> 8; - msg->msg[10] = phys_addr3 & 0xff; -} - -static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *msg, - __u16 *phys_addr, - __u16 *phys_addr1, - __u16 *phys_addr2, - __u16 *phys_addr3) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; - *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; - *phys_addr3 = (msg->msg[9] << 8) | msg->msg[10]; -} - -static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; -} - -static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) -{ - msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; -} - -static inline void cec_ops_cdc_hec_discover(const struct cec_msg *msg, - __u16 *phys_addr) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; -} - -static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, - __u8 input_port, - __u8 hpd_state) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; - msg->msg[5] = (input_port << 4) | hpd_state; -} - -static inline void cec_ops_cdc_hpd_set_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *input_port, - __u8 *hpd_state) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *input_port = msg->msg[5] >> 4; - *hpd_state = msg->msg[5] & 0xf; -} - -static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, - __u8 hpd_state, - __u8 hpd_error) -{ - msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ - msg->msg[1] = CEC_MSG_CDC_MESSAGE; - /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ - msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; - msg->msg[5] = (hpd_state << 4) | hpd_error; -} - -static inline void cec_ops_cdc_hpd_report_state(const struct cec_msg *msg, - __u16 *phys_addr, - __u8 *hpd_state, - __u8 *hpd_error) -{ - *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; - *hpd_state = msg->msg[5] >> 4; - *hpd_error = msg->msg[5] & 0xf; -} - -#endif diff --git a/include/linux/cec.h b/include/linux/cec.h deleted file mode 100644 index 9c87711c0e1c..000000000000 --- a/include/linux/cec.h +++ /dev/null @@ -1,1071 +0,0 @@ -/* - * cec - HDMI Consumer Electronics Control public header - * - * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. - * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -/* - * Note: this framework is still in staging and it is likely the API - * will change before it goes out of staging. - * - * Once it is moved out of staging this header will move to uapi. - */ -#ifndef _CEC_UAPI_H -#define _CEC_UAPI_H - -#include - -#define CEC_MAX_MSG_SIZE 16 - -/** - * struct cec_msg - CEC message structure. - * @tx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the - * driver when the message transmission has finished. - * @rx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the - * driver when the message was received. - * @len: Length in bytes of the message. - * @timeout: The timeout (in ms) that is used to timeout CEC_RECEIVE. - * Set to 0 if you want to wait forever. This timeout can also be - * used with CEC_TRANSMIT as the timeout for waiting for a reply. - * If 0, then it will use a 1 second timeout instead of waiting - * forever as is done with CEC_RECEIVE. - * @sequence: The framework assigns a sequence number to messages that are - * sent. This can be used to track replies to previously sent - * messages. - * @flags: Set to 0. - * @msg: The message payload. - * @reply: This field is ignored with CEC_RECEIVE and is only used by - * CEC_TRANSMIT. If non-zero, then wait for a reply with this - * opcode. Set to CEC_MSG_FEATURE_ABORT if you want to wait for - * a possible ABORT reply. If there was an error when sending the - * msg or FeatureAbort was returned, then reply is set to 0. - * If reply is non-zero upon return, then len/msg are set to - * the received message. - * If reply is zero upon return and status has the - * CEC_TX_STATUS_FEATURE_ABORT bit set, then len/msg are set to - * the received feature abort message. - * If reply is zero upon return and status has the - * CEC_TX_STATUS_MAX_RETRIES bit set, then no reply was seen at - * all. If reply is non-zero for CEC_TRANSMIT and the message is a - * broadcast, then -EINVAL is returned. - * if reply is non-zero, then timeout is set to 1000 (the required - * maximum response time). - * @rx_status: The message receive status bits. Set by the driver. - * @tx_status: The message transmit status bits. Set by the driver. - * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver. - * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver. - * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the - * driver. - * @tx_error_cnt: The number of 'Error' events. Set by the driver. - */ -struct cec_msg { - __u64 tx_ts; - __u64 rx_ts; - __u32 len; - __u32 timeout; - __u32 sequence; - __u32 flags; - __u8 msg[CEC_MAX_MSG_SIZE]; - __u8 reply; - __u8 rx_status; - __u8 tx_status; - __u8 tx_arb_lost_cnt; - __u8 tx_nack_cnt; - __u8 tx_low_drive_cnt; - __u8 tx_error_cnt; -}; - -/** - * cec_msg_initiator - return the initiator's logical address. - * @msg: the message structure - */ -static inline __u8 cec_msg_initiator(const struct cec_msg *msg) -{ - return msg->msg[0] >> 4; -} - -/** - * cec_msg_destination - return the destination's logical address. - * @msg: the message structure - */ -static inline __u8 cec_msg_destination(const struct cec_msg *msg) -{ - return msg->msg[0] & 0xf; -} - -/** - * cec_msg_opcode - return the opcode of the message, -1 for poll - * @msg: the message structure - */ -static inline int cec_msg_opcode(const struct cec_msg *msg) -{ - return msg->len > 1 ? msg->msg[1] : -1; -} - -/** - * cec_msg_is_broadcast - return true if this is a broadcast message. - * @msg: the message structure - */ -static inline bool cec_msg_is_broadcast(const struct cec_msg *msg) -{ - return (msg->msg[0] & 0xf) == 0xf; -} - -/** - * cec_msg_init - initialize the message structure. - * @msg: the message structure - * @initiator: the logical address of the initiator - * @destination:the logical address of the destination (0xf for broadcast) - * - * The whole structure is zeroed, the len field is set to 1 (i.e. a poll - * message) and the initiator and destination are filled in. - */ -static inline void cec_msg_init(struct cec_msg *msg, - __u8 initiator, __u8 destination) -{ - memset(msg, 0, sizeof(*msg)); - msg->msg[0] = (initiator << 4) | destination; - msg->len = 1; -} - -/** - * cec_msg_set_reply_to - fill in destination/initiator in a reply message. - * @msg: the message structure for the reply - * @orig: the original message structure - * - * Set the msg destination to the orig initiator and the msg initiator to the - * orig destination. Note that msg and orig may be the same pointer, in which - * case the change is done in place. - */ -static inline void cec_msg_set_reply_to(struct cec_msg *msg, - struct cec_msg *orig) -{ - /* The destination becomes the initiator and vice versa */ - msg->msg[0] = (cec_msg_destination(orig) << 4) | - cec_msg_initiator(orig); - msg->reply = msg->timeout = 0; -} - -/* cec_msg flags field */ -#define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) - -/* cec_msg tx/rx_status field */ -#define CEC_TX_STATUS_OK (1 << 0) -#define CEC_TX_STATUS_ARB_LOST (1 << 1) -#define CEC_TX_STATUS_NACK (1 << 2) -#define CEC_TX_STATUS_LOW_DRIVE (1 << 3) -#define CEC_TX_STATUS_ERROR (1 << 4) -#define CEC_TX_STATUS_MAX_RETRIES (1 << 5) - -#define CEC_RX_STATUS_OK (1 << 0) -#define CEC_RX_STATUS_TIMEOUT (1 << 1) -#define CEC_RX_STATUS_FEATURE_ABORT (1 << 2) - -static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) -{ - if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK)) - return false; - if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK)) - return false; - if (!msg->tx_status && !msg->rx_status) - return false; - return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT); -} - -#define CEC_LOG_ADDR_INVALID 0xff -#define CEC_PHYS_ADDR_INVALID 0xffff - -/* - * The maximum number of logical addresses one device can be assigned to. - * The CEC 2.0 spec allows for only 2 logical addresses at the moment. The - * Analog Devices CEC hardware supports 3. So let's go wild and go for 4. - */ -#define CEC_MAX_LOG_ADDRS 4 - -/* The logical addresses defined by CEC 2.0 */ -#define CEC_LOG_ADDR_TV 0 -#define CEC_LOG_ADDR_RECORD_1 1 -#define CEC_LOG_ADDR_RECORD_2 2 -#define CEC_LOG_ADDR_TUNER_1 3 -#define CEC_LOG_ADDR_PLAYBACK_1 4 -#define CEC_LOG_ADDR_AUDIOSYSTEM 5 -#define CEC_LOG_ADDR_TUNER_2 6 -#define CEC_LOG_ADDR_TUNER_3 7 -#define CEC_LOG_ADDR_PLAYBACK_2 8 -#define CEC_LOG_ADDR_RECORD_3 9 -#define CEC_LOG_ADDR_TUNER_4 10 -#define CEC_LOG_ADDR_PLAYBACK_3 11 -#define CEC_LOG_ADDR_BACKUP_1 12 -#define CEC_LOG_ADDR_BACKUP_2 13 -#define CEC_LOG_ADDR_SPECIFIC 14 -#define CEC_LOG_ADDR_UNREGISTERED 15 /* as initiator address */ -#define CEC_LOG_ADDR_BROADCAST 15 /* ad destination address */ - -/* The logical address types that the CEC device wants to claim */ -#define CEC_LOG_ADDR_TYPE_TV 0 -#define CEC_LOG_ADDR_TYPE_RECORD 1 -#define CEC_LOG_ADDR_TYPE_TUNER 2 -#define CEC_LOG_ADDR_TYPE_PLAYBACK 3 -#define CEC_LOG_ADDR_TYPE_AUDIOSYSTEM 4 -#define CEC_LOG_ADDR_TYPE_SPECIFIC 5 -#define CEC_LOG_ADDR_TYPE_UNREGISTERED 6 -/* - * Switches should use UNREGISTERED. - * Processors should use SPECIFIC. - */ - -#define CEC_LOG_ADDR_MASK_TV (1 << CEC_LOG_ADDR_TV) -#define CEC_LOG_ADDR_MASK_RECORD ((1 << CEC_LOG_ADDR_RECORD_1) | \ - (1 << CEC_LOG_ADDR_RECORD_2) | \ - (1 << CEC_LOG_ADDR_RECORD_3)) -#define CEC_LOG_ADDR_MASK_TUNER ((1 << CEC_LOG_ADDR_TUNER_1) | \ - (1 << CEC_LOG_ADDR_TUNER_2) | \ - (1 << CEC_LOG_ADDR_TUNER_3) | \ - (1 << CEC_LOG_ADDR_TUNER_4)) -#define CEC_LOG_ADDR_MASK_PLAYBACK ((1 << CEC_LOG_ADDR_PLAYBACK_1) | \ - (1 << CEC_LOG_ADDR_PLAYBACK_2) | \ - (1 << CEC_LOG_ADDR_PLAYBACK_3)) -#define CEC_LOG_ADDR_MASK_AUDIOSYSTEM (1 << CEC_LOG_ADDR_AUDIOSYSTEM) -#define CEC_LOG_ADDR_MASK_BACKUP ((1 << CEC_LOG_ADDR_BACKUP_1) | \ - (1 << CEC_LOG_ADDR_BACKUP_2)) -#define CEC_LOG_ADDR_MASK_SPECIFIC (1 << CEC_LOG_ADDR_SPECIFIC) -#define CEC_LOG_ADDR_MASK_UNREGISTERED (1 << CEC_LOG_ADDR_UNREGISTERED) - -static inline bool cec_has_tv(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_TV; -} - -static inline bool cec_has_record(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD; -} - -static inline bool cec_has_tuner(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER; -} - -static inline bool cec_has_playback(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK; -} - -static inline bool cec_has_audiosystem(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM; -} - -static inline bool cec_has_backup(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP; -} - -static inline bool cec_has_specific(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC; -} - -static inline bool cec_is_unregistered(__u16 log_addr_mask) -{ - return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED; -} - -static inline bool cec_is_unconfigured(__u16 log_addr_mask) -{ - return log_addr_mask == 0; -} - -/* - * Use this if there is no vendor ID (CEC_G_VENDOR_ID) or if the vendor ID - * should be disabled (CEC_S_VENDOR_ID) - */ -#define CEC_VENDOR_ID_NONE 0xffffffff - -/* The message handling modes */ -/* Modes for initiator */ -#define CEC_MODE_NO_INITIATOR (0x0 << 0) -#define CEC_MODE_INITIATOR (0x1 << 0) -#define CEC_MODE_EXCL_INITIATOR (0x2 << 0) -#define CEC_MODE_INITIATOR_MSK 0x0f - -/* Modes for follower */ -#define CEC_MODE_NO_FOLLOWER (0x0 << 4) -#define CEC_MODE_FOLLOWER (0x1 << 4) -#define CEC_MODE_EXCL_FOLLOWER (0x2 << 4) -#define CEC_MODE_EXCL_FOLLOWER_PASSTHRU (0x3 << 4) -#define CEC_MODE_MONITOR (0xe << 4) -#define CEC_MODE_MONITOR_ALL (0xf << 4) -#define CEC_MODE_FOLLOWER_MSK 0xf0 - -/* Userspace has to configure the physical address */ -#define CEC_CAP_PHYS_ADDR (1 << 0) -/* Userspace has to configure the logical addresses */ -#define CEC_CAP_LOG_ADDRS (1 << 1) -/* Userspace can transmit messages (and thus become follower as well) */ -#define CEC_CAP_TRANSMIT (1 << 2) -/* - * Passthrough all messages instead of processing them. - */ -#define CEC_CAP_PASSTHROUGH (1 << 3) -/* Supports remote control */ -#define CEC_CAP_RC (1 << 4) -/* Hardware can monitor all messages, not just directed and broadcast. */ -#define CEC_CAP_MONITOR_ALL (1 << 5) - -/** - * struct cec_caps - CEC capabilities structure. - * @driver: name of the CEC device driver. - * @name: name of the CEC device. @driver + @name must be unique. - * @available_log_addrs: number of available logical addresses. - * @capabilities: capabilities of the CEC adapter. - * @version: version of the CEC adapter framework. - */ -struct cec_caps { - char driver[32]; - char name[32]; - __u32 available_log_addrs; - __u32 capabilities; - __u32 version; -}; - -/** - * struct cec_log_addrs - CEC logical addresses structure. - * @log_addr: the claimed logical addresses. Set by the driver. - * @log_addr_mask: current logical address mask. Set by the driver. - * @cec_version: the CEC version that the adapter should implement. Set by the - * caller. - * @num_log_addrs: how many logical addresses should be claimed. Set by the - * caller. - * @vendor_id: the vendor ID of the device. Set by the caller. - * @flags: flags. - * @osd_name: the OSD name of the device. Set by the caller. - * @primary_device_type: the primary device type for each logical address. - * Set by the caller. - * @log_addr_type: the logical address types. Set by the caller. - * @all_device_types: CEC 2.0: all device types represented by the logical - * address. Set by the caller. - * @features: CEC 2.0: The logical address features. Set by the caller. - */ -struct cec_log_addrs { - __u8 log_addr[CEC_MAX_LOG_ADDRS]; - __u16 log_addr_mask; - __u8 cec_version; - __u8 num_log_addrs; - __u32 vendor_id; - __u32 flags; - char osd_name[15]; - __u8 primary_device_type[CEC_MAX_LOG_ADDRS]; - __u8 log_addr_type[CEC_MAX_LOG_ADDRS]; - - /* CEC 2.0 */ - __u8 all_device_types[CEC_MAX_LOG_ADDRS]; - __u8 features[CEC_MAX_LOG_ADDRS][12]; -}; - -/* Allow a fallback to unregistered */ -#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) -/* Passthrough RC messages to the input subsystem */ -#define CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU (1 << 1) -/* CDC-Only device: supports only CDC messages */ -#define CEC_LOG_ADDRS_FL_CDC_ONLY (1 << 2) - -/* Events */ - -/* Event that occurs when the adapter state changes */ -#define CEC_EVENT_STATE_CHANGE 1 -/* - * This event is sent when messages are lost because the application - * didn't empty the message queue in time - */ -#define CEC_EVENT_LOST_MSGS 2 - -#define CEC_EVENT_FL_INITIAL_STATE (1 << 0) - -/** - * struct cec_event_state_change - used when the CEC adapter changes state. - * @phys_addr: the current physical address - * @log_addr_mask: the current logical address mask - */ -struct cec_event_state_change { - __u16 phys_addr; - __u16 log_addr_mask; -}; - -/** - * struct cec_event_lost_msgs - tells you how many messages were lost due. - * @lost_msgs: how many messages were lost. - */ -struct cec_event_lost_msgs { - __u32 lost_msgs; -}; - -/** - * struct cec_event - CEC event structure - * @ts: the timestamp of when the event was sent. - * @event: the event. - * array. - * @state_change: the event payload for CEC_EVENT_STATE_CHANGE. - * @lost_msgs: the event payload for CEC_EVENT_LOST_MSGS. - * @raw: array to pad the union. - */ -struct cec_event { - __u64 ts; - __u32 event; - __u32 flags; - union { - struct cec_event_state_change state_change; - struct cec_event_lost_msgs lost_msgs; - __u32 raw[16]; - }; -}; - -/* ioctls */ - -/* Adapter capabilities */ -#define CEC_ADAP_G_CAPS _IOWR('a', 0, struct cec_caps) - -/* - * phys_addr is either 0 (if this is the CEC root device) - * or a valid physical address obtained from the sink's EDID - * as read by this CEC device (if this is a source device) - * or a physical address obtained and modified from a sink - * EDID and used for a sink CEC device. - * If nothing is connected, then phys_addr is 0xffff. - * See HDMI 1.4b, section 8.7 (Physical Address). - * - * The CEC_ADAP_S_PHYS_ADDR ioctl may not be available if that is handled - * internally. - */ -#define CEC_ADAP_G_PHYS_ADDR _IOR('a', 1, __u16) -#define CEC_ADAP_S_PHYS_ADDR _IOW('a', 2, __u16) - -/* - * Configure the CEC adapter. It sets the device type and which - * logical types it will try to claim. It will return which - * logical addresses it could actually claim. - * An error is returned if the adapter is disabled or if there - * is no physical address assigned. - */ - -#define CEC_ADAP_G_LOG_ADDRS _IOR('a', 3, struct cec_log_addrs) -#define CEC_ADAP_S_LOG_ADDRS _IOWR('a', 4, struct cec_log_addrs) - -/* Transmit/receive a CEC command */ -#define CEC_TRANSMIT _IOWR('a', 5, struct cec_msg) -#define CEC_RECEIVE _IOWR('a', 6, struct cec_msg) - -/* Dequeue CEC events */ -#define CEC_DQEVENT _IOWR('a', 7, struct cec_event) - -/* - * Get and set the message handling mode for this filehandle. - */ -#define CEC_G_MODE _IOR('a', 8, __u32) -#define CEC_S_MODE _IOW('a', 9, __u32) - -/* - * The remainder of this header defines all CEC messages and operands. - * The format matters since it the cec-ctl utility parses it to generate - * code for implementing all these messages. - * - * Comments ending with 'Feature' group messages for each feature. - * If messages are part of multiple features, then the "Has also" - * comment is used to list the previously defined messages that are - * supported by the feature. - * - * Before operands are defined a comment is added that gives the - * name of the operand and in brackets the variable name of the - * corresponding argument in the cec-funcs.h function. - */ - -/* Messages */ - -/* One Touch Play Feature */ -#define CEC_MSG_ACTIVE_SOURCE 0x82 -#define CEC_MSG_IMAGE_VIEW_ON 0x04 -#define CEC_MSG_TEXT_VIEW_ON 0x0d - - -/* Routing Control Feature */ - -/* - * Has also: - * CEC_MSG_ACTIVE_SOURCE - */ - -#define CEC_MSG_INACTIVE_SOURCE 0x9d -#define CEC_MSG_REQUEST_ACTIVE_SOURCE 0x85 -#define CEC_MSG_ROUTING_CHANGE 0x80 -#define CEC_MSG_ROUTING_INFORMATION 0x81 -#define CEC_MSG_SET_STREAM_PATH 0x86 - - -/* Standby Feature */ -#define CEC_MSG_STANDBY 0x36 - - -/* One Touch Record Feature */ -#define CEC_MSG_RECORD_OFF 0x0b -#define CEC_MSG_RECORD_ON 0x09 -/* Record Source Type Operand (rec_src_type) */ -#define CEC_OP_RECORD_SRC_OWN 1 -#define CEC_OP_RECORD_SRC_DIGITAL 2 -#define CEC_OP_RECORD_SRC_ANALOG 3 -#define CEC_OP_RECORD_SRC_EXT_PLUG 4 -#define CEC_OP_RECORD_SRC_EXT_PHYS_ADDR 5 -/* Service Identification Method Operand (service_id_method) */ -#define CEC_OP_SERVICE_ID_METHOD_BY_DIG_ID 0 -#define CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL 1 -/* Digital Service Broadcast System Operand (dig_bcast_system) */ -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_GEN 0x00 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN 0x01 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_GEN 0x02 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_BS 0x08 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_CS 0x09 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_T 0x0a -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE 0x10 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT 0x11 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T 0x12 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_C 0x18 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S 0x19 -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S2 0x1a -#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_T 0x1b -/* Analogue Broadcast Type Operand (ana_bcast_type) */ -#define CEC_OP_ANA_BCAST_TYPE_CABLE 0 -#define CEC_OP_ANA_BCAST_TYPE_SATELLITE 1 -#define CEC_OP_ANA_BCAST_TYPE_TERRESTRIAL 2 -/* Broadcast System Operand (bcast_system) */ -#define CEC_OP_BCAST_SYSTEM_PAL_BG 0x00 -#define CEC_OP_BCAST_SYSTEM_SECAM_LQ 0x01 /* SECAM L' */ -#define CEC_OP_BCAST_SYSTEM_PAL_M 0x02 -#define CEC_OP_BCAST_SYSTEM_NTSC_M 0x03 -#define CEC_OP_BCAST_SYSTEM_PAL_I 0x04 -#define CEC_OP_BCAST_SYSTEM_SECAM_DK 0x05 -#define CEC_OP_BCAST_SYSTEM_SECAM_BG 0x06 -#define CEC_OP_BCAST_SYSTEM_SECAM_L 0x07 -#define CEC_OP_BCAST_SYSTEM_PAL_DK 0x08 -#define CEC_OP_BCAST_SYSTEM_OTHER 0x1f -/* Channel Number Format Operand (channel_number_fmt) */ -#define CEC_OP_CHANNEL_NUMBER_FMT_1_PART 0x01 -#define CEC_OP_CHANNEL_NUMBER_FMT_2_PART 0x02 - -#define CEC_MSG_RECORD_STATUS 0x0a -/* Record Status Operand (rec_status) */ -#define CEC_OP_RECORD_STATUS_CUR_SRC 0x01 -#define CEC_OP_RECORD_STATUS_DIG_SERVICE 0x02 -#define CEC_OP_RECORD_STATUS_ANA_SERVICE 0x03 -#define CEC_OP_RECORD_STATUS_EXT_INPUT 0x04 -#define CEC_OP_RECORD_STATUS_NO_DIG_SERVICE 0x05 -#define CEC_OP_RECORD_STATUS_NO_ANA_SERVICE 0x06 -#define CEC_OP_RECORD_STATUS_NO_SERVICE 0x07 -#define CEC_OP_RECORD_STATUS_INVALID_EXT_PLUG 0x09 -#define CEC_OP_RECORD_STATUS_INVALID_EXT_PHYS_ADDR 0x0a -#define CEC_OP_RECORD_STATUS_UNSUP_CA 0x0b -#define CEC_OP_RECORD_STATUS_NO_CA_ENTITLEMENTS 0x0c -#define CEC_OP_RECORD_STATUS_CANT_COPY_SRC 0x0d -#define CEC_OP_RECORD_STATUS_NO_MORE_COPIES 0x0e -#define CEC_OP_RECORD_STATUS_NO_MEDIA 0x10 -#define CEC_OP_RECORD_STATUS_PLAYING 0x11 -#define CEC_OP_RECORD_STATUS_ALREADY_RECORDING 0x12 -#define CEC_OP_RECORD_STATUS_MEDIA_PROT 0x13 -#define CEC_OP_RECORD_STATUS_NO_SIGNAL 0x14 -#define CEC_OP_RECORD_STATUS_MEDIA_PROBLEM 0x15 -#define CEC_OP_RECORD_STATUS_NO_SPACE 0x16 -#define CEC_OP_RECORD_STATUS_PARENTAL_LOCK 0x17 -#define CEC_OP_RECORD_STATUS_TERMINATED_OK 0x1a -#define CEC_OP_RECORD_STATUS_ALREADY_TERM 0x1b -#define CEC_OP_RECORD_STATUS_OTHER 0x1f - -#define CEC_MSG_RECORD_TV_SCREEN 0x0f - - -/* Timer Programming Feature */ -#define CEC_MSG_CLEAR_ANALOGUE_TIMER 0x33 -/* Recording Sequence Operand (recording_seq) */ -#define CEC_OP_REC_SEQ_SUNDAY 0x01 -#define CEC_OP_REC_SEQ_MONDAY 0x02 -#define CEC_OP_REC_SEQ_TUESDAY 0x04 -#define CEC_OP_REC_SEQ_WEDNESDAY 0x08 -#define CEC_OP_REC_SEQ_THURSDAY 0x10 -#define CEC_OP_REC_SEQ_FRIDAY 0x20 -#define CEC_OP_REC_SEQ_SATERDAY 0x40 -#define CEC_OP_REC_SEQ_ONCE_ONLY 0x00 - -#define CEC_MSG_CLEAR_DIGITAL_TIMER 0x99 - -#define CEC_MSG_CLEAR_EXT_TIMER 0xa1 -/* External Source Specifier Operand (ext_src_spec) */ -#define CEC_OP_EXT_SRC_PLUG 0x04 -#define CEC_OP_EXT_SRC_PHYS_ADDR 0x05 - -#define CEC_MSG_SET_ANALOGUE_TIMER 0x34 -#define CEC_MSG_SET_DIGITAL_TIMER 0x97 -#define CEC_MSG_SET_EXT_TIMER 0xa2 - -#define CEC_MSG_SET_TIMER_PROGRAM_TITLE 0x67 -#define CEC_MSG_TIMER_CLEARED_STATUS 0x43 -/* Timer Cleared Status Data Operand (timer_cleared_status) */ -#define CEC_OP_TIMER_CLR_STAT_RECORDING 0x00 -#define CEC_OP_TIMER_CLR_STAT_NO_MATCHING 0x01 -#define CEC_OP_TIMER_CLR_STAT_NO_INFO 0x02 -#define CEC_OP_TIMER_CLR_STAT_CLEARED 0x80 - -#define CEC_MSG_TIMER_STATUS 0x35 -/* Timer Overlap Warning Operand (timer_overlap_warning) */ -#define CEC_OP_TIMER_OVERLAP_WARNING_NO_OVERLAP 0 -#define CEC_OP_TIMER_OVERLAP_WARNING_OVERLAP 1 -/* Media Info Operand (media_info) */ -#define CEC_OP_MEDIA_INFO_UNPROT_MEDIA 0 -#define CEC_OP_MEDIA_INFO_PROT_MEDIA 1 -#define CEC_OP_MEDIA_INFO_NO_MEDIA 2 -/* Programmed Indicator Operand (prog_indicator) */ -#define CEC_OP_PROG_IND_NOT_PROGRAMMED 0 -#define CEC_OP_PROG_IND_PROGRAMMED 1 -/* Programmed Info Operand (prog_info) */ -#define CEC_OP_PROG_INFO_ENOUGH_SPACE 0x08 -#define CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE 0x09 -#define CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE 0x0b -#define CEC_OP_PROG_INFO_NONE_AVAILABLE 0x0a -/* Not Programmed Error Info Operand (prog_error) */ -#define CEC_OP_PROG_ERROR_NO_FREE_TIMER 0x01 -#define CEC_OP_PROG_ERROR_DATE_OUT_OF_RANGE 0x02 -#define CEC_OP_PROG_ERROR_REC_SEQ_ERROR 0x03 -#define CEC_OP_PROG_ERROR_INV_EXT_PLUG 0x04 -#define CEC_OP_PROG_ERROR_INV_EXT_PHYS_ADDR 0x05 -#define CEC_OP_PROG_ERROR_CA_UNSUPP 0x06 -#define CEC_OP_PROG_ERROR_INSUF_CA_ENTITLEMENTS 0x07 -#define CEC_OP_PROG_ERROR_RESOLUTION_UNSUPP 0x08 -#define CEC_OP_PROG_ERROR_PARENTAL_LOCK 0x09 -#define CEC_OP_PROG_ERROR_CLOCK_FAILURE 0x0a -#define CEC_OP_PROG_ERROR_DUPLICATE 0x0e - - -/* System Information Feature */ -#define CEC_MSG_CEC_VERSION 0x9e -/* CEC Version Operand (cec_version) */ -#define CEC_OP_CEC_VERSION_1_3A 4 -#define CEC_OP_CEC_VERSION_1_4 5 -#define CEC_OP_CEC_VERSION_2_0 6 - -#define CEC_MSG_GET_CEC_VERSION 0x9f -#define CEC_MSG_GIVE_PHYSICAL_ADDR 0x83 -#define CEC_MSG_GET_MENU_LANGUAGE 0x91 -#define CEC_MSG_REPORT_PHYSICAL_ADDR 0x84 -/* Primary Device Type Operand (prim_devtype) */ -#define CEC_OP_PRIM_DEVTYPE_TV 0 -#define CEC_OP_PRIM_DEVTYPE_RECORD 1 -#define CEC_OP_PRIM_DEVTYPE_TUNER 3 -#define CEC_OP_PRIM_DEVTYPE_PLAYBACK 4 -#define CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM 5 -#define CEC_OP_PRIM_DEVTYPE_SWITCH 6 -#define CEC_OP_PRIM_DEVTYPE_PROCESSOR 7 - -#define CEC_MSG_SET_MENU_LANGUAGE 0x32 -#define CEC_MSG_REPORT_FEATURES 0xa6 /* HDMI 2.0 */ -/* All Device Types Operand (all_device_types) */ -#define CEC_OP_ALL_DEVTYPE_TV 0x80 -#define CEC_OP_ALL_DEVTYPE_RECORD 0x40 -#define CEC_OP_ALL_DEVTYPE_TUNER 0x20 -#define CEC_OP_ALL_DEVTYPE_PLAYBACK 0x10 -#define CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM 0x08 -#define CEC_OP_ALL_DEVTYPE_SWITCH 0x04 -/* - * And if you wondering what happened to PROCESSOR devices: those should - * be mapped to a SWITCH. - */ - -/* Valid for RC Profile and Device Feature operands */ -#define CEC_OP_FEAT_EXT 0x80 /* Extension bit */ -/* RC Profile Operand (rc_profile) */ -#define CEC_OP_FEAT_RC_TV_PROFILE_NONE 0x00 -#define CEC_OP_FEAT_RC_TV_PROFILE_1 0x02 -#define CEC_OP_FEAT_RC_TV_PROFILE_2 0x06 -#define CEC_OP_FEAT_RC_TV_PROFILE_3 0x0a -#define CEC_OP_FEAT_RC_TV_PROFILE_4 0x0e -#define CEC_OP_FEAT_RC_SRC_HAS_DEV_ROOT_MENU 0x50 -#define CEC_OP_FEAT_RC_SRC_HAS_DEV_SETUP_MENU 0x48 -#define CEC_OP_FEAT_RC_SRC_HAS_CONTENTS_MENU 0x44 -#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_TOP_MENU 0x42 -#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_CONTEXT_MENU 0x41 -/* Device Feature Operand (dev_features) */ -#define CEC_OP_FEAT_DEV_HAS_RECORD_TV_SCREEN 0x40 -#define CEC_OP_FEAT_DEV_HAS_SET_OSD_STRING 0x20 -#define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL 0x10 -#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 -#define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 -#define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 - -#define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ - - -/* Deck Control Feature */ -#define CEC_MSG_DECK_CONTROL 0x42 -/* Deck Control Mode Operand (deck_control_mode) */ -#define CEC_OP_DECK_CTL_MODE_SKIP_FWD 1 -#define CEC_OP_DECK_CTL_MODE_SKIP_REV 2 -#define CEC_OP_DECK_CTL_MODE_STOP 3 -#define CEC_OP_DECK_CTL_MODE_EJECT 4 - -#define CEC_MSG_DECK_STATUS 0x1b -/* Deck Info Operand (deck_info) */ -#define CEC_OP_DECK_INFO_PLAY 0x11 -#define CEC_OP_DECK_INFO_RECORD 0x12 -#define CEC_OP_DECK_INFO_PLAY_REV 0x13 -#define CEC_OP_DECK_INFO_STILL 0x14 -#define CEC_OP_DECK_INFO_SLOW 0x15 -#define CEC_OP_DECK_INFO_SLOW_REV 0x16 -#define CEC_OP_DECK_INFO_FAST_FWD 0x17 -#define CEC_OP_DECK_INFO_FAST_REV 0x18 -#define CEC_OP_DECK_INFO_NO_MEDIA 0x19 -#define CEC_OP_DECK_INFO_STOP 0x1a -#define CEC_OP_DECK_INFO_SKIP_FWD 0x1b -#define CEC_OP_DECK_INFO_SKIP_REV 0x1c -#define CEC_OP_DECK_INFO_INDEX_SEARCH_FWD 0x1d -#define CEC_OP_DECK_INFO_INDEX_SEARCH_REV 0x1e -#define CEC_OP_DECK_INFO_OTHER 0x1f - -#define CEC_MSG_GIVE_DECK_STATUS 0x1a -/* Status Request Operand (status_req) */ -#define CEC_OP_STATUS_REQ_ON 1 -#define CEC_OP_STATUS_REQ_OFF 2 -#define CEC_OP_STATUS_REQ_ONCE 3 - -#define CEC_MSG_PLAY 0x41 -/* Play Mode Operand (play_mode) */ -#define CEC_OP_PLAY_MODE_PLAY_FWD 0x24 -#define CEC_OP_PLAY_MODE_PLAY_REV 0x20 -#define CEC_OP_PLAY_MODE_PLAY_STILL 0x25 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MIN 0x05 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MED 0x06 -#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MAX 0x07 -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MIN 0x09 -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MED 0x0a -#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MAX 0x0b -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MIN 0x15 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MED 0x16 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MAX 0x17 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MIN 0x19 -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MED 0x1a -#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MAX 0x1b - - -/* Tuner Control Feature */ -#define CEC_MSG_GIVE_TUNER_DEVICE_STATUS 0x08 -#define CEC_MSG_SELECT_ANALOGUE_SERVICE 0x92 -#define CEC_MSG_SELECT_DIGITAL_SERVICE 0x93 -#define CEC_MSG_TUNER_DEVICE_STATUS 0x07 -/* Recording Flag Operand (rec_flag) */ -#define CEC_OP_REC_FLAG_USED 0 -#define CEC_OP_REC_FLAG_NOT_USED 1 -/* Tuner Display Info Operand (tuner_display_info) */ -#define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL 0 -#define CEC_OP_TUNER_DISPLAY_INFO_NONE 1 -#define CEC_OP_TUNER_DISPLAY_INFO_ANALOGUE 2 - -#define CEC_MSG_TUNER_STEP_DECREMENT 0x06 -#define CEC_MSG_TUNER_STEP_INCREMENT 0x05 - - -/* Vendor Specific Commands Feature */ - -/* - * Has also: - * CEC_MSG_CEC_VERSION - * CEC_MSG_GET_CEC_VERSION - */ -#define CEC_MSG_DEVICE_VENDOR_ID 0x87 -#define CEC_MSG_GIVE_DEVICE_VENDOR_ID 0x8c -#define CEC_MSG_VENDOR_COMMAND 0x89 -#define CEC_MSG_VENDOR_COMMAND_WITH_ID 0xa0 -#define CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN 0x8a -#define CEC_MSG_VENDOR_REMOTE_BUTTON_UP 0x8b - - -/* OSD Display Feature */ -#define CEC_MSG_SET_OSD_STRING 0x64 -/* Display Control Operand (disp_ctl) */ -#define CEC_OP_DISP_CTL_DEFAULT 0x00 -#define CEC_OP_DISP_CTL_UNTIL_CLEARED 0x40 -#define CEC_OP_DISP_CTL_CLEAR 0x80 - - -/* Device OSD Transfer Feature */ -#define CEC_MSG_GIVE_OSD_NAME 0x46 -#define CEC_MSG_SET_OSD_NAME 0x47 - - -/* Device Menu Control Feature */ -#define CEC_MSG_MENU_REQUEST 0x8d -/* Menu Request Type Operand (menu_req) */ -#define CEC_OP_MENU_REQUEST_ACTIVATE 0x00 -#define CEC_OP_MENU_REQUEST_DEACTIVATE 0x01 -#define CEC_OP_MENU_REQUEST_QUERY 0x02 - -#define CEC_MSG_MENU_STATUS 0x8e -/* Menu State Operand (menu_state) */ -#define CEC_OP_MENU_STATE_ACTIVATED 0x00 -#define CEC_OP_MENU_STATE_DEACTIVATED 0x01 - -#define CEC_MSG_USER_CONTROL_PRESSED 0x44 -/* UI Broadcast Type Operand (ui_bcast_type) */ -#define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL 0x00 -#define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA 0x01 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE 0x10 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_T 0x20 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_CABLE 0x30 -#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_SAT 0x40 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL 0x50 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_T 0x60 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_CABLE 0x70 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_SAT 0x80 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT 0x90 -#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT2 0x91 -#define CEC_OP_UI_BCAST_TYPE_IP 0xa0 -/* UI Sound Presentation Control Operand (ui_snd_pres_ctl) */ -#define CEC_OP_UI_SND_PRES_CTL_DUAL_MONO 0x10 -#define CEC_OP_UI_SND_PRES_CTL_KARAOKE 0x20 -#define CEC_OP_UI_SND_PRES_CTL_DOWNMIX 0x80 -#define CEC_OP_UI_SND_PRES_CTL_REVERB 0x90 -#define CEC_OP_UI_SND_PRES_CTL_EQUALIZER 0xa0 -#define CEC_OP_UI_SND_PRES_CTL_BASS_UP 0xb1 -#define CEC_OP_UI_SND_PRES_CTL_BASS_NEUTRAL 0xb2 -#define CEC_OP_UI_SND_PRES_CTL_BASS_DOWN 0xb3 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_UP 0xc1 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_NEUTRAL 0xc2 -#define CEC_OP_UI_SND_PRES_CTL_TREBLE_DOWN 0xc3 - -#define CEC_MSG_USER_CONTROL_RELEASED 0x45 - - -/* Remote Control Passthrough Feature */ - -/* - * Has also: - * CEC_MSG_USER_CONTROL_PRESSED - * CEC_MSG_USER_CONTROL_RELEASED - */ - - -/* Power Status Feature */ -#define CEC_MSG_GIVE_DEVICE_POWER_STATUS 0x8f -#define CEC_MSG_REPORT_POWER_STATUS 0x90 -/* Power Status Operand (pwr_state) */ -#define CEC_OP_POWER_STATUS_ON 0 -#define CEC_OP_POWER_STATUS_STANDBY 1 -#define CEC_OP_POWER_STATUS_TO_ON 2 -#define CEC_OP_POWER_STATUS_TO_STANDBY 3 - - -/* General Protocol Messages */ -#define CEC_MSG_FEATURE_ABORT 0x00 -/* Abort Reason Operand (reason) */ -#define CEC_OP_ABORT_UNRECOGNIZED_OP 0 -#define CEC_OP_ABORT_INCORRECT_MODE 1 -#define CEC_OP_ABORT_NO_SOURCE 2 -#define CEC_OP_ABORT_INVALID_OP 3 -#define CEC_OP_ABORT_REFUSED 4 -#define CEC_OP_ABORT_UNDETERMINED 5 - -#define CEC_MSG_ABORT 0xff - - -/* System Audio Control Feature */ - -/* - * Has also: - * CEC_MSG_USER_CONTROL_PRESSED - * CEC_MSG_USER_CONTROL_RELEASED - */ -#define CEC_MSG_GIVE_AUDIO_STATUS 0x71 -#define CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS 0x7d -#define CEC_MSG_REPORT_AUDIO_STATUS 0x7a -/* Audio Mute Status Operand (aud_mute_status) */ -#define CEC_OP_AUD_MUTE_STATUS_OFF 0 -#define CEC_OP_AUD_MUTE_STATUS_ON 1 - -#define CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR 0xa3 -#define CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR 0xa4 -#define CEC_MSG_SET_SYSTEM_AUDIO_MODE 0x72 -/* System Audio Status Operand (sys_aud_status) */ -#define CEC_OP_SYS_AUD_STATUS_OFF 0 -#define CEC_OP_SYS_AUD_STATUS_ON 1 - -#define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST 0x70 -#define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS 0x7e -/* Audio Format ID Operand (audio_format_id) */ -#define CEC_OP_AUD_FMT_ID_CEA861 0 -#define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 - - -/* Audio Rate Control Feature */ -#define CEC_MSG_SET_AUDIO_RATE 0x9a -/* Audio Rate Operand (audio_rate) */ -#define CEC_OP_AUD_RATE_OFF 0 -#define CEC_OP_AUD_RATE_WIDE_STD 1 -#define CEC_OP_AUD_RATE_WIDE_FAST 2 -#define CEC_OP_AUD_RATE_WIDE_SLOW 3 -#define CEC_OP_AUD_RATE_NARROW_STD 4 -#define CEC_OP_AUD_RATE_NARROW_FAST 5 -#define CEC_OP_AUD_RATE_NARROW_SLOW 6 - - -/* Audio Return Channel Control Feature */ -#define CEC_MSG_INITIATE_ARC 0xc0 -#define CEC_MSG_REPORT_ARC_INITIATED 0xc1 -#define CEC_MSG_REPORT_ARC_TERMINATED 0xc2 -#define CEC_MSG_REQUEST_ARC_INITIATION 0xc3 -#define CEC_MSG_REQUEST_ARC_TERMINATION 0xc4 -#define CEC_MSG_TERMINATE_ARC 0xc5 - - -/* Dynamic Audio Lipsync Feature */ -/* Only for CEC 2.0 and up */ -#define CEC_MSG_REQUEST_CURRENT_LATENCY 0xa7 -#define CEC_MSG_REPORT_CURRENT_LATENCY 0xa8 -/* Low Latency Mode Operand (low_latency_mode) */ -#define CEC_OP_LOW_LATENCY_MODE_OFF 0 -#define CEC_OP_LOW_LATENCY_MODE_ON 1 -/* Audio Output Compensated Operand (audio_out_compensated) */ -#define CEC_OP_AUD_OUT_COMPENSATED_NA 0 -#define CEC_OP_AUD_OUT_COMPENSATED_DELAY 1 -#define CEC_OP_AUD_OUT_COMPENSATED_NO_DELAY 2 -#define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY 3 - - -/* Capability Discovery and Control Feature */ -#define CEC_MSG_CDC_MESSAGE 0xf8 -/* Ethernet-over-HDMI: nobody ever does this... */ -#define CEC_MSG_CDC_HEC_INQUIRE_STATE 0x00 -#define CEC_MSG_CDC_HEC_REPORT_STATE 0x01 -/* HEC Functionality State Operand (hec_func_state) */ -#define CEC_OP_HEC_FUNC_STATE_NOT_SUPPORTED 0 -#define CEC_OP_HEC_FUNC_STATE_INACTIVE 1 -#define CEC_OP_HEC_FUNC_STATE_ACTIVE 2 -#define CEC_OP_HEC_FUNC_STATE_ACTIVATION_FIELD 3 -/* Host Functionality State Operand (host_func_state) */ -#define CEC_OP_HOST_FUNC_STATE_NOT_SUPPORTED 0 -#define CEC_OP_HOST_FUNC_STATE_INACTIVE 1 -#define CEC_OP_HOST_FUNC_STATE_ACTIVE 2 -/* ENC Functionality State Operand (enc_func_state) */ -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_NOT_SUPPORTED 0 -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_INACTIVE 1 -#define CEC_OP_ENC_FUNC_STATE_EXT_CON_ACTIVE 2 -/* CDC Error Code Operand (cdc_errcode) */ -#define CEC_OP_CDC_ERROR_CODE_NONE 0 -#define CEC_OP_CDC_ERROR_CODE_CAP_UNSUPPORTED 1 -#define CEC_OP_CDC_ERROR_CODE_WRONG_STATE 2 -#define CEC_OP_CDC_ERROR_CODE_OTHER 3 -/* HEC Support Operand (hec_support) */ -#define CEC_OP_HEC_SUPPORT_NO 0 -#define CEC_OP_HEC_SUPPORT_YES 1 -/* HEC Activation Operand (hec_activation) */ -#define CEC_OP_HEC_ACTIVATION_ON 0 -#define CEC_OP_HEC_ACTIVATION_OFF 1 - -#define CEC_MSG_CDC_HEC_SET_STATE_ADJACENT 0x02 -#define CEC_MSG_CDC_HEC_SET_STATE 0x03 -/* HEC Set State Operand (hec_set_state) */ -#define CEC_OP_HEC_SET_STATE_DEACTIVATE 0 -#define CEC_OP_HEC_SET_STATE_ACTIVATE 1 - -#define CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION 0x04 -#define CEC_MSG_CDC_HEC_NOTIFY_ALIVE 0x05 -#define CEC_MSG_CDC_HEC_DISCOVER 0x06 -/* Hotplug Detect messages */ -#define CEC_MSG_CDC_HPD_SET_STATE 0x10 -/* HPD State Operand (hpd_state) */ -#define CEC_OP_HPD_STATE_CP_EDID_DISABLE 0 -#define CEC_OP_HPD_STATE_CP_EDID_ENABLE 1 -#define CEC_OP_HPD_STATE_CP_EDID_DISABLE_ENABLE 2 -#define CEC_OP_HPD_STATE_EDID_DISABLE 3 -#define CEC_OP_HPD_STATE_EDID_ENABLE 4 -#define CEC_OP_HPD_STATE_EDID_DISABLE_ENABLE 5 -#define CEC_MSG_CDC_HPD_REPORT_STATE 0x11 -/* HPD Error Code Operand (hpd_error) */ -#define CEC_OP_HPD_ERROR_NONE 0 -#define CEC_OP_HPD_ERROR_INITIATOR_NOT_CAPABLE 1 -#define CEC_OP_HPD_ERROR_INITIATOR_WRONG_STATE 2 -#define CEC_OP_HPD_ERROR_OTHER 3 -#define CEC_OP_HPD_ERROR_NONE_NO_VIDEO 4 - -/* End of Messages */ - -/* Helper functions to identify the 'special' CEC devices */ - -static inline bool cec_is_2nd_tv(const struct cec_log_addrs *las) -{ - /* - * It is a second TV if the logical address is 14 or 15 and the - * primary device type is a TV. - */ - return las->num_log_addrs && - las->log_addr[0] >= CEC_LOG_ADDR_SPECIFIC && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_TV; -} - -static inline bool cec_is_processor(const struct cec_log_addrs *las) -{ - /* - * It is a processor if the logical address is 12-15 and the - * primary device type is a Processor. - */ - return las->num_log_addrs && - las->log_addr[0] >= CEC_LOG_ADDR_BACKUP_1 && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_PROCESSOR; -} - -static inline bool cec_is_switch(const struct cec_log_addrs *las) -{ - /* - * It is a switch if the logical address is 15 and the - * primary device type is a Switch and the CDC-Only flag is not set. - */ - return las->num_log_addrs == 1 && - las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && - !(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); -} - -static inline bool cec_is_cdc_only(const struct cec_log_addrs *las) -{ - /* - * It is a CDC-only device if the logical address is 15 and the - * primary device type is a Switch and the CDC-Only flag is set. - */ - return las->num_log_addrs == 1 && - las->log_addr[0] == CEC_LOG_ADDR_UNREGISTERED && - las->primary_device_type[0] == CEC_OP_PRIM_DEVTYPE_SWITCH && - (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY); -} - -#endif -- cgit From 217f6974368188fd8bd7804bf5a036aa5762c5e4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Nov 2016 10:15:11 -0800 Subject: net: busy-poll: allow preemption in sk_busy_loop() After commit 4cd13c21b207 ("softirq: Let ksoftirqd do its job"), sk_busy_loop() needs a bit of care : softirqs might be delayed since we do not allow preemption yet. This patch adds preemptiom points in sk_busy_loop(), and makes sure no unnecessary cache line dirtying or atomic operations are done while looping. A new flag is added into napi->state : NAPI_STATE_IN_BUSY_POLL This prevents napi_complete_done() from clearing NAPIF_STATE_SCHED, so that sk_busy_loop() does not have to grab it again. Similarly, netpoll_poll_lock() is done one time. This gives about 10 to 20 % improvement in various busy polling tests, especially when many threads are busy polling in configurations with large number of NIC queues. This should allow experimenting with bigger delays without hurting overall latencies. Tested: On a 40Gb mlx4 NIC, 32 RX/TX queues. echo 70 >/proc/sys/net/core/busy_read for i in `seq 1 40`; do echo -n $i: ; ./super_netperf $i -H lpaa24 -t UDP_RR -- -N -n; done Before: After: 1: 90072 92819 2: 157289 184007 3: 235772 213504 4: 344074 357513 5: 394755 458267 6: 461151 487819 7: 549116 625963 8: 544423 716219 9: 720460 738446 10: 794686 837612 11: 915998 923960 12: 937507 925107 13: 1019677 971506 14: 1046831 1113650 15: 1114154 1148902 16: 1105221 1179263 17: 1266552 1299585 18: 1258454 1383817 19: 1341453 1312194 20: 1363557 1488487 21: 1387979 1501004 22: 1417552 1601683 23: 1550049 1642002 24: 1568876 1601915 25: 1560239 1683607 26: 1640207 1745211 27: 1706540 1723574 28: 1638518 1722036 29: 1734309 1757447 30: 1782007 1855436 31: 1724806 1888539 32: 1717716 1944297 33: 1778716 1869118 34: 1805738 1983466 35: 1815694 2020758 36: 1893059 2035632 37: 1843406 2034653 38: 1888830 2086580 39: 1972827 2143567 40: 1877729 2181851 Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Cc: Adam Belay Cc: Tariq Toukan Cc: Yuval Mintz Cc: Ariel Elior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 86bacf6a64f0..e71de66e3792 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -334,6 +334,16 @@ enum { NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ + NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ +}; + +enum { + NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), + NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { -- cgit From 364b6055738b4c752c30ccaaf25c624e69d76195 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Nov 2016 10:15:13 -0800 Subject: net: busy-poll: return busypolling status to drivers NAPI drivers use napi_complete_done() or napi_complete() when they drained RX ring and right before re-enabling device interrupts. In busy polling, we can avoid interrupts being delivered since we are polling RX ring in a controlled loop. Drivers can chose to use napi_complete_done() return value to reduce interrupts overhead while busy polling is active. This is optional, legacy drivers should work fine even if not updated. Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Cc: Adam Belay Cc: Tariq Toukan Cc: Yuval Mintz Cc: Ariel Elior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e71de66e3792..bcddf951ccee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -463,16 +463,17 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -void __napi_complete(struct napi_struct *n); -void napi_complete_done(struct napi_struct *n, int work_done); +bool __napi_complete(struct napi_struct *n); +bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete * @n: NAPI context * * Mark NAPI processing as complete. * Consider using napi_complete_done() instead. + * Return false if device should avoid rearming interrupts. */ -static inline void napi_complete(struct napi_struct *n) +static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } -- cgit From c139c6b7b75abfaa2246cbde2393656806d37b51 Mon Sep 17 00:00:00 2001 From: "Longpeng \\(Mike\\)" Date: Wed, 9 Nov 2016 10:51:23 +0800 Subject: ACPI / tebles: remove redundant declare of acpi_table_parse_entries() This function declared twice, so remove one declaration of it. Signed-off-by: Longpeng(Mike) [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 61a3d90f32b3..cb4616641235 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -220,10 +220,6 @@ int __init acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); -int __init acpi_table_parse_entries(char *id, unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries); int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); -- cgit From 89c4b442b78bdba388337cc746fe63caba85f46c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Nov 2016 14:54:50 -0800 Subject: netpoll: more efficient locking Callers of netpoll_poll_lock() own NAPI_STATE_SCHED Callers of netpoll_poll_unlock() have BH blocked between the NAPI_STATE_SCHED being cleared and poll_lock is released. We can avoid the spinlock which has no contention, and use cmpxchg() on poll_owner which we need to set anyway. This removes a possible lockdep violation after the cited commit, since sk_busy_loop() re-enables BH before calling busy_poll_stop() Fixes: 217f69743681 ("net: busy-poll: allow preemption in sk_busy_loop()") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - include/linux/netpoll.h | 13 +++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bcddf951ccee..e84800edd249 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -316,7 +316,6 @@ struct napi_struct { unsigned int gro_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL - spinlock_t poll_lock; int poll_owner; #endif struct net_device *dev; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index b25ee9ffdbe6..1828900c9411 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -78,8 +78,11 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi) struct net_device *dev = napi->dev; if (dev && dev->npinfo) { - spin_lock(&napi->poll_lock); - napi->poll_owner = smp_processor_id(); + int owner = smp_processor_id(); + + while (cmpxchg(&napi->poll_owner, -1, owner) != -1) + cpu_relax(); + return napi; } return NULL; @@ -89,10 +92,8 @@ static inline void netpoll_poll_unlock(void *have) { struct napi_struct *napi = have; - if (napi) { - napi->poll_owner = -1; - spin_unlock(&napi->poll_lock); - } + if (napi) + smp_store_release(&napi->poll_owner, -1); } static inline bool netpoll_tx_running(struct net_device *dev) -- cgit From 6d0d287891a022ebba572327cbd70b5de69a63a2 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 16 Nov 2016 13:23:05 +0100 Subject: locking/core: Provide common cpu_relax_yield() definition No need to duplicate the same define everywhere. Since the only user is stop-machine and the only provider is s390, we can use a default implementation of cpu_relax_yield() in sched.h. Suggested-by: Russell King Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand Acked-by: Russell King Cc: Andrew Morton Cc: Catalin Marinas Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Noam Camus Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-s390 Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1479298985-191589-1-git-send-email-borntraeger@de.ibm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..c1aa3b02f6ac 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2444,6 +2444,10 @@ static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } #endif /* CONFIG_NO_HZ_COMMON */ +#ifndef cpu_relax_yield +#define cpu_relax_yield() cpu_relax() +#endif + /* * Do not use outside of architecture code which knows its limitations. * -- cgit From da6f8ca13fb7d40f263ef647ebb41ff0a575d194 Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Thu, 10 Nov 2016 16:17:49 +0100 Subject: dmaengine: pl08x: Add support for the DMA slave map This patch adds support for the new channel request API introduced in commit a8135d0d79e9d0ad3a4ff494fceeaae83 "dmaengine: core: Introduce new, universal API to request a channel". param field of struct dma_slave_map type entries in the platform data structure should be pointing to struct pl08x_channel_data of related DMA channel. Signed-off-by: Sylwester Nawrocki Tested-by: Charles Keepax Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/amba/pl08x.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 27e9ec8778eb..5308eae9ce35 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -84,6 +84,8 @@ struct pl08x_channel_data { * running any DMA transfer and multiplexing can be recycled * @lli_buses: buses which LLIs can be fetched from: PL08X_AHB1 | PL08X_AHB2 * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2 + * @slave_map: DMA slave matching table + * @slave_map_len: number of elements in @slave_map */ struct pl08x_platform_data { struct pl08x_channel_data *slave_channels; @@ -93,6 +95,8 @@ struct pl08x_platform_data { void (*put_xfer_signal)(const struct pl08x_channel_data *, int); u8 lli_buses; u8 mem_buses; + const struct dma_slave_map *slave_map; + int slave_map_len; }; #ifdef CONFIG_AMBA_PL08X -- cgit From c41668ad5de939855636650d39e961893dc5d6fc Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Thu, 10 Nov 2016 16:17:52 +0100 Subject: ARM: s3c64xx: Drop unused DMA fields from struct s3c64xx_spi_csinfo There is no drivers using those fields so remove them and the remaining initializations. Signed-off-by: Sylwester Nawrocki Tested-by: Charles Keepax Acked-by: Krzysztof Kozlowski Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/platform_data/spi-s3c64xx.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 5c1e21c87270..da79774078a7 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -40,9 +40,6 @@ struct s3c64xx_spi_info { int num_cs; bool no_cs; int (*cfg_gpio)(void); - dma_filter_fn filter; - void *dma_tx; - void *dma_rx; }; /** -- cgit From f97df70b1c879f764f88b25b0e67b03a5213968a Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Mon, 14 Nov 2016 11:12:56 +0000 Subject: xenfs: Use proc_create_mount_point() to create /proc/xen Mounting proc in user namespace containers fails if the xenbus filesystem is mounted on /proc/xen because this directory fails the "permanently empty" test. proc_create_mount_point() exists specifically to create such mountpoints in proc but is currently proc-internal. Export this interface to modules, then use it in xenbus when creating /proc/xen. Signed-off-by: Seth Forshee Signed-off-by: David Vrabel Signed-off-by: Juergen Gross --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b97bf2ef996e..8bd2f726436a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -21,6 +21,7 @@ extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, struct proc_dir_entry *, void *); extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, struct proc_dir_entry *); +struct proc_dir_entry *proc_create_mount_point(const char *name); extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, @@ -56,6 +57,7 @@ static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) { return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} +static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, -- cgit From 298d4de1ed003ad91cb49e068d744db0343cacb6 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 7 Nov 2016 12:47:38 +0000 Subject: i2c: Match using traditional OF methods, then by vendor-less compatible strings This function provides a single call for all I2C devices which need to match firstly using traditional OF means i.e by of_node, then if that fails we attempt to match using the supplied I2C client name with a list of supplied compatible strings with the ',' string removed. The latter is required due to the unruly naming conventions used currently by I2C devices. Acked-by: Grant Likely Signed-off-by: Lee Jones [Kieran: Fix static inline usage on !CONFIG_OF] Tested-by: Kieran Bingham Reviewed-by: Javier Martinez Canillas Tested-by: Javier Martinez Canillas Signed-off-by: Kieran Bingham Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 6422eef428c4..c0a4a12815aa 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -774,6 +774,10 @@ extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); +extern const struct of_device_id +*i2c_of_match_device(const struct of_device_id *matches, + struct i2c_client *client); + #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -790,6 +794,14 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node { return NULL; } + +static inline const struct of_device_id +*i2c_of_match_device(const struct of_device_id *matches, + struct i2c_client *client) +{ + return NULL; +} + #endif /* CONFIG_OF */ #if IS_ENABLED(CONFIG_ACPI) -- cgit From 5f441fcaa3ce54681923475cf0040216d190e646 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 7 Nov 2016 12:47:40 +0000 Subject: i2c: Export i2c_match_id() for direct use by device drivers When there was no other way to match a I2C device to driver i2c_match_id() was exclusively used. However, now there are other types of tables which are commonly supplied, matching on an i2c_device_id table is used less frequently. Instead of _always_ calling i2c_match_id() from within the framework, we only need to do so from drivers which have no other way of matching. This patch makes i2c_match_id() available to the aforementioned device drivers. Acked-by: Grant Likely Signed-off-by: Lee Jones Tested-by: Kieran Bingham Reviewed-by: Javier Martinez Canillas Tested-by: Javier Martinez Canillas Signed-off-by: Kieran Bingham Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c0a4a12815aa..7e00efd6a62f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -243,6 +243,8 @@ struct i2c_client { extern struct i2c_client *i2c_verify_client(struct device *dev); extern struct i2c_adapter *i2c_verify_adapter(struct device *dev); +extern const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, + const struct i2c_client *client); static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) { -- cgit From b8a1a4cd5a98a2adf8dfd6902cd98e57d910ee12 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 7 Nov 2016 12:47:41 +0000 Subject: i2c: Provide a temporary .probe_new() call-back type This will aid the seamless removal of the current probe()'s, more commonly unused than used second parameter. Most I2C drivers can simply switch over to the new interface, others which have DT support can use its own matching instead and others can call i2c_match_id() themselves. This brings I2C's device probe method into line with other similar interfaces in the kernel and prevents the requirement to pass an i2c_device_id table. Suggested-by: Grant Likely Signed-off-by: Lee Jones [Kieran: fix rebase conflicts and adapt for dev_pm_domain_{attach,detach}] Tested-by: Kieran Bingham Reviewed-by: Javier Martinez Canillas Tested-by: Javier Martinez Canillas Signed-off-by: Kieran Bingham Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7e00efd6a62f..82cf90945bb8 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -135,7 +135,8 @@ enum i2c_alert_protocol { * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) * @attach_adapter: Callback for bus addition (deprecated) - * @probe: Callback for device binding + * @probe: Callback for device binding - soon to be deprecated + * @probe_new: New callback for device binding * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown * @alert: Alert callback, for example for the SMBus alert protocol @@ -178,6 +179,11 @@ struct i2c_driver { int (*probe)(struct i2c_client *, const struct i2c_device_id *); int (*remove)(struct i2c_client *); + /* New driver model interface to aid the seamless removal of the + * current probe()'s, more commonly unused than used second parameter. + */ + int (*probe_new)(struct i2c_client *); + /* driver model interfaces that don't relate to enumeration */ void (*shutdown)(struct i2c_client *); -- cgit From 7b96953bc640b6b25665fe17ffca4b668b371f14 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 02:16:13 +0530 Subject: vfio: Mediated device Core driver Design for Mediated Device Driver: Main purpose of this driver is to provide a common interface for mediated device management that can be used by different drivers of different devices. This module provides a generic interface to create the device, add it to mediated bus, add device to IOMMU group and then add it to vfio group. Below is the high Level block diagram, with Nvidia, Intel and IBM devices as example, since these are the devices which are going to actively use this module as of now. +---------------+ | | | +-----------+ | mdev_register_driver() +--------------+ | | | +<------------------------+ __init() | | | mdev | | | | | | bus | +------------------------>+ |<-> VFIO user | | driver | | probe()/remove() | vfio_mdev.ko | APIs | | | | | | | +-----------+ | +--------------+ | | | MDEV CORE | | MODULE | | mdev.ko | | +-----------+ | mdev_register_device() +--------------+ | | | +<------------------------+ | | | | | | nvidia.ko |<-> physical | | | +------------------------>+ | device | | | | callback +--------------+ | | Physical | | | | device | | mdev_register_device() +--------------+ | | interface | |<------------------------+ | | | | | | i915.ko |<-> physical | | | +------------------------>+ | device | | | | callback +--------------+ | | | | | | | | mdev_register_device() +--------------+ | | | +<------------------------+ | | | | | | ccw_device.ko|<-> physical | | | +------------------------>+ | device | | | | callback +--------------+ | +-----------+ | +---------------+ Core driver provides two types of registration interfaces: 1. Registration interface for mediated bus driver: /** * struct mdev_driver - Mediated device's driver * @name: driver name * @probe: called when new device created * @remove:called when device removed * @driver:device driver structure * **/ struct mdev_driver { const char *name; int (*probe) (struct device *dev); void (*remove) (struct device *dev); struct device_driver driver; }; Mediated bus driver for mdev device should use this interface to register and unregister with core driver respectively: int mdev_register_driver(struct mdev_driver *drv, struct module *owner); void mdev_unregister_driver(struct mdev_driver *drv); Mediated bus driver is responsible to add/delete mediated devices to/from VFIO group when devices are bound and unbound to the driver. 2. Physical device driver interface This interface provides vendor driver the set APIs to manage physical device related work in its driver. APIs are : * dev_attr_groups: attributes of the parent device. * mdev_attr_groups: attributes of the mediated device. * supported_type_groups: attributes to define supported type. This is mandatory field. * create: to allocate basic resources in vendor driver for a mediated device. This is mandatory to be provided by vendor driver. * remove: to free resources in vendor driver when mediated device is destroyed. This is mandatory to be provided by vendor driver. * open: open callback of mediated device * release: release callback of mediated device * read : read emulation callback. * write: write emulation callback. * ioctl: ioctl callback. * mmap: mmap emulation callback. Drivers should use these interfaces to register and unregister device to mdev core driver respectively: extern int mdev_register_device(struct device *dev, const struct parent_ops *ops); extern void mdev_unregister_device(struct device *dev); There are no locks to serialize above callbacks in mdev driver and vfio_mdev driver. If required, vendor driver can have locks to serialize above APIs in their driver. Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Reviewed-by: Jike Song Reviewed-by: Dong Jia Shi Signed-off-by: Alex Williamson --- include/linux/mdev.h | 168 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 168 insertions(+) create mode 100644 include/linux/mdev.h (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h new file mode 100644 index 000000000000..ec819e9a115a --- /dev/null +++ b/include/linux/mdev.h @@ -0,0 +1,168 @@ +/* + * Mediated device definition + * + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved. + * Author: Neo Jia + * Kirti Wankhede + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef MDEV_H +#define MDEV_H + +/* Parent device */ +struct parent_device { + struct device *dev; + const struct parent_ops *ops; + + /* internal */ + struct kref ref; + struct mutex lock; + struct list_head next; + struct kset *mdev_types_kset; + struct list_head type_list; +}; + +/* Mediated device */ +struct mdev_device { + struct device dev; + struct parent_device *parent; + uuid_le uuid; + void *driver_data; + + /* internal */ + struct kref ref; + struct list_head next; + struct kobject *type_kobj; +}; + +/** + * struct parent_ops - Structure to be registered for each parent device to + * register the device to mdev module. + * + * @owner: The module owner. + * @dev_attr_groups: Attributes of the parent device. + * @mdev_attr_groups: Attributes of the mediated device. + * @supported_type_groups: Attributes to define supported types. It is mandatory + * to provide supported types. + * @create: Called to allocate basic resources in parent device's + * driver for a particular mediated device. It is + * mandatory to provide create ops. + * @kobj: kobject of type for which 'create' is called. + * @mdev: mdev_device structure on of mediated device + * that is being created + * Returns integer: success (0) or error (< 0) + * @remove: Called to free resources in parent device's driver for a + * a mediated device. It is mandatory to provide 'remove' + * ops. + * @mdev: mdev_device device structure which is being + * destroyed + * Returns integer: success (0) or error (< 0) + * @open: Open mediated device. + * @mdev: mediated device. + * Returns integer: success (0) or error (< 0) + * @release: release mediated device + * @mdev: mediated device. + * @read: Read emulation callback + * @mdev: mediated device structure + * @buf: read buffer + * @count: number of bytes to read + * @ppos: address. + * Retuns number on bytes read on success or error. + * @write: Write emulation callback + * @mdev: mediated device structure + * @buf: write buffer + * @count: number of bytes to be written + * @ppos: address. + * Retuns number on bytes written on success or error. + * @ioctl: IOCTL callback + * @mdev: mediated device structure + * @cmd: ioctl command + * @arg: arguments to ioctl + * @mmap: mmap callback + * @mdev: mediated device structure + * @vma: vma structure + * Parent device that support mediated device should be registered with mdev + * module with parent_ops structure. + **/ + +struct parent_ops { + struct module *owner; + const struct attribute_group **dev_attr_groups; + const struct attribute_group **mdev_attr_groups; + struct attribute_group **supported_type_groups; + + int (*create)(struct kobject *kobj, struct mdev_device *mdev); + int (*remove)(struct mdev_device *mdev); + int (*open)(struct mdev_device *mdev); + void (*release)(struct mdev_device *mdev); + ssize_t (*read)(struct mdev_device *mdev, char __user *buf, + size_t count, loff_t *ppos); + ssize_t (*write)(struct mdev_device *mdev, const char __user *buf, + size_t count, loff_t *ppos); + ssize_t (*ioctl)(struct mdev_device *mdev, unsigned int cmd, + unsigned long arg); + int (*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma); +}; + +/* interface for exporting mdev supported type attributes */ +struct mdev_type_attribute { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, struct device *dev, char *buf); + ssize_t (*store)(struct kobject *kobj, struct device *dev, + const char *buf, size_t count); +}; + +#define MDEV_TYPE_ATTR(_name, _mode, _show, _store) \ +struct mdev_type_attribute mdev_type_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) +#define MDEV_TYPE_ATTR_RW(_name) \ + struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name) +#define MDEV_TYPE_ATTR_RO(_name) \ + struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) +#define MDEV_TYPE_ATTR_WO(_name) \ + struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name) + +/** + * struct mdev_driver - Mediated device driver + * @name: driver name + * @probe: called when new device created + * @remove: called when device removed + * @driver: device driver structure + * + **/ +struct mdev_driver { + const char *name; + int (*probe)(struct device *dev); + void (*remove)(struct device *dev); + struct device_driver driver; +}; + +#define to_mdev_driver(drv) container_of(drv, struct mdev_driver, driver) +#define to_mdev_device(dev) container_of(dev, struct mdev_device, dev) + +static inline void *mdev_get_drvdata(struct mdev_device *mdev) +{ + return mdev->driver_data; +} + +static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data) +{ + mdev->driver_data = data; +} + +extern struct bus_type mdev_bus_type; + +#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type) + +extern int mdev_register_device(struct device *dev, + const struct parent_ops *ops); +extern void mdev_unregister_device(struct device *dev); + +extern int mdev_register_driver(struct mdev_driver *drv, struct module *owner); +extern void mdev_unregister_driver(struct mdev_driver *drv); + +#endif /* MDEV_H */ -- cgit From 2169037dc322d8baa84d9bd4468995f818f25d82 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 02:16:17 +0530 Subject: vfio iommu: Added pin and unpin callback functions to vfio_iommu_driver_ops Added APIs for pining and unpining set of pages. These call back into backend iommu module to actually pin and unpin pages. Added two new callback functions to struct vfio_iommu_driver_ops. Backend IOMMU module that supports pining and unpinning pages for mdev devices should provide these functions. Renamed static functions in vfio_type1_iommu.c to resolve conflicts Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Reviewed-by: Dong Jia Shi Signed-off-by: Alex Williamson --- include/linux/vfio.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 0ecae0b1cd34..3c862a030029 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -75,7 +75,11 @@ struct vfio_iommu_driver_ops { struct iommu_group *group); void (*detach_group)(void *iommu_data, struct iommu_group *group); - + int (*pin_pages)(void *iommu_data, unsigned long *user_pfn, + int npage, int prot, + unsigned long *phys_pfn); + int (*unpin_pages)(void *iommu_data, + unsigned long *user_pfn, int npage); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); @@ -92,6 +96,13 @@ extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); +#define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) + +extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, + int npage, int prot, unsigned long *phys_pfn); +extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, + int npage); + /* * Sub-module helpers */ -- cgit From c086de818dd81c3c2f7cecff23de6585b74340c0 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 10:28:26 +0530 Subject: vfio iommu: Add blocking notifier to notify DMA_UNMAP Added blocking notifier to IOMMU TYPE1 driver to notify vendor drivers about DMA_UNMAP. Exported two APIs vfio_register_notifier() and vfio_unregister_notifier(). Notifier should be registered, if external user wants to use vfio_pin_pages()/vfio_unpin_pages() APIs to pin/unpin pages. Vendor driver should use VFIO_IOMMU_NOTIFY_DMA_UNMAP action to invalidate mappings. Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Signed-off-by: Alex Williamson --- include/linux/vfio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 3c862a030029..6ab13f7e2920 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -80,6 +80,10 @@ struct vfio_iommu_driver_ops { unsigned long *phys_pfn); int (*unpin_pages)(void *iommu_data, unsigned long *user_pfn, int npage); + int (*register_notifier)(void *iommu_data, + struct notifier_block *nb); + int (*unregister_notifier)(void *iommu_data, + struct notifier_block *nb); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); @@ -103,6 +107,14 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage); +#define VFIO_IOMMU_NOTIFY_DMA_UNMAP (1) + +extern int vfio_register_notifier(struct device *dev, + struct notifier_block *nb); + +extern int vfio_unregister_notifier(struct device *dev, + struct notifier_block *nb); + /* * Sub-module helpers */ -- cgit From b3c0a866f1692da2d1059dadd9c429ff5b364fc9 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 02:16:25 +0530 Subject: vfio: Introduce common function to add capabilities Vendor driver using mediated device framework should use vfio_info_add_capability() to add capabilities. Introduced this function to reduce code duplication in vendor drivers. vfio_info_cap_shift() manipulated a data buffer to add an offset to each element in a chain. This data buffer is documented in a uapi header. Changing vfio_info_cap_shift symbol to be available to all drivers. Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 6ab13f7e2920..e26f7ccab564 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -126,6 +126,9 @@ extern struct vfio_info_cap_header *vfio_info_cap_add( struct vfio_info_cap *caps, size_t size, u16 id, u16 version); extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset); +extern int vfio_info_add_capability(struct vfio_info_cap *caps, + int cap_type_id, void *cap_type); + struct pci_dev; #ifdef CONFIG_EEH extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); -- cgit From c747f08aea847c8c0704acf9375ca83c4800f6c1 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Thu, 17 Nov 2016 02:16:27 +0530 Subject: vfio: Introduce vfio_set_irqs_validate_and_prepare() Vendor driver using mediated device framework would use same mechnism to validate and prepare IRQs. Introducing this function to reduce code replication in multiple drivers. Signed-off-by: Kirti Wankhede Signed-off-by: Neo Jia Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e26f7ccab564..15ff0421b423 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -129,6 +129,10 @@ extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset); extern int vfio_info_add_capability(struct vfio_info_cap *caps, int cap_type_id, void *cap_type); +extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, + int num_irqs, int max_irq_type, + size_t *data_size); + struct pci_dev; #ifdef CONFIG_EEH extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); -- cgit From 7c7a6077f5c7a35fc03a7f452875d8440dd1bc8d Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Wed, 16 Nov 2016 22:51:29 +0200 Subject: mei: bus: split RX and async notification callbacks Split callbacks for RX and async notification events on mei bus to eliminate synchronization problems and to open way for RX optimizations. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 4adb2e7c9f84..017f5232b3de 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -8,8 +8,7 @@ struct mei_cl_device; struct mei_device; -typedef void (*mei_cldev_event_cb_t)(struct mei_cl_device *cldev, - u32 events); +typedef void (*mei_cldev_cb_t)(struct mei_cl_device *cldev); /** * struct mei_cl_device - MEI device handle @@ -24,11 +23,12 @@ typedef void (*mei_cldev_event_cb_t)(struct mei_cl_device *cldev, * @me_cl: me client * @cl: mei client * @name: device name - * @event_work: async work to execute event callback - * @event_cb: Drivers register this callback to get asynchronous ME - * events (e.g. Rx buffer pending) notifications. - * @events_mask: Events bit mask requested by driver. - * @events: Events bitmask sent to the driver. + * @rx_work: async work to execute Rx event callback + * @rx_cb: Drivers register this callback to get asynchronous ME + * Rx buffer pending notifications. + * @notif_work: async work to execute FW notif event callback + * @notif_cb: Drivers register this callback to get asynchronous ME + * FW notification pending notifications. * * @do_match: wheather device can be matched with a driver * @is_added: device is already scanned @@ -43,10 +43,10 @@ struct mei_cl_device { struct mei_cl *cl; char name[MEI_CL_NAME_SIZE]; - struct work_struct event_work; - mei_cldev_event_cb_t event_cb; - unsigned long events_mask; - unsigned long events; + struct work_struct rx_work; + mei_cldev_cb_t rx_cb; + struct work_struct notif_work; + mei_cldev_cb_t notif_cb; unsigned int do_match:1; unsigned int is_added:1; @@ -88,13 +88,9 @@ void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length); ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); -int mei_cldev_register_event_cb(struct mei_cl_device *cldev, - unsigned long event_mask, - mei_cldev_event_cb_t read_cb); - -#define MEI_CL_EVENT_RX 0 -#define MEI_CL_EVENT_TX 1 -#define MEI_CL_EVENT_NOTIF 2 +int mei_cldev_register_rx_cb(struct mei_cl_device *cldev, mei_cldev_cb_t rx_cb); +int mei_cldev_register_notif_cb(struct mei_cl_device *cldev, + mei_cldev_cb_t notif_cb); const uuid_le *mei_cldev_uuid(const struct mei_cl_device *cldev); u8 mei_cldev_ver(const struct mei_cl_device *cldev); -- cgit From 06426adf072bca62ac31ea396ff2159a34f276c2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Nov 2016 13:01:59 -0700 Subject: blk-mq: implement hybrid poll mode for sync O_DIRECT This patch enables a hybrid polling mode. Instead of polling after IO submission, we can induce an artificial delay, and then poll after that. For example, if the IO is presumed to complete in 8 usecs from now, we can sleep for 4 usecs, wake up, and then do our polling. This still puts a sleep/wakeup cycle in the IO path, but instead of the wakeup happening after the IO has completed, it'll happen before. With this hybrid scheme, we can achieve big latency reductions while still using the same (or less) amount of CPU. Signed-off-by: Jens Axboe Tested-By: Stephen Bates Reviewed-By: Stephen Bates --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bab18ee5810d..37ed4ea705c8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -509,6 +509,7 @@ struct request_queue { unsigned int request_fn_active; unsigned int rq_timeout; + unsigned int poll_nsec; struct timer_list timeout; struct work_struct timeout_work; struct list_head timeout_list; -- cgit From 64f1c21e86f7fe63337b5c23c129de3ec506431d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Nov 2016 13:03:03 -0700 Subject: blk-mq: make the polling code adaptive The previous commit introduced the hybrid sleep/poll mode. Take that one step further, and use the completion latencies to automatically sleep for half the mean completion time. This is a good approximation. This changes the 'io_poll_delay' sysfs file a bit to expose the various options. Depending on the value, the polling code will behave differently: -1 Never enter hybrid sleep mode 0 Use half of the completion mean for the sleep delay >0 Use this specific value as the sleep delay Signed-off-by: Jens Axboe Tested-By: Stephen Bates Reviewed-By: Stephen Bates --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 37ed4ea705c8..85699bc90a51 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -509,7 +509,7 @@ struct request_queue { unsigned int request_fn_active; unsigned int rq_timeout; - unsigned int poll_nsec; + int poll_nsec; struct timer_list timeout; struct work_struct timeout_work; struct list_head timeout_list; -- cgit From 7254383341bc6e1a61996accd836009f0c922b21 Mon Sep 17 00:00:00 2001 From: Noa Osherovich Date: Thu, 17 Nov 2016 16:06:56 -0600 Subject: PCI: Add Mellanox device IDs Add Mellanox device IDs for use by the mlx4 driver and INTx quirks. [bhelgaas: sorted and adapted from http://lkml.kernel.org/r/1478011644-12080-1-git-send-email-noaos@mellanox.com] Signed-off-by: Noa Osherovich Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c58752fe16c4..f020ab4079d3 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2256,12 +2256,29 @@ #define PCI_DEVICE_ID_ZOLTRIX_2BD0 0x2bd0 #define PCI_VENDOR_ID_MELLANOX 0x15b3 -#define PCI_DEVICE_ID_MELLANOX_TAVOR 0x5a44 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX3 0x1003 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX3_PRO 0x1007 +#define PCI_DEVICE_ID_MELLANOX_CONNECTIB 0x1011 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX4 0x1013 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX4_LX 0x1015 +#define PCI_DEVICE_ID_MELLANOX_TAVOR 0x5a44 #define PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE 0x5a46 -#define PCI_DEVICE_ID_MELLANOX_ARBEL_COMPAT 0x6278 -#define PCI_DEVICE_ID_MELLANOX_ARBEL 0x6282 -#define PCI_DEVICE_ID_MELLANOX_SINAI_OLD 0x5e8c -#define PCI_DEVICE_ID_MELLANOX_SINAI 0x6274 +#define PCI_DEVICE_ID_MELLANOX_SINAI_OLD 0x5e8c +#define PCI_DEVICE_ID_MELLANOX_SINAI 0x6274 +#define PCI_DEVICE_ID_MELLANOX_ARBEL_COMPAT 0x6278 +#define PCI_DEVICE_ID_MELLANOX_ARBEL 0x6282 +#define PCI_DEVICE_ID_MELLANOX_HERMON_SDR 0x6340 +#define PCI_DEVICE_ID_MELLANOX_HERMON_DDR 0x634a +#define PCI_DEVICE_ID_MELLANOX_HERMON_QDR 0x6354 +#define PCI_DEVICE_ID_MELLANOX_HERMON_EN 0x6368 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX_EN 0x6372 +#define PCI_DEVICE_ID_MELLANOX_HERMON_DDR_GEN2 0x6732 +#define PCI_DEVICE_ID_MELLANOX_HERMON_QDR_GEN2 0x673c +#define PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_5_GEN2 0x6746 +#define PCI_DEVICE_ID_MELLANOX_HERMON_EN_GEN2 0x6750 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_T_GEN2 0x675a +#define PCI_DEVICE_ID_MELLANOX_CONNECTX_EN_GEN2 0x6764 +#define PCI_DEVICE_ID_MELLANOX_CONNECTX2 0x676e #define PCI_VENDOR_ID_DFI 0x15bd -- cgit From c02b7bf532f7e46f1f9a0e9c3c27ca3f6f134e8d Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 10 Nov 2016 21:26:23 +0000 Subject: i2c: mux: mellanox: add driver This driver allows I2C routing controlled through CPLD select registers on a wide range of Mellanox systems (CPLD Lattice device). MUX selection is provided by digital and analog HW. Analog part is not under SW control. Digital part is under CPLD control (channel selection/de-selection). Connectivity schema. .---. .-------------. | l | | |-- i2cx1 -- i2cx8 | i |-- i2cn --+--| mlxcpld mux | | n | | | |-- i2cy1 -- i2cy8 | u | | '-------------' | x | | | '---' '---------' i2c-mux-mlxpcld does not necessarily require i2c-mlxcpld. It can be used along with another bus driver, and still control i2c routing through CPLD mux selection, in case the system is equipped with CPLD capable of mux selection control. The Kconfig currently controlling compilation of this code is: drivers/i2c/muxes/Kconfig:config I2C_MUX_MLXCPLD Signed-off-by: Michael Shych Signed-off-by: Vadim Pasternak Reviewed-by: Jiri Pirko Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/i2c/mlxcpld.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/i2c/mlxcpld.h (limited to 'include/linux') diff --git a/include/linux/i2c/mlxcpld.h b/include/linux/i2c/mlxcpld.h new file mode 100644 index 000000000000..b08dcb183fca --- /dev/null +++ b/include/linux/i2c/mlxcpld.h @@ -0,0 +1,52 @@ +/* + * mlxcpld.h - Mellanox I2C multiplexer support in CPLD + * + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Michael Shych + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_I2C_MLXCPLD_H +#define _LINUX_I2C_MLXCPLD_H + +/* Platform data for the CPLD I2C multiplexers */ + +/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info + * @adap_ids - adapter array + * @num_adaps - number of adapters + * @sel_reg_addr - mux select register offset in CPLD space + */ +struct mlxcpld_mux_plat_data { + int *adap_ids; + int num_adaps; + int sel_reg_addr; +}; + +#endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit From 437eb7bf7b28472f8b7689e166dc1dd691367121 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 28 Oct 2016 10:52:06 +0200 Subject: ACPI / hotplug / PCI: Make device_is_managed_by_native_pciehp() public We're about to add runtime PM of hotplug ports, but we need to restrict it to ports that are handled natively by the OS: If they're handled by the firmware (which is the case for Thunderbolt on non-Macs), things would break if the OS put the ports into D3hot behind the firmware's back. To determine if a hotplug port is handled natively, one has to walk up from the port to the root bridge and check the cached _OSC Control Field for the value of the "PCI Express Native Hot Plug control" bit. There's already a function to do that, device_is_managed_by_native_pciehp(), but it's private to drivers/pci/hotplug/acpiphp_glue.c and only compiled in if CONFIG_HOTPLUG_PCI_ACPI is enabled. Make it public and move it to drivers/pci/pci-acpi.c, so that it is available in the more general CONFIG_ACPI case. The function contains a check if the device in question is a hotplug port and returns false if it's not. The caller we're going to add doesn't need this as it only calls the function if it actually *is* a hotplug port. Move the check out of the function into the single existing caller. Rename it to pciehp_is_native() and add some kerneldoc and polish. No functional change intended. Tested-by: Mika Westerberg Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- include/linux/pci_hotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8c7895061121..2e855afa0212 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -176,6 +176,7 @@ struct hotplug_params { #ifdef CONFIG_ACPI #include int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); +bool pciehp_is_native(struct pci_dev *pdev); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); @@ -185,5 +186,6 @@ static inline int pci_get_hp_params(struct pci_dev *dev, { return -ENODEV; } +static inline bool pciehp_is_native(struct pci_dev *pdev) { return true; } #endif #endif -- cgit From bf0f2d380f15f1fa05254b000ddeeb560dfb8638 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 10:31:18 +0100 Subject: block: add reference counting for struct bsg_job Add reference counting to 'struct bsg_job' so we can implement a reuqest timeout handler for bsg_jobs, which is needed for Fibre Channel. Signed-off-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index a226652a5a6c..58e0717fda6e 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -40,6 +40,8 @@ struct bsg_job { struct device *dev; struct request *req; + struct kref kref; + /* Transport/driver specific request/reply structs */ void *request; void *reply; -- cgit From c00da4c90ffd066cdfe7f53ff3529c8ab4a35db0 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 10:31:20 +0100 Subject: scsi: fc: Use bsg_destroy_job fc_destroy_bsgjob() and bsg_destroy_job() are now 1:1 copies, so use the latter. As bsg_destroy_job() comes from bsg-lib we need to select it in Kconfig once CONFOG_SCSI_FC_ATTRS is active. Signed-off-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 58e0717fda6e..67f7de6146c9 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -69,5 +69,6 @@ void bsg_job_done(struct bsg_job *job, int result, int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); +void bsg_destroy_job(struct kref *kref); #endif -- cgit From 6aa858cd335a94e2824ed542140ac9704c0a64e2 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 10:31:21 +0100 Subject: scsi: fc: use bsg_softirq_done bsg_softirq_done() and fc_bsg_softirq_done() are copies of each other, so ditch the fc specific one. Signed-off-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 67f7de6146c9..09f304437cd6 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -70,5 +70,6 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); void bsg_destroy_job(struct kref *kref); +void bsg_softirq_done(struct request *rq); #endif -- cgit From fb6f7c8d8a19e5543d5b4d44c58e2c4e5a82bb12 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 10:31:23 +0100 Subject: block: add bsg_job_put() and bsg_job_get() Add bsg_job_put() and bsg_job_get() so don't need to export bsg_destroy_job() any more. Signed-off-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 09f304437cd6..b708db91618f 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -69,7 +69,8 @@ void bsg_job_done(struct bsg_job *job, int result, int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); -void bsg_destroy_job(struct kref *kref); void bsg_softirq_done(struct request *rq); +void bsg_job_put(struct bsg_job *job); +int __must_check bsg_job_get(struct bsg_job *job); #endif -- cgit From a0f4bd7f2a5be485747aa438cea38f69e3ae8962 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 10:31:24 +0100 Subject: scsi: fc: move FC transport's bsg code to bsg-lib Now that all conversions are done, move the FibreChannel bsg code over to the bsg library. This patch is derived from work done by Mike Christie in 2011 [1] but only the iscsi parts got merged back then. [1] http://marc.info/?l=linux-scsi&m=131149780921009&w=2 Signed-off-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index b708db91618f..657a718c27d2 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -69,7 +69,6 @@ void bsg_job_done(struct bsg_job *job, int result, int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); -void bsg_softirq_done(struct request *rq); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit From 982555fc26f9d8bcdbd5f9db0378fe0682eb4188 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Tue, 8 Nov 2016 10:08:24 +0800 Subject: usb: gadget: fix request length error for isoc transfer For isoc endpoint descriptor, the wMaxPacketSize is not real max packet size (see Table 9-13. Standard Endpoint Descriptor, USB 2.0 specifcation), it may contain the number of packet, so the real max packet should be ep->desc->wMaxPacketSize && 0x7ff. Cc: Felipe F. Tonello Cc: Felipe Balbi Fixes: 16b114a6d797 ("usb: gadget: fix usb_ep_align_maybe endianness and new usb_ep_aligna") Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 8e81f9eb95e4..e4516e9ded0f 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -429,7 +429,9 @@ static inline struct usb_gadget *dev_to_usb_gadget(struct device *dev) */ static inline size_t usb_ep_align(struct usb_ep *ep, size_t len) { - return round_up(len, (size_t)le16_to_cpu(ep->desc->wMaxPacketSize)); + int max_packet_size = (size_t)usb_endpoint_maxp(ep->desc) & 0x7ff; + + return round_up(len, max_packet_size); } /** -- cgit From 9a05e7541c39680d28ecf91892338e074738d5fd Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 18 Nov 2016 15:16:06 +0100 Subject: block: Change extern inline to static inline With compilers which follow the C99 standard (like modern versions of gcc and clang), "extern inline" does the opposite thing from older versions of gcc (emits code for an externally linkable version of the inline function). "static inline" does the intended behavior in all cases instead. Description taken from commit 6d91857d4826 ("staging, rtl8192e, LLVMLinux: Change extern inline to static inline"). This also fixes the following GCC warning when building with CONFIG_PM disabled: ./include/linux/blkdev.h:1143:20: warning: no previous prototype for 'blk_set_runtime_active' [-Wmissing-prototypes] Fixes: d07ab6d11477 ("block: Add blk_set_runtime_active()") Reviewed-by: Mika Westerberg Signed-off-by: Tobias Klauser Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 85699bc90a51..541fdd8787a5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1174,7 +1174,7 @@ static inline int blk_pre_runtime_suspend(struct request_queue *q) static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} static inline void blk_pre_runtime_resume(struct request_queue *q) {} static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} -extern inline void blk_set_runtime_active(struct request_queue *q) {} +static inline void blk_set_runtime_active(struct request_queue *q) {} #endif /* -- cgit From 0ac3ea70897fb9f84b620aeda074ecccf481629d Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 17 Nov 2016 13:45:55 +0200 Subject: net/mlx5: Make the command interface cache more flexible Add more cache command size sets and more entries for each set based on the current commands set different sizes and commands frequency. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ecc451d89ccd..5e7dbbcf47f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -208,7 +208,7 @@ struct mlx5_cmd_first { struct mlx5_cmd_msg { struct list_head list; - struct cache_ent *cache; + struct cmd_msg_cache *parent; u32 len; struct mlx5_cmd_first first; struct mlx5_cmd_mailbox *next; @@ -228,17 +228,17 @@ struct mlx5_cmd_debug { u16 outlen; }; -struct cache_ent { +struct cmd_msg_cache { /* protect block chain allocations */ spinlock_t lock; struct list_head head; + unsigned int max_inbox_size; + unsigned int num_ent; }; -struct cmd_msg_cache { - struct cache_ent large; - struct cache_ent med; - +enum { + MLX5_NUM_COMMAND_CACHES = 5, }; struct mlx5_cmd_stats { @@ -281,7 +281,7 @@ struct mlx5_cmd { struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; struct pci_pool *pool; struct mlx5_cmd_debug dbg; - struct cmd_msg_cache cache; + struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; }; -- cgit From 4ce3bf2fa8ba309b5ca19539fcc8671a0fc084f9 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Thu, 17 Nov 2016 13:45:56 +0200 Subject: net/mlx5: Port module event hardware structures Add hardware structures and constants definitions needed for module events support. Signed-off-by: Huy Nguyen Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 11 +++++++++++ include/linux/mlx5/mlx5_ifc.h | 3 ++- include/linux/mlx5/port.h | 3 +++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 58276144ba81..52b437431c6a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -277,6 +277,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_INTERNAL_ERROR = 0x08, MLX5_EVENT_TYPE_PORT_CHANGE = 0x09, MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, + MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, @@ -552,6 +553,15 @@ struct mlx5_eqe_vport_change { __be32 rsvd1[6]; } __packed; +struct mlx5_eqe_port_module { + u8 reserved_at_0[1]; + u8 module; + u8 reserved_at_2[1]; + u8 module_status; + u8 reserved_at_4[2]; + u8 error_type; +} __packed; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -565,6 +575,7 @@ union ev_data { struct mlx5_eqe_page_req req_pages; struct mlx5_eqe_page_fault page_fault; struct mlx5_eqe_vport_change vport_change; + struct mlx5_eqe_port_module port_module; } __packed; struct mlx5_eqe { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2632cb2caf10..cd1d530ca368 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -824,7 +824,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 early_vf_enable[0x1]; u8 reserved_at_1a9[0x2]; u8 local_ca_ack_delay[0x5]; - u8 reserved_at_1af[0x2]; + u8 port_module_event[0x1]; + u8 reserved_at_1b0[0x1]; u8 ports_check[0x1]; u8 reserved_at_1b2[0x1]; u8 disable_link_up[0x1]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index b3065acd20b4..dde8c7ec5ff1 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -94,6 +94,9 @@ enum mlx5e_link_mode { #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF +#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF + int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port); -- cgit From d4eb4cd78b0774c7061db56844ed2ea7790cc77c Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Thu, 17 Nov 2016 13:45:57 +0200 Subject: net/mlx5: Add handling for port module event For each asynchronous port module event: 1. print with ratelimit to the dmesg log 2. increment the corresponding event counter Signed-off-by: Huy Nguyen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5e7dbbcf47f0..7336c8e529d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -498,6 +498,31 @@ struct mlx5_rl_table { struct mlx5_rl_entry *rl_entry; }; +enum port_module_event_status_type { + MLX5_MODULE_STATUS_PLUGGED = 0x1, + MLX5_MODULE_STATUS_UNPLUGGED = 0x2, + MLX5_MODULE_STATUS_ERROR = 0x3, + MLX5_MODULE_STATUS_NUM = 0x3, +}; + +enum port_module_event_error_type { + MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED, + MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE, + MLX5_MODULE_EVENT_ERROR_BUS_STUCK, + MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT, + MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST, + MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER, + MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE, + MLX5_MODULE_EVENT_ERROR_BAD_CABLE, + MLX5_MODULE_EVENT_ERROR_UNKNOWN, + MLX5_MODULE_EVENT_ERROR_NUM, +}; + +struct mlx5_port_module_event_stats { + u64 status_counters[MLX5_MODULE_STATUS_NUM]; + u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM]; +}; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; @@ -559,6 +584,8 @@ struct mlx5_priv { unsigned long pci_dev_data; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; + + struct mlx5_port_module_event_stats pme_stats; }; enum mlx5_device_state { -- cgit From 0dbc6fe09fbe5f5191bcc606f3bdc9a829f97066 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 17 Nov 2016 13:45:59 +0200 Subject: net/mlx5: Set driver version infrastructure Add driver_version capability bit is enabled, and set driver version command in mlx5_ifc firmware header. The only purpose of this command is to store a driver version/OS string in FW to be reported and displayed in various management systems, such as IPMI/BMC. Signed-off-by: Saeed Mahameed Signed-off-by: Huy Nguyen Signed-off-by: Leon Romanovsky Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cd1d530ca368..f08a06247fba 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -83,6 +83,7 @@ enum { MLX5_CMD_OP_SET_HCA_CAP = 0x109, MLX5_CMD_OP_QUERY_ISSI = 0x10a, MLX5_CMD_OP_SET_ISSI = 0x10b, + MLX5_CMD_OP_SET_DRIVER_VERSION = 0x10d, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -909,7 +910,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_at_261[0x1]; + u8 driver_version[0x1]; u8 pad_tx_eth_packet[0x1]; u8 reserved_at_263[0x8]; u8 log_bf_reg_size[0x5]; @@ -4005,6 +4006,25 @@ struct mlx5_ifc_query_issi_in_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_set_driver_version_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_driver_version_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + u8 driver_version[64][0x8]; +}; + struct mlx5_ifc_query_hca_vport_pkey_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit From 7f503169cabd70c1f13b9279c50eca7dfb9a7d51 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 17 Nov 2016 13:46:01 +0200 Subject: net/mlx5: Add MPCNT register infrastructure Add the needed infrastructure for future use of MPCNT register. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 5 +++ include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 93 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 52b437431c6a..9f489365b3d3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1071,6 +1071,11 @@ enum { MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, }; +enum { + MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP = 0x0, + MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP = 0x2, +}; + static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) { if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7336c8e529d7..ae1f451e8f89 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -121,6 +121,7 @@ enum { MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MCIA = 0x9014, MLX5_REG_MLCR = 0x902b, + MLX5_REG_MPCNT = 0x9051, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f08a06247fba..a5f0fbedf1e7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1757,6 +1757,80 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { u8 reserved_at_4c0[0x300]; }; +struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { + u8 life_time_counter_high[0x20]; + + u8 life_time_counter_low[0x20]; + + u8 rx_errors[0x20]; + + u8 tx_errors[0x20]; + + u8 l0_to_recovery_eieos[0x20]; + + u8 l0_to_recovery_ts[0x20]; + + u8 l0_to_recovery_framing[0x20]; + + u8 l0_to_recovery_retrain[0x20]; + + u8 crc_error_dllp[0x20]; + + u8 crc_error_tlp[0x20]; + + u8 reserved_at_140[0x680]; +}; + +struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits { + u8 life_time_counter_high[0x20]; + + u8 life_time_counter_low[0x20]; + + u8 time_to_boot_image_start[0x20]; + + u8 time_to_link_image[0x20]; + + u8 calibration_time[0x20]; + + u8 time_to_first_perst[0x20]; + + u8 time_to_detect_state[0x20]; + + u8 time_to_l0[0x20]; + + u8 time_to_crs_en[0x20]; + + u8 time_to_plastic_image_start[0x20]; + + u8 time_to_iron_image_start[0x20]; + + u8 perst_handler[0x20]; + + u8 times_in_l1[0x20]; + + u8 times_in_l23[0x20]; + + u8 dl_down[0x20]; + + u8 config_cycle1usec[0x20]; + + u8 config_cycle2to7usec[0x20]; + + u8 config_cycle_8to15usec[0x20]; + + u8 config_cycle_16_to_63usec[0x20]; + + u8 config_cycle_64usec[0x20]; + + u8 correctable_err_msg_sent[0x20]; + + u8 non_fatal_err_msg_sent[0x20]; + + u8 fatal_err_msg_sent[0x20]; + + u8 reserved_at_2e0[0x4e0]; +}; + struct mlx5_ifc_cmd_inter_comp_event_bits { u8 command_completion_vector[0x20]; @@ -2921,6 +2995,12 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { u8 reserved_at_0[0x7c0]; }; +union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits { + struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout; + struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits pcie_tas_cntrs_grp_data_layout; + u8 reserved_at_0[0x7c0]; +}; + union mlx5_ifc_event_auto_bits { struct mlx5_ifc_comp_event_bits comp_event; struct mlx5_ifc_dct_events_bits dct_events; @@ -7240,6 +7320,18 @@ struct mlx5_ifc_ppcnt_reg_bits { union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; +struct mlx5_ifc_mpcnt_reg_bits { + u8 reserved_at_0[0x8]; + u8 pcie_index[0x8]; + u8 reserved_at_10[0xa]; + u8 grp[0x6]; + + u8 clr[0x1]; + u8 reserved_at_21[0x1f]; + + union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set; +}; + struct mlx5_ifc_ppad_reg_bits { u8 reserved_at_0[0x3]; u8 single_mac[0x1]; @@ -7845,6 +7937,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pmtu_reg_bits pmtu_reg; struct mlx5_ifc_ppad_reg_bits ppad_reg; struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg; struct mlx5_ifc_pplm_reg_bits pplm_reg; struct mlx5_ifc_pplr_reg_bits pplr_reg; struct mlx5_ifc_ppsc_reg_bits ppsc_reg; -- cgit From 968ad9da7e0e333e25442950e10a1b631981ce84 Mon Sep 17 00:00:00 2001 From: Raju Lakkaraju Date: Thu, 17 Nov 2016 13:07:21 +0100 Subject: ethtool: Implements ETHTOOL_PHY_GTUNABLE/ETHTOOL_PHY_STUNABLE Adding get_tunable/set_tunable function pointer to the phy_driver structure, and uses these function pointers to implement the ETHTOOL_PHY_GTUNABLE/ETHTOOL_PHY_STUNABLE ioctls. Signed-off-by: Raju Lakkaraju Reviewed-by: Andrew Lunn Signed-off-by: Allan W. Nielsen Signed-off-by: David S. Miller --- include/linux/phy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index b9bd3b4f4ea1..edde28ce163a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -611,6 +611,13 @@ struct phy_driver { void (*get_strings)(struct phy_device *dev, u8 *data); void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); + + /* Get and Set PHY tunables */ + int (*get_tunable)(struct phy_device *dev, + struct ethtool_tunable *tuna, void *data); + int (*set_tunable)(struct phy_device *dev, + struct ethtool_tunable *tuna, + const void *data); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit From 603ab57363a0ba66c77ca4b3027bc0b4505df504 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 17 Nov 2016 11:19:12 -0800 Subject: bus: mvebu-bus: Provide inline stub for mvebu_mbus_get_dram_win_info In preparation for allowing CONFIG_MVNETA_BM to build with COMPILE_TEST, provide an inline stub for mvebu_mbus_get_dram_win_info(). Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mbus.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 2931aa43dab1..0d3f14fd2621 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -82,6 +82,7 @@ static inline int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, } #endif +#ifdef CONFIG_MVEBU_MBUS int mvebu_mbus_save_cpu_target(u32 __iomem *store_addr); void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); void mvebu_mbus_get_pcie_io_aperture(struct resource *res); @@ -97,5 +98,12 @@ int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, size_t mbus_size, phys_addr_t sdram_phys_base, size_t sdram_size); int mvebu_mbus_dt_init(bool is_coherent); +#else +static inline int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, + u8 *attr) +{ + return -EINVAL; +} +#endif /* CONFIG_MVEBU_MBUS */ #endif /* __LINUX_MBUS_H */ -- cgit From 3371d663bb4579f1b2003a92162edd6d90edd089 Mon Sep 17 00:00:00 2001 From: Marc Gonzalez Date: Tue, 15 Nov 2016 10:56:20 +0100 Subject: mtd: nand: Support controllers with custom page If your controller already sends the required NAND commands when reading or writing a page, then the framework is not supposed to send READ0 and SEQIN/PAGEPROG respectively. Signed-off-by: Marc Gonzalez Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 970ceb948835..ed6fd1993be1 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -142,6 +142,12 @@ enum nand_ecc_algo { */ #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) +/* + * If your controller already sends the required NAND commands when + * reading or writing a page, then the framework is not supposed to + * send READ0 and SEQIN/PAGEPROG respectively. + */ +#define NAND_ECC_CUSTOM_PAGE_ACCESS BIT(2) /* Bit mask for flags passed to do_nand_read_ecc */ #define NAND_GET_DEVICE 0x80 @@ -186,6 +192,7 @@ enum nand_ecc_algo { /* Macros to identify the above */ #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) +#define NAND_HAS_SUBPAGE_WRITE(chip) !((chip)->options & NAND_NO_SUBPAGE_WRITE) /* Non chip related options */ /* This option skips the bbt scan during initialization. */ @@ -568,6 +575,11 @@ struct nand_ecc_ctrl { int page); }; +static inline int nand_standard_page_accessors(struct nand_ecc_ctrl *ecc) +{ + return !(ecc->options & NAND_ECC_CUSTOM_PAGE_ACCESS); +} + /** * struct nand_buffers - buffer structure for read/write * @ecccalc: buffer pointer for calculated ECC, size is oobsize. -- cgit From d66016a77757b004b8637f44d87bedfc4a47b89c Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Fri, 18 Nov 2016 15:40:39 -0800 Subject: virtio_net.h: Fix comment. Fix incorrent comment after the final #endif. Signed-off-by: Jarno Rajahalme Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 1c912f85e041..74f1e3363506 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -98,4 +98,4 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, return 0; } -#endif /* _LINUX_VIRTIO_BYTEORDER */ +#endif /* _LINUX_VIRTIO_NET_H */ -- cgit From 9403cd7cbb08aa3709c632decafa2014c8ed96e6 Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Fri, 18 Nov 2016 15:40:40 -0800 Subject: virtio_net: Do not clear memory for struct virtio_net_hdr twice. virtio_net_hdr_from_skb() clears the memory for the header, so there is no point for the callers to do the same. Signed-off-by: Jarno Rajahalme Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 74f1e3363506..66204007d7ac 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -58,7 +58,7 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian) { - memset(hdr, 0, sizeof(*hdr)); + memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); -- cgit From c72d8cdaa5dbd3baf918046ee5149ab69330923e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 19 Nov 2016 04:08:08 +0300 Subject: net: fix bogus cast in skb_pagelen() and use unsigned variables 1) cast to "int" is unnecessary: u8 will be promoted to int before decrementing, small positive numbers fit into "int", so their values won't be changed during promotion. Once everything is int including loop counters, signedness doesn't matter: 32-bit operations will stay 32-bit operations. But! Someone tried to make this loop smart by making everything of the same type apparently in an attempt to optimise it. Do the optimization, just differently. Do the cast where it matters. :^) 2) frag size is unsigned entity and sum of fragments sizes is also unsigned. Make everything unsigned, leave no MOVSX instruction behind. add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-4 (-4) function old new delta skb_cow_data 835 834 -1 ip_do_fragment 2549 2548 -1 ip6_fragment 3130 3128 -2 Total: Before=154865032, After=154865028, chg -0.00% Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a4aeeca7e805..9c535fbccf2c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1799,11 +1799,11 @@ static inline unsigned int skb_headlen(const struct sk_buff *skb) return skb->len - skb->data_len; } -static inline int skb_pagelen(const struct sk_buff *skb) +static inline unsigned int skb_pagelen(const struct sk_buff *skb) { - int i, len = 0; + unsigned int i, len = 0; - for (i = (int)skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) + for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len + skb_headlen(skb); } -- cgit From dd936e4313fa3f60abd6e67abb3cb66fc9a018d1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sun, 20 Nov 2016 20:48:36 -0500 Subject: dax: rip out get_block based IO support No one uses functions using the get_block callback anymore. Rip them out and update documentation. Reviewed-by: Ross Zwisler Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/dax.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 8d1a5c47945f..0afade8bd3d7 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -38,13 +38,8 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops); -ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, - get_block_t, dio_iodone_t, int flags); -int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); -int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops); -int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_wake_mapping_entry_waiter(struct address_space *mapping, pgoff_t index, void *entry, bool wake_all); @@ -73,12 +68,6 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags, get_block_t gb) -{ - return VM_FAULT_FALLBACK; -} - #ifdef CONFIG_FS_DAX_PMD static inline unsigned int dax_radix_order(void *entry) { @@ -101,7 +90,6 @@ static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma, } #endif int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); -#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) static inline bool vma_is_dax(struct vm_area_struct *vma) { -- cgit From 1e8096bb2031c53b6bf3adc7667b4b2bdf2a1ac6 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Thu, 17 Nov 2016 17:57:28 -0500 Subject: EDAC: Add LRDDR4 DRAM type AMD Fam17h systems can support Load-Reduced DDR4 DIMMs. So add this new type to edac.h in preparation for the Fam17h EDAC update. Also, let's fix a format issue with the LRDDR3 line while we're here. Signed-off-by: Yazen Ghannam Cc: Aravind Gopalakrishnan Cc: linux-edac Link: http://lkml.kernel.org/r/1479423463-8536-3-git-send-email-Yazen.Ghannam@amd.com Signed-off-by: Borislav Petkov --- include/linux/edac.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 9e0d78966552..bf2bf87bb2f9 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -192,10 +192,11 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_DDR3: DDR3 RAM * @MEM_RDDR3: Registered DDR3 RAM * This is a variant of the DDR3 memories. - * @MEM_LRDDR3 Load-Reduced DDR3 memory. + * @MEM_LRDDR3: Load-Reduced DDR3 memory. * @MEM_DDR4: Unbuffered DDR4 RAM * @MEM_RDDR4: Registered DDR4 RAM * This is a variant of the DDR4 memories. + * @MEM_LRDDR4: Load-Reduced DDR4 memory. */ enum mem_type { MEM_EMPTY = 0, @@ -218,6 +219,7 @@ enum mem_type { MEM_LRDDR3, MEM_DDR4, MEM_RDDR4, + MEM_LRDDR4, }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -239,6 +241,7 @@ enum mem_type { #define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) #define MEM_FLAG_DDR4 BIT(MEM_DDR4) #define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) +#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) /** * enum edac-type - Error Detection and Correction capabilities and mode -- cgit From 194a6b5b9cb6b91a5f7d86984165a3bc55188599 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 17 Nov 2016 11:46:38 -0500 Subject: sched/wake_q: Rename WAKE_Q to DEFINE_WAKE_Q Currently the wake_q data structure is defined by the WAKE_Q() macro. This macro, however, looks like a function doing something as "wake" is a verb. Even checkpatch.pl was confused as it reported warnings like WARNING: Missing a blank line after declarations #548: FILE: kernel/futex.c:3665: + int ret; + WAKE_Q(wake_q); This patch renames the WAKE_Q() macro to DEFINE_WAKE_Q() which clarifies what the macro is doing and eliminates the checkpatch.pl warnings. Signed-off-by: Waiman Long Acked-by: Davidlohr Bueso Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1479401198-1765-1-git-send-email-longman@redhat.com [ Resolved conflict and added missing rename. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1aa3b02f6ac..dc37cbe2b13c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -989,7 +989,7 @@ enum cpu_idle_type { * already in a wake queue, the wakeup will happen soon and the second * waker can just skip it. * - * The WAKE_Q macro declares and initializes the list head. + * The DEFINE_WAKE_Q macro declares and initializes the list head. * wake_up_q() does NOT reinitialize the list; it's expected to be * called near the end of a function, where the fact that the queue is * not used again will be easy to see by inspection. @@ -1009,7 +1009,7 @@ struct wake_q_head { #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) -#define WAKE_Q(name) \ +#define DEFINE_WAKE_Q(name) \ struct wake_q_head name = { WAKE_Q_TAIL, &name.first } extern void wake_q_add(struct wake_q_head *head, -- cgit From d12a969ebbfcfc25853c4147d42b388f758e8784 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Thu, 17 Nov 2016 17:57:32 -0500 Subject: EDAC, amd64: Add Deferred Error type Currently, deferred errors are classified as correctable in EDAC. Add a new error type for deferred errors so that they are correctly reported to the user. Signed-off-by: Yazen Ghannam Cc: Aravind Gopalakrishnan Cc: linux-edac Link: http://lkml.kernel.org/r/1479423463-8536-7-git-send-email-Yazen.Ghannam@amd.com Signed-off-by: Borislav Petkov --- include/linux/edac.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index bf2bf87bb2f9..cb56dcba68c6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -134,6 +134,7 @@ enum dev_type { enum hw_event_mc_err_type { HW_EVENT_ERR_CORRECTED, HW_EVENT_ERR_UNCORRECTED, + HW_EVENT_ERR_DEFERRED, HW_EVENT_ERR_FATAL, HW_EVENT_ERR_INFO, }; @@ -145,6 +146,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) return "Corrected"; case HW_EVENT_ERR_UNCORRECTED: return "Uncorrected"; + case HW_EVENT_ERR_DEFERRED: + return "Deferred"; case HW_EVENT_ERR_FATAL: return "Fatal"; default: -- cgit From 3f89586bc1ce1434b15f78e62b555c0619852295 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Fri, 1 Jul 2016 17:29:23 +0800 Subject: mfd: axp20x: Add adc volatile ranges for axp22x AXP22x has also some different register map than axp20x, they're also added here. Signed-off-by: Icenowy Zheng Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index fec597fb34cb..6349496f09fc 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -226,6 +226,10 @@ enum { #define AXP20X_OCV_MAX 0xf /* AXP22X specific registers */ +#define AXP22X_PMIC_ADC_H 0x56 +#define AXP22X_PMIC_ADC_L 0x57 +#define AXP22X_TS_ADC_H 0x58 +#define AXP22X_TS_ADC_L 0x59 #define AXP22X_BATLOW_THRES1 0xe6 /* AXP288 specific registers */ -- cgit From 30248feff5e5c6a01ade5e6126009e296ed8bd35 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 18 Nov 2016 13:59:21 +0100 Subject: cpufreq: Make cpufreq_update_policy() void The return value of cpufreq_update_policy() is never used, so make it void. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 40dc2e29f480..7e05c5e4e45c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -175,7 +175,7 @@ void disable_cpufreq(void); u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); +void cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); -- cgit From ed424bb3680b6e6167a44c5c195ec8f9aea3ab3b Mon Sep 17 00:00:00 2001 From: PrasannaKumar Muralidharan Date: Fri, 18 Nov 2016 23:00:10 +0530 Subject: hwrng: Make explicit that max >= 32 always As hw_random core calls ->read with max > 32 or more, make it explicit. Also remove checks involving 'max' being less than 8. Signed-off-by: PrasannaKumar Muralidharan Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 34a0dc18f327..bee0827766a3 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -30,8 +30,7 @@ * Must not be NULL. *OBSOLETE* * @read: New API. drivers can fill up to max bytes of data * into the buffer. The buffer is aligned for any type - * and max is guaranteed to be >= to that alignment - * (either 4 or 8 depending on architecture). + * and max is a multiple of 4 and >= 32 bytes. * @priv: Private data, for use by the RNG driver. * @quality: Estimation of true entropy in RNG's bitstream * (per mill). -- cgit From 6d67942dd0ebc3dddc86edf9208169d064a9b3d7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 19 Nov 2016 01:45:03 +0100 Subject: bpf: add __must_check attributes to refcount manipulating helpers Helpers like bpf_prog_add(), bpf_prog_inc(), bpf_map_inc() can fail with an error, so make sure the caller properly checks their return value and not just ignores it, which could worst-case lead to use after free. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 01c1487277b2..69d0a7f12a3b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -233,14 +233,14 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); -struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i); +struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); +struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref); +struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); @@ -299,7 +299,8 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } -static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, + int i) { return ERR_PTR(-EOPNOTSUPP); } @@ -311,7 +312,8 @@ static inline void bpf_prog_sub(struct bpf_prog *prog, int i) static inline void bpf_prog_put(struct bpf_prog *prog) { } -static inline struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) + +static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } -- cgit From 93c5bdf7ab71bbdae27f8f51fa175e06f000d69d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Nov 2016 16:18:18 +0100 Subject: block: clear all of bi_opf in bio_set_op_attrs Since commit 87374179 ("block: add a proper block layer data direction encoding") we only or the new op and flags into bi_opf in bio_set_op_attrs instead of clearing the old value. I've not seen any breakage with the new behavior, but it seems dangerous. Also convert it to an inline function to make the argument passing safer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4d0044d09984..f57458a6a93b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -207,8 +207,11 @@ enum req_flag_bits { ((req)->cmd_flags & REQ_OP_MASK) /* obsolete, don't use in new code */ -#define bio_set_op_attrs(bio, op, op_flags) \ - ((bio)->bi_opf |= (op | op_flags)) +static inline void bio_set_op_attrs(struct bio *bio, unsigned op, + unsigned op_flags) +{ + bio->bi_opf = op | op_flags; +} static inline bool op_is_write(unsigned int op) { -- cgit From 08b98d3291652bdcd1029a059e39fbcae5ad93e2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 17 Nov 2016 03:28:53 +0100 Subject: PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag Modify the ACPI system sleep support setup code to select suspend-to-idle as the default system sleep state if the ACPI_FADT_LOW_POWER_S0 flag is set in the FADT and the default sleep state was not selected from the kernel command line. Signed-off-by: Rafael J. Wysocki Tested-by: Mario Limonciello --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d9718378a8be..0c729c3c8549 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -194,6 +194,8 @@ struct platform_freeze_ops { }; #ifdef CONFIG_SUSPEND +extern suspend_state_t mem_sleep_default; + /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. -- cgit From a9c6ce57ec2f136d08141e8220a0ffaca216f7b0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 8 Nov 2016 14:38:46 +0100 Subject: led: core: Use atomic bit-field for the blink-flags All the LED_BLINK* flags are accessed read-modify-write from e.g. led_set_brightness and led_blink_set_oneshot while both set_brightness_work and the blink_timer may be running. If these race then the modify step done by one of them may be lost, switch the LED_BLINK* flags to a new atomic work_flags bit-field to avoid this race. Signed-off-by: Hans de Goede Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index ddfcb2df3656..21c598b366f8 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -42,16 +42,20 @@ struct led_classdev { #define LED_UNREGISTERING (1 << 1) /* Upper 16 bits reflect control information */ #define LED_CORE_SUSPENDRESUME (1 << 16) -#define LED_BLINK_SW (1 << 17) -#define LED_BLINK_ONESHOT (1 << 18) -#define LED_BLINK_ONESHOT_STOP (1 << 19) -#define LED_BLINK_INVERT (1 << 20) -#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 21) -#define LED_BLINK_DISABLE (1 << 22) -#define LED_SYSFS_DISABLE (1 << 23) -#define LED_DEV_CAP_FLASH (1 << 24) -#define LED_HW_PLUGGABLE (1 << 25) -#define LED_PANIC_INDICATOR (1 << 26) +#define LED_SYSFS_DISABLE (1 << 17) +#define LED_DEV_CAP_FLASH (1 << 18) +#define LED_HW_PLUGGABLE (1 << 19) +#define LED_PANIC_INDICATOR (1 << 20) + + /* set_brightness_work / blink_timer flags, atomic, private. */ + unsigned long work_flags; + +#define LED_BLINK_SW 0 +#define LED_BLINK_ONESHOT 1 +#define LED_BLINK_ONESHOT_STOP 2 +#define LED_BLINK_INVERT 3 +#define LED_BLINK_BRIGHTNESS_CHANGE 4 +#define LED_BLINK_DISABLE 5 /* Set LED brightness level * Must not sleep. Use brightness_set_blocking for drivers -- cgit From eb1610b4c273370f491c5e194e5a56e3470d81e8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 23 Oct 2016 21:47:26 +0200 Subject: led: core: Fix blink_brightness setting race All 3 of led_timer_func, led_set_brightness and led_set_software_blink set blink_brightness. If led_timer_func or led_set_software_blink race with led_set_brightness they may end up overwriting the new blink_brightness. The new atomic work_flags does not protect against this as it just protects the flags and not blink_brightness. This commit introduces a new new_blink_brightness value which gets set by led_set_brightness and read by led_timer_func on LED on, fixing this. Dealing with the new brightness at LED on time, makes the new brightness apply sooner, which also fixes a led_set_brightness which happens while a oneshot blink which ends in LED on is running not getting applied. Signed-off-by: Hans de Goede Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 21c598b366f8..569cb531094c 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -93,6 +93,7 @@ struct led_classdev { unsigned long blink_delay_on, blink_delay_off; struct timer_list blink_timer; int blink_brightness; + int new_blink_brightness; void (*flash_resume)(struct led_classdev *led_cdev); struct work_struct set_brightness_work; -- cgit From d9345c65eb7930ac6755cf593ee7686f4029ccf4 Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Wed, 2 Nov 2016 05:08:28 -0400 Subject: sched/core: Introduce the vcpu_is_preempted(cpu) interface This patch is the first step to add support to improve lock holder preemption beaviour. vcpu_is_preempted(cpu) does the obvious thing: it tells us whether a vCPU is preempted or not. Defaults to false on architectures that don't support it. Suggested-by: Peter Zijlstra (Intel) Tested-by: Juergen Gross Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) [ Translated the changelog to English. ] Acked-by: Christian Borntraeger Acked-by: Paolo Bonzini Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: benh@kernel.crashing.org Cc: boqun.feng@gmail.com Cc: bsingharora@gmail.com Cc: dave@stgolabs.net Cc: kernellwp@gmail.com Cc: konrad.wilk@oracle.com Cc: linuxppc-dev@lists.ozlabs.org Cc: mpe@ellerman.id.au Cc: paulmck@linux.vnet.ibm.com Cc: paulus@samba.org Cc: rkrcmar@redhat.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: xen-devel-request@lists.xenproject.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1478077718-37424-2-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dc37cbe2b13c..37261afbf16a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3510,6 +3510,18 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +/* + * In order to reduce various lock holder preemption latencies provide an + * interface to see if a vCPU is currently running or not. + * + * This allows us to terminate optimistic spin loops and block, analogous to + * the native optimistic spin heuristic of testing if the lock owner task is + * running or not. + */ +#ifndef vcpu_is_preempted +# define vcpu_is_preempted(cpu) false +#endif + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); -- cgit From 4ec6e863625625a54f527464ab91ce1a1cb16c42 Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Wed, 2 Nov 2016 05:08:34 -0400 Subject: kvm: Introduce kvm_write_guest_offset_cached() It allows us to update some status or field of a structure partially. We can also save a kvm_read_guest_cached() call if we just update one fild of the struct regardless of its current value. Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paolo Bonzini Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: benh@kernel.crashing.org Cc: boqun.feng@gmail.com Cc: borntraeger@de.ibm.com Cc: bsingharora@gmail.com Cc: dave@stgolabs.net Cc: jgross@suse.com Cc: kernellwp@gmail.com Cc: konrad.wilk@oracle.com Cc: linuxppc-dev@lists.ozlabs.org Cc: mpe@ellerman.id.au Cc: paulmck@linux.vnet.ibm.com Cc: paulus@samba.org Cc: rkrcmar@redhat.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: xen-devel-request@lists.xenproject.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1478077718-37424-8-git-send-email-xinhui.pan@linux.vnet.ibm.com [ Typo fixes. ] Signed-off-by: Ingo Molnar --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01c0b9cc3915..6f0023797b33 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -645,6 +645,8 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); +int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, int offset, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); -- cgit From 3a83f4677539bce8eaa2bca9ee9c20e172d7ab04 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 22 Nov 2016 08:57:21 -0700 Subject: block: bio: pass bvec table to bio_init() Some drivers often use external bvec table, so introduce this helper for this case. It is always safe to access the bio->bi_io_vec in this way for this case. After converting to this usage, it will becomes a bit easier to evaluate the remaining direct access to bio->bi_io_vec, so it can help to prepare for the following multipage bvec support. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Fixed up the new O_DIRECT cases. Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index d367cd37a7f7..70a7244f08a7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -420,7 +420,8 @@ extern int bio_phys_segments(struct request_queue *, struct bio *); extern int submit_bio_wait(struct bio *bio); extern void bio_advance(struct bio *, unsigned); -extern void bio_init(struct bio *); +extern void bio_init(struct bio *bio, struct bio_vec *table, + unsigned short max_vecs); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); -- cgit From ae0f5499511e5b1723792c848e44d661d0d4e22f Mon Sep 17 00:00:00 2001 From: Bandan Das Date: Tue, 15 Nov 2016 01:36:18 -0500 Subject: kvm: x86: don't print warning messages for unimplemented msrs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change unimplemented msrs messages to use pr_debug. If CONFIG_DYNAMIC_DEBUG is set, then these messages can be enabled at run time or else -DDEBUG can be used at compile time to enable them. These messages will still be printed if ignore_msrs=1. Signed-off-by: Bandan Das Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01c0b9cc3915..274bf343cbd0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -439,6 +439,9 @@ struct kvm { pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug(fmt, ...) \ pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) +#define kvm_debug_ratelimited(fmt, ...) \ + pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \ + ## __VA_ARGS__) #define kvm_pr_unimpl(fmt, ...) \ pr_err_ratelimited("kvm [%i]: " fmt, \ task_tgid_nr(current), ## __VA_ARGS__) @@ -450,6 +453,9 @@ struct kvm { #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +#define vcpu_debug_ratelimited(vcpu, fmt, ...) \ + kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \ + ## __VA_ARGS__) #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) -- cgit From bfedb589252c01fa505ac9f6f2a3d5d68d707ef4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 13 Oct 2016 21:23:16 -0500 Subject: mm: Add a user_ns owner to mm_struct and fix ptrace permission checks During exec dumpable is cleared if the file that is being executed is not readable by the user executing the file. A bug in ptrace_may_access allows reading the file if the executable happens to enter into a subordinate user namespace (aka clone(CLONE_NEWUSER), unshare(CLONE_NEWUSER), or setns(fd, CLONE_NEWUSER). This problem is fixed with only necessary userspace breakage by adding a user namespace owner to mm_struct, captured at the time of exec, so it is clear in which user namespace CAP_SYS_PTRACE must be present in to be able to safely give read permission to the executable. The function ptrace_may_access is modified to verify that the ptracer has CAP_SYS_ADMIN in task->mm->user_ns instead of task->cred->user_ns. This ensures that if the task changes it's cred into a subordinate user namespace it does not become ptraceable. The function ptrace_attach is modified to only set PT_PTRACE_CAP when CAP_SYS_PTRACE is held over task->mm->user_ns. The intent of PT_PTRACE_CAP is to be a flag to note that whatever permission changes the task might go through the tracer has sufficient permissions for it not to be an issue. task->cred->user_ns is always the same as or descendent of mm->user_ns. Which guarantees that having CAP_SYS_PTRACE over mm->user_ns is the worst case for the tasks credentials. To prevent regressions mm->dumpable and mm->user_ns are not considered when a task has no mm. As simply failing ptrace_may_attach causes regressions in privileged applications attempting to read things such as /proc//stat Cc: stable@vger.kernel.org Acked-by: Kees Cook Tested-by: Cyrill Gorcunov Fixes: 8409cca70561 ("userns: allow ptrace from non-init user namespaces") Signed-off-by: "Eric W. Biederman" --- include/linux/mm_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4a8acedf4b7d..08d947fc4c59 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -473,6 +473,7 @@ struct mm_struct { */ struct task_struct __rcu *owner; #endif + struct user_namespace *user_ns; /* store ref to file /proc//exe symlink points to */ struct file __rcu *exe_file; -- cgit From 64b875f7ac8a5d60a4e191479299e931ee949b67 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2016 18:48:07 -0600 Subject: ptrace: Capture the ptracer's creds not PT_PTRACE_CAP When the flag PT_PTRACE_CAP was added the PTRACE_TRACEME path was overlooked. This can result in incorrect behavior when an application like strace traces an exec of a setuid executable. Further PT_PTRACE_CAP does not have enough information for making good security decisions as it does not report which user namespace the capability is in. This has already allowed one mistake through insufficient granulariy. I found this issue when I was testing another corner case of exec and discovered that I could not get strace to set PT_PTRACE_CAP even when running strace as root with a full set of caps. This change fixes the above issue with strace allowing stracing as root a setuid executable without disabling setuid. More fundamentaly this change allows what is allowable at all times, by using the correct information in it's decision. Cc: stable@vger.kernel.org Fixes: 4214e42f96d4 ("v2.4.9.11 -> v2.4.9.12") Signed-off-by: "Eric W. Biederman" --- include/linux/capability.h | 1 + include/linux/ptrace.h | 1 - include/linux/sched.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index dbc21c719ce6..d6088e2a7668 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -242,6 +242,7 @@ static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) #endif /* CONFIG_MULTIUSER */ extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); +extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 504c98a278d4..e13bfdf7f314 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -19,7 +19,6 @@ #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 #define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ -#define PT_PTRACE_CAP 0x00000004 /* ptracer can follow suid-exec */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..e9f693598e15 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1656,6 +1656,7 @@ struct task_struct { struct list_head cpu_timers[3]; /* process credentials */ + const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ const struct cred __rcu *real_cred; /* objective and real subjective task * credentials (COW) */ const struct cred __rcu *cred; /* effective (overridable) subjective task -- cgit From 84d77d3f06e7e8dea057d10e8ec77ad71f721be3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 22 Nov 2016 12:06:50 -0600 Subject: ptrace: Don't allow accessing an undumpable mm It is the reasonable expectation that if an executable file is not readable there will be no way for a user without special privileges to read the file. This is enforced in ptrace_attach but if ptrace is already attached before exec there is no enforcement for read-only executables. As the only way to read such an mm is through access_process_vm spin a variant called ptrace_access_vm that will fail if the target process is not being ptraced by the current process, or the current process did not have sufficient privileges when ptracing began to read the target processes mm. In the ptrace implementations replace access_process_vm by ptrace_access_vm. There remain several ptrace sites that still use access_process_vm as they are reading the target executables instructions (for kernel consumption) or register stacks. As such it does not appear necessary to add a permission check to those calls. This bug has always existed in Linux. Fixes: v1.0 Cc: stable@vger.kernel.org Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- include/linux/mm.h | 2 ++ include/linux/ptrace.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a92c8d73aeaf..0b5b2e4df14e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1270,6 +1270,8 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); +extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, + unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e13bfdf7f314..e0e539321ab9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -8,6 +8,9 @@ #include /* For task_active_pid_ns. */ #include +extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags); + /* * Ptrace flags * -- cgit From f84df2a6f268de584a201e8911384a2d244876e3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2016 22:06:51 -0600 Subject: exec: Ensure mm->user_ns contains the execed files When the user namespace support was merged the need to prevent ptrace from revealing the contents of an unreadable executable was overlooked. Correct this oversight by ensuring that the executed file or files are in mm->user_ns, by adjusting mm->user_ns. Use the new function privileged_wrt_inode_uidgid to see if the executable is a member of the user namespace, and as such if having CAP_SYS_PTRACE in the user namespace should allow tracing the executable. If not update mm->user_ns to the parent user namespace until an appropriate parent is found. Cc: stable@vger.kernel.org Reported-by: Jann Horn Fixes: 9e4a36ece652 ("userns: Fail exec for suid and sgid binaries with ids outside our user namespace.") Signed-off-by: "Eric W. Biederman" --- include/linux/capability.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index d6088e2a7668..6ffb67e10c06 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -240,6 +240,7 @@ static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) return true; } #endif /* CONFIG_MULTIUSER */ +extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode); extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); -- cgit From d6526e73dbbbc4c382c1b16942413eab77ed5e1a Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Nov 2016 19:35:22 +0100 Subject: x86/mce/therm_throt: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Cc: Tony Luck Cc: rt@linuxtronix.de Cc: Borislav Petkov Cc: linux-edac@vger.kernel.org Link: http://lkml.kernel.org/r/20161117183541.8588-2-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 79b96f647d64..aea6c6a63139 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,6 +59,7 @@ enum cpuhp_state { CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, + CPUHP_X86_THERM_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 33d97302eb502b72b76107d3122afbf18b09b3ec Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 21 Nov 2016 13:15:32 +0100 Subject: x86/mce/therm_throt: Move hotplug callbacks to online No point to have the sysfs files around before the cpu is online and no point to have them around until the cpu is dead. Get rid of the explicit state. Signed-off-by: Thomas Gleixner Cc: Sebastian Siewior Cc: Tony Luck Cc: Borislav Petkov --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index aea6c6a63139..79b96f647d64 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,7 +59,6 @@ enum cpuhp_state { CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, - CPUHP_X86_THERM_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 8c07b494ab2859bc7efb27c40d6faff255f2d2ae Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Nov 2016 19:35:23 +0100 Subject: x86/cpuid: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Cc: rt@linuxtronix.de Link: http://lkml.kernel.org/r/20161117183541.8588-3-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 79b96f647d64..bc340ef2f200 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,6 +59,7 @@ enum cpuhp_state { CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, + CPUHP_X86_CPUID_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From ee92be9b0d7ad34cb58b61d5c0933d2e5ff7c31d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 21 Nov 2016 13:07:34 +0100 Subject: x86/cpuid: Move the hotplug callbacks to online No point to have this file around before the cpu is online and no point to have it around until the cpu is dead. Get rid of the explicit state. Signed-off-by: Thomas Gleixner Cc: Sebastian Siewior --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index bc340ef2f200..79b96f647d64 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,7 +59,6 @@ enum cpuhp_state { CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, - CPUHP_X86_CPUID_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 9c248f8896e6bf0c77abb98bfea8d69b5a7cd11d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Nov 2016 19:35:28 +0100 Subject: PCI/xgene-msi: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Cc: linux-pci@vger.kernel.org Cc: Duc Dang Cc: rt@linuxtronix.de Cc: Bjorn Helgaas Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20161117183541.8588-8-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 79b96f647d64..94c6a189421f 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -38,6 +38,7 @@ enum cpuhp_state { CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC_DEAD, CPUHP_NET_DEV_DEAD, + CPUHP_PCI_XGENE_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 38b482929e8f96dfe459d2ef757d0a5c3a74cea3 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Nov 2016 19:35:33 +0100 Subject: net/iucv: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. The smp function calls in the online/downprep callbacks are not required as the callback is guaranteed to be invoked on the upcoming/outgoing cpu. Signed-off-by: Sebastian Andrzej Siewior Cc: "David S. Miller" Cc: linux-s390@vger.kernel.org Cc: netdev@vger.kernel.org Cc: Ursula Braun Cc: rt@linuxtronix.de Link: http://lkml.kernel.org/r/20161117183541.8588-13-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 94c6a189421f..12bbcf3ded70 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -60,6 +60,7 @@ enum cpuhp_state { CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, + CPUHP_NET_IUCV_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From a3c9b14f6f151ee4c2a119fab14f9a60d1684d60 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Nov 2016 19:35:35 +0100 Subject: arm/bL_switcher: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Cc: rt@linuxtronix.de Cc: linux-arm-kernel@lists.infradead.org Cc: Russell King Link: http://lkml.kernel.org/r/20161117183541.8588-15-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 12bbcf3ded70..e3771fb959c0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -61,6 +61,7 @@ enum cpuhp_state { CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, CPUHP_NET_IUCV_PREPARE, + CPUHP_ARM_BL_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 478409dd683db76cbcfe7bf8332a37f01deb0a2d Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Mon, 21 Nov 2016 15:57:18 +0800 Subject: tracing: Add hook to function tracing for other subsystems to use Currently Function traces can be only exported to the ring buffer. This adds a trace_export concept which can process traces and export them to a registered destination as an addition to the current one that outputs to Ftrace - i.e. ring buffer. In this way, if we want function traces to be sent to other destinations rather than only to the ring buffer, we just need to register a new trace_export and implement its own .write() function for writing traces to storage. With this patch, only function tracing (trace type is TRACE_FN) is supported. Link: http://lkml.kernel.org/r/1479715043-6534-2-git-send-email-zhang.chunyan@linaro.org Signed-off-by: Chunyan Zhang Signed-off-by: Steven Rostedt --- include/linux/trace.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 include/linux/trace.h (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h new file mode 100644 index 000000000000..9330a58e2651 --- /dev/null +++ b/include/linux/trace.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_TRACE_H +#define _LINUX_TRACE_H + +#ifdef CONFIG_TRACING +/* + * The trace export - an export of Ftrace output. The trace_export + * can process traces and export them to a registered destination as + * an addition to the current only output of Ftrace - i.e. ring buffer. + * + * If you want traces to be sent to some other place rather than ring + * buffer only, just need to register a new trace_export and implement + * its own .write() function for writing traces to the storage. + * + * next - pointer to the next trace_export + * write - copy traces which have been delt with ->commit() to + * the destination + */ +struct trace_export { + struct trace_export __rcu *next; + void (*write)(const void *, unsigned int); +}; + +int register_ftrace_export(struct trace_export *export); +int unregister_ftrace_export(struct trace_export *export); + +#endif /* CONFIG_TRACING */ + +#endif /* _LINUX_TRACE_H */ -- cgit From 9dfed80d87ca2c365cd1004a91ef4ed716c8e44e Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Mon, 21 Nov 2016 15:57:23 +0800 Subject: stm: Mark the functions of writing STM with notrace If CONFIG_STM_SOURCE_FTRACE is selected, Function trace data can be writen to sink via STM, all functions that related to writing data packets to STM should be marked 'notrace' to avoid being traced by Ftrace, otherwise the program would stall into an endless loop. Link: http://lkml.kernel.org/r/1479715043-6534-7-git-send-email-zhang.chunyan@linaro.org Signed-off-by: Chunyan Zhang Acked-by: Alexander Shishkin Signed-off-by: Steven Rostedt --- include/linux/stm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stm.h b/include/linux/stm.h index 8369d8a8cabd..210ff2292361 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -133,7 +133,7 @@ int stm_source_register_device(struct device *parent, struct stm_source_data *data); void stm_source_unregister_device(struct stm_source_data *data); -int stm_source_write(struct stm_source_data *data, unsigned int chan, - const char *buf, size_t count); +int notrace stm_source_write(struct stm_source_data *data, unsigned int chan, + const char *buf, size_t count); #endif /* _STM_H_ */ -- cgit From 29fd0ec2bdbef6734fd4c39c23f61d9f030a66a0 Mon Sep 17 00:00:00 2001 From: Nick Dyer Date: Tue, 22 Nov 2016 17:44:12 -0800 Subject: Input: synaptics-rmi4 - add support for F34 device reflash Add support for updating firmware, triggered by a sysfs attribute. This patch has been tested on Synaptics S7300. Signed-off-by: Nick Dyer Tested-by: Chris Healy Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index ac904bb439a5..4096b0246c23 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -337,11 +337,13 @@ struct rmi_driver_data { struct rmi_device *rmi_dev; struct rmi_function *f01_container; + struct rmi_function *f34_container; bool f01_bootloader_mode; u32 attn_count; int num_of_irq_regs; int irq_count; + void *irq_memory; unsigned long *irq_status; unsigned long *fn_irq_bits; unsigned long *current_irq_mask; -- cgit From c762cc68b6a12eedebefc156ea4838e54804e2eb Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 22 Nov 2016 17:57:02 -0800 Subject: Input: synaptics-rmi4 - propagate correct number of rx and tx electrodes to F54 F54 diagnostics report functions provide data based on the number of enabled rx and tx electrodes, which is not identical to the number of electrodes reported with F54:Query0 and F54:Query1. Those values report the number of supported electrodes, not the number of enabled electrodes. The number of enabled electrodes can be determined by analyzing F55:Ctrl1 (sensor receiver assignment) and F55:Ctrl2 (sensor transmitter assignment). Propagate the number of enabled electrodes from F55 to F54 to avoid corrupted output if not all electrodes are enabled. Fixes: 3a762dbd5347 ("[media] Input: synaptics-rmi4 - add support for F54 ...") Signed-off-by: Guenter Roeck Tested-by: Nick Dyer Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 4096b0246c23..8499b6aa2221 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -354,6 +354,9 @@ struct rmi_driver_data { u8 pdt_props; u8 bsr; + u8 num_rx_electrodes; + u8 num_tx_electrodes; + bool enabled; void *data; -- cgit From 4d0fe7490d7f4d61b582acbae718328284f151b9 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Mon, 7 Nov 2016 21:08:52 -0800 Subject: thermal: core: move trips attributes to tz->device.groups Finally, move the last thermal zone sysfs attributes to tz->device.groups: trips attributes. This requires adding a attribute_group to thermal_zone_device, creating it dynamically, and then setting all trips attributes in it. The trips attribute is then added to the tz->device.groups. As the removal of all attributes are handled by device core, the device remove calls are not needed anymore. Cc: Zhang Rui Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 511182a88e76..e275e98bdceb 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -204,6 +205,7 @@ struct thermal_zone_device { int id; char type[THERMAL_NAME_LENGTH]; struct device device; + struct attribute_group trips_attribute_group; struct thermal_attr *trip_temp_attrs; struct thermal_attr *trip_type_attrs; struct thermal_attr *trip_hyst_attrs; -- cgit From 1cea4e7776b7e9096b696eeb66364f51a8d321ec Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 15 Sep 2016 15:44:22 +0100 Subject: devfreq_cooling: make the structs devfreq_cooling_xxx visible for all MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the protection #ifdef CONFIG_DEVFREQ_THERMAL cuts the needed structures devfreq_cooling_ops and devfreq_cooling_device. The functions which are supposed to provide the empty implementation complain about unknown structures. Similar solution is present in include/linux/devfreq.h. Reviewed-by: Ørjan Eide Signed-off-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- include/linux/devfreq_cooling.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h index 7adf6cc4b305..3049f9422507 100644 --- a/include/linux/devfreq_cooling.h +++ b/include/linux/devfreq_cooling.h @@ -20,7 +20,6 @@ #include #include -#ifdef CONFIG_DEVFREQ_THERMAL /** * struct devfreq_cooling_power - Devfreq cooling power ops @@ -43,6 +42,8 @@ struct devfreq_cooling_power { unsigned long dyn_power_coeff; }; +#ifdef CONFIG_DEVFREQ_THERMAL + struct thermal_cooling_device * of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, struct devfreq_cooling_power *dfc_power); -- cgit From 3aa5374376746f20a27be8682be7f91c8b71d1d8 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Thu, 15 Sep 2016 15:44:23 +0100 Subject: devfreq_cooling: pass a pointer to devfreq in the power model callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the devfreq cooling device was designed, it was an oversight not to pass a pointer to the struct devfreq as the first parameters of the callbacks. The design patterns of the kernel suggest it for a good reason. By passing a pointer to struct devfreq, the driver can register one function that works with multiple devices. With the current implementation, a driver that can work with multiple devices has to create multiple copies of the same function with different parameters so that each devfreq_cooling_device can use the appropriate one. By passing a pointer to struct devfreq, the driver can identify which device it's referring to. Cc: Zhang Rui Cc: Eduardo Valentin Reviewed-by: Punit Agrawal Reviewed-by: Ørjan Eide Reviewed-by: Lukasz Luba Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- include/linux/devfreq_cooling.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h index 3049f9422507..c35d0c0e0ada 100644 --- a/include/linux/devfreq_cooling.h +++ b/include/linux/devfreq_cooling.h @@ -36,8 +36,10 @@ * @dyn_power_coeff * frequency * voltage^2 */ struct devfreq_cooling_power { - unsigned long (*get_static_power)(unsigned long voltage); - unsigned long (*get_dynamic_power)(unsigned long freq, + unsigned long (*get_static_power)(struct devfreq *devfreq, + unsigned long voltage); + unsigned long (*get_dynamic_power)(struct devfreq *devfreq, + unsigned long freq, unsigned long voltage); unsigned long dyn_power_coeff; }; -- cgit From ba6379f7e6c7e51b3c0e92672bc61bb6961c2b5e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 23 Nov 2016 12:53:00 +0100 Subject: fs: Provide function to get superblock with exclusive s_umount Quota code will need a variant of get_super_thawed() that returns superblock with s_umount held in exclusive mode to serialize quota on and quota off operations. Provide this functionality. Signed-off-by: Jan Kara --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..d04cfdefcd11 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2949,8 +2949,10 @@ extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); extern struct super_block *get_super_thawed(struct block_device *); +extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev); extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); +extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); -- cgit From 383d0fca7035a12f1201277d33e8fc87c9d60c9a Mon Sep 17 00:00:00 2001 From: Venkat Reddy Talla Date: Thu, 17 Nov 2016 23:24:35 +0530 Subject: regulator: max77620: add support to configure MPOK Adding support to configure regulator POK mapping bit to control nRST_IO and GPIO1 POK function. In tegra based platform which uses MAX20024 pmic, when some of regulators are configured FPS_NONE(flexible power sequencer) causes PMIC GPIO1 to go low which lead to various other rails turning off, to avoid this MPOK bit of those regulators need to be set to 0 so that PMIC GPIO1 will not go low. Signed-off-by: Venkat Reddy Talla Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/max77620.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max77620.h b/include/linux/mfd/max77620.h index 3ca0af07fc78..ad2a9a852aea 100644 --- a/include/linux/mfd/max77620.h +++ b/include/linux/mfd/max77620.h @@ -180,6 +180,7 @@ #define MAX77620_SD_CFG1_FPWM_SD_MASK BIT(2) #define MAX77620_SD_CFG1_FPWM_SD_SKIP 0 #define MAX77620_SD_CFG1_FPWM_SD_FPWM BIT(2) +#define MAX20024_SD_CFG1_MPOK_MASK BIT(1) #define MAX77620_SD_CFG1_FSRADE_SD_MASK BIT(0) #define MAX77620_SD_CFG1_FSRADE_SD_DISABLE 0 #define MAX77620_SD_CFG1_FSRADE_SD_ENABLE BIT(0) @@ -187,6 +188,7 @@ /* LDO_CNFG2 */ #define MAX77620_LDO_POWER_MODE_MASK 0xC0 #define MAX77620_LDO_POWER_MODE_SHIFT 6 +#define MAX20024_LDO_CFG2_MPOK_MASK BIT(2) #define MAX77620_LDO_CFG2_ADE_MASK BIT(1) #define MAX77620_LDO_CFG2_ADE_DISABLE 0 #define MAX77620_LDO_CFG2_ADE_ENABLE BIT(1) -- cgit From 4239174570da080f3623724d97062bf55de7e36b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 23 Nov 2016 15:52:45 -0500 Subject: tracing: Make tracepoint_printk a static_key Currently, when tracepoint_printk is set (enabled by the "tp_printk" kernel command line), it causes trace events to print via printk(). This is a very dangerous operation, but is useful for debugging. The issue is, it's seldom used, but it is always checked even if it's not enabled by the kernel command line. Instead of having this feature called by a branch against a variable, turn that variable into a static key, and this will remove the test and jump. To simplify things, the functions output_printk() and trace_event_buffer_commit() were moved from trace_events.c to trace.c. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b3d34d3e0e7e..8700049fd0e5 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -945,6 +945,10 @@ extern int __disable_trace_on_warning; #define INIT_TRACE_RECURSION .trace_recursion = 0, #endif +int tracepoint_printk_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + #else /* CONFIG_TRACING */ static inline void disable_trace_on_warning(void) { } #endif /* CONFIG_TRACING */ -- cgit From 3bee9ea1de687925d116670f036599cbed8b66b0 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 4 Nov 2016 13:33:13 -0500 Subject: power: supply: bq27xxx_battery: Fix register map for BQ27510 and BQ27520 The BQ27510 and BQ27520 use a slightly different register map than the BQ27500, add a new type enum and add these gauges to it. Fixes: d74534c27775 ("power: bq27xxx_battery: Add support for additional bq27xxx family devices") Based-on-patch-by: Kenneth R. Crudup Signed-off-by: Andrew F. Davis Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e30deb046156..bed9557b69e7 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -4,7 +4,8 @@ enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ - BQ27500, /* bq27500, bq27510, bq27520 */ + BQ27500, /* bq27500 */ + BQ27510, /* bq27510, bq27520 */ BQ27530, /* bq27530, bq27531 */ BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ BQ27545, /* bq27545 */ -- cgit From afe06efdf07c12fd9370d5cce5383398cedf6c90 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Tue, 22 Nov 2016 12:23:53 -0800 Subject: sched: Extend scheduler's asym packing We generalize the scheduler's asym packing to provide an ordering of the cpu beyond just the cpu number. This allows the use of the ASYM_PACKING scheduler machinery to move loads to preferred CPU in a sched domain. The preference is defined with the cpu priority given by arch_asym_cpu_priority(cpu). We also record the most preferred cpu in a sched group when we build the cpu's capacity for fast lookup of preferred cpu during load balancing. Co-developed-by: Peter Zijlstra (Intel) Signed-off-by: Tim Chen Acked-by: Peter Zijlstra (Intel) Cc: linux-pm@vger.kernel.org Cc: jolsa@redhat.com Cc: rjw@rjwysocki.net Cc: linux-acpi@vger.kernel.org Cc: Srinivas Pandruvada Cc: bp@suse.de Link: http://lkml.kernel.org/r/0e73ae12737dfaafa46c07066cc7c5d3f1675e46.1479844244.git.tim.c.chen@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 19abba04ceca..fe9a499d5aa4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1077,6 +1077,8 @@ static inline int cpu_numa_flags(void) } #endif +extern int arch_asym_cpu_priority(int cpu); + struct sched_domain_attr { int relax_domain_level; }; -- cgit From 2027cbcf497579cb3bd71ed4173ae9b950aa09a3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 22 Nov 2016 18:31:49 +0100 Subject: driver core: add CLASS_ATTR_WO() Some class subsystems are open-coding CLASS_ATTR_WO because the driver core never provided it. Add the macro to device.h so that we can go around and fix up the individual subsystems as needed. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 49f453892ca5..4264caacebb9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -465,6 +465,8 @@ struct class_attribute { struct class_attribute class_attr_##_name = __ATTR_RW(_name) #define CLASS_ATTR_RO(_name) \ struct class_attribute class_attr_##_name = __ATTR_RO(_name) +#define CLASS_ATTR_WO(_name) \ + struct class_attribute class_attr_##_name = __ATTR_WO(_name) extern int __must_check class_create_file_ns(struct class *class, const struct class_attribute *attr, -- cgit From 4d5538f5882a6b67eefbab0f0a3a67ce811621aa Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 13 Oct 2016 14:10:40 +0200 Subject: i2c: use an IRQ to report Host Notify events, not alert The current SMBus Host Notify implementation relies on .alert() to relay its notifications. However, the use cases where SMBus Host Notify is needed currently is to signal data ready on touchpads. This is closer to an IRQ than a custom API through .alert(). Given that the 2 touchpad manufacturers (Synaptics and Elan) that use SMBus Host Notify don't put any data in the SMBus payload, the concept actually matches one to one. Benefits are multiple: - simpler code and API: the client will just have an IRQ, and nothing needs to be added in the adapter beside internally enabling it. - no more specific workqueue, the threading is handled by IRQ core directly (when required) - no more races when removing the device (the drivers are already required to disable irq on remove) - simpler handling for drivers: use plain regular IRQs - no more dependency on i2c-smbus for i2c-i801 (and any other adapter) - the IRQ domain is created automatically when the adapter exports the Host Notify capability - the IRQ are assign only if ACPI, OF and the caller did not assign one already - the domain is automatically destroyed on remove - fewer lines of code (minus 20, yeah!) Signed-off-by: Benjamin Tissoires Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 27 --------------------------- include/linux/i2c.h | 4 ++++ 2 files changed, 4 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index c2e3324f9468..a1385023a29b 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -50,31 +50,4 @@ struct i2c_client *i2c_setup_smbus_alert(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); -/** - * smbus_host_notify - internal structure used by the Host Notify mechanism. - * @adapter: the I2C adapter associated with this struct - * @work: worker used to schedule the IRQ in the slave device - * @lock: spinlock to check if a notification is already pending - * @pending: flag set when a notification is pending (any new notification will - * be rejected if pending is true) - * @payload: the actual payload of the Host Notify event - * @addr: the address of the slave device which raised the notification - * - * This struct needs to be allocated by i2c_setup_smbus_host_notify() and does - * not need to be freed. Internally, i2c_setup_smbus_host_notify() uses a - * managed resource to clean this up when the adapter get released. - */ -struct smbus_host_notify { - struct i2c_adapter *adapter; - struct work_struct work; - spinlock_t lock; - bool pending; - u16 payload; - u8 addr; -}; - -struct smbus_host_notify *i2c_setup_smbus_host_notify(struct i2c_adapter *adap); -int i2c_handle_smbus_host_notify(struct smbus_host_notify *host_notify, - unsigned short addr, unsigned int data); - #endif /* _LINUX_I2C_SMBUS_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 82cf90945bb8..b2109c522dec 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -30,6 +30,7 @@ #include /* for struct device */ #include /* for completion */ #include +#include /* for Host Notify IRQ */ #include /* for struct device_node */ #include /* for swab16 */ #include @@ -575,6 +576,8 @@ struct i2c_adapter { struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; + + struct irq_domain *host_notify_domain; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) @@ -747,6 +750,7 @@ static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) return (msg->addr << 1) | (msg->flags & I2C_M_RD ? 1 : 0); } +int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); /** * module_i2c_driver() - Helper macro for registering a modular I2C driver * @__i2c_driver: i2c_driver struct -- cgit From 8b533a0eeefc5861cea57163dd3cec2798a77f6c Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 22 Nov 2016 12:23:59 -0800 Subject: acpi/bus: Set _OSC for diverse core support Set the OSC_SB_CPC_DIVERSE_HIGH_SUPPORT (bit 12) to enable diverse core support. This is required to enable the BIOS support of the Intel Turbo Boost Max Technology 3.0 feature. Signed-off-by: Srinivas Pandruvada Signed-off-by: Tim Chen Cc: linux-pm@vger.kernel.org Cc: peterz@infradead.org Cc: jolsa@redhat.com Cc: rjw@rjwysocki.net Cc: linux-acpi@vger.kernel.org Cc: bp@suse.de Link: http://lkml.kernel.org/r/a023623a727e86040a1715797055f6402caefd7e.1479844244.git.tim.c.chen@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 61a3d90f32b3..051023756520 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -469,6 +469,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 +#define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; -- cgit From d06f78c4232d6a84b50839f61d9d7fbb222d8118 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 22 Nov 2016 11:40:55 -0800 Subject: net: phy: broadcom: Add support code for downshift/Wirespeed Broadcom's Wirespeed feature allows us to configure how auto-negotiation should behave with fewer working pairs of wires on a cable. Add support code for retrieving and setting such downshift counters using the recently added ethtool downshift tunables. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 848dc508ef57..f9f8aaf9c943 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -114,6 +114,7 @@ #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 #define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN (1 << 8) +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN (1 << 4) #define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 @@ -130,6 +131,7 @@ #define BCM_LED_SRC_INTR 0x6 #define BCM_LED_SRC_QUALITY 0x7 #define BCM_LED_SRC_RCVLED 0x8 +#define BCM_LED_SRC_WIRESPEED 0x9 #define BCM_LED_SRC_MULTICOLOR1 0xa #define BCM_LED_SRC_OPENSHORT 0xb #define BCM_LED_SRC_OFF 0xe /* Tied high */ @@ -141,6 +143,14 @@ * Shadow values go into bits [14:10] of register 0x1c to select a shadow * register to access. */ + +/* 00100: Reserved control register 2 */ +#define BCM54XX_SHD_SCR2 0x04 +#define BCM54XX_SHD_SCR2_WSPD_RTRY_DIS 0x100 +#define BCM54XX_SHD_SCR2_WSPD_RTRY_LMT_SHIFT 2 +#define BCM54XX_SHD_SCR2_WSPD_RTRY_LMT_OFFSET 2 +#define BCM54XX_SHD_SCR2_WSPD_RTRY_LMT_MASK 0x7 + /* 00101: Spare Control Register 3 */ #define BCM54XX_SHD_SCR3 0x05 #define BCM54XX_SHD_SCR3_DEF_CLK125 0x0001 -- cgit From 3df5b3c67546fb05266766b6abaf71563f82efe4 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 22 Nov 2016 23:09:54 +0200 Subject: net: Add net-device param to the get offloaded stats ndo Some drivers would need to check few internal matters for that. To be used in downstream mlx5 commit. Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e84800edd249..ae32a27523f9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,7 +925,7 @@ struct netdev_xdp { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * bool (*ndo_has_offload_stats)(int attr_id) + * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id) * Return true if this device supports offload stats of this attr_id. * * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, @@ -1165,7 +1165,7 @@ struct net_device_ops { struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); - bool (*ndo_has_offload_stats)(int attr_id); + bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, void *attr_data); -- cgit From 34e4e99078667d30f71a50c1e5181e4270e9d8bb Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 22 Nov 2016 23:09:58 +0200 Subject: net/mlx5: Enable to query min inline for a specific vport Also move the inline capablities enum to a shared header vport.h Signed-off-by: Roi Dayan Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/vport.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 451b0bde9083..ec35157ea725 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,6 +36,12 @@ #include #include +enum { + MLX5_CAP_INLINE_MODE_L2, + MLX5_CAP_INLINE_MODE_VPORT_CONTEXT, + MLX5_CAP_INLINE_MODE_NOT_REQUIRED, +}; + u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); @@ -43,8 +49,8 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); -void mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, - u8 *min_inline); +int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, + u16 vport, u8 *min_inline); int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 min_inline); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, -- cgit From d245b3f9bd36f02fd641cba9931d8b4c77126e74 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 24 Nov 2016 10:57:25 +0100 Subject: gpio: simplify adding threaded interrupts This tries to simplify the use of CONFIG_GPIOLIB_IRQCHIP when using threaded interrupts: add a new call gpiochip_irqchip_add_nested() to indicate that we're dealing with a nested rather than a chained irqchip, then create a separate gpiochip_set_nested_irqchip() to mirror the gpiochip_set_chained_irqchip() call to connect the parent and child interrupts. In the nested case gpiochip_set_nested_irqchip() does nothing more than call irq_set_parent() on each valid child interrupt, which has little semantic effect in the kernel, but this is probably still formally correct. Update all drivers using nested interrupts to use gpiochip_irqchip_add_nested() so we can now see clearly which these users are. The DLN2 driver can drop its specific hack with .irq_not_threaded as we now recognize whether a chip is threaded or not from its use of gpiochip_irqchip_add_nested() signature rather than from inspecting .can_sleep. We rename the .irq_parent to .irq_chained_parent since this parent IRQ is only really kept around for the chained interrupt handlers. Cc: Lars Poeschel Cc: Octavian Purdila Cc: Daniel Baluta Cc: Bin Gao Cc: Mika Westerberg Cc: Ajay Thomas Cc: Semen Protsenko Cc: Alexander Stein Cc: Phil Reid Cc: Bartosz Golaszewski Cc: Patrice Chotard Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 24e2cc56beb1..4b20238e7570 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -82,8 +82,6 @@ enum single_ended_mode { * implies that if the chip supports IRQs, these IRQs need to be threaded * as the chip access may sleep when e.g. reading out the IRQ status * registers. - * @irq_not_threaded: flag must be set if @can_sleep is set but the - * IRQs don't need to be threaded * @read_reg: reader function for generic GPIO * @write_reg: writer function for generic GPIO * @pin2mask: some generic GPIO controllers work with the big-endian bits @@ -109,8 +107,10 @@ enum single_ended_mode { * for GPIO IRQs, provided by GPIO driver * @irq_default_type: default IRQ triggering type applied during GPIO driver * initialization, provided by GPIO driver - * @irq_parent: GPIO IRQ chip parent/bank linux irq number, - * provided by GPIO driver + * @irq_chained_parent: GPIO IRQ chip parent/bank linux irq number, + * provided by GPIO driver for chained interrupt (not for nested + * interrupts). + * @irq_nested: True if set the interrupt handling is nested. * @irq_need_valid_mask: If set core allocates @irq_valid_mask with all * bits set to one * @irq_valid_mask: If not %NULL holds bitmask of GPIOs which are valid to @@ -166,7 +166,6 @@ struct gpio_chip { u16 ngpio; const char *const *names; bool can_sleep; - bool irq_not_threaded; #if IS_ENABLED(CONFIG_GPIO_GENERIC) unsigned long (*read_reg)(void __iomem *reg); @@ -192,7 +191,8 @@ struct gpio_chip { unsigned int irq_base; irq_flow_handler_t irq_handler; unsigned int irq_default_type; - int irq_parent; + int irq_chained_parent; + bool irq_nested; bool irq_need_valid_mask; unsigned long *irq_valid_mask; struct lock_class_key *lock_key; @@ -270,24 +270,40 @@ void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip, int parent_irq, irq_flow_handler_t parent_handler); +void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + int parent_irq); + int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, unsigned int type, + bool nested, struct lock_class_key *lock_key); +/* FIXME: I assume threaded IRQchips do not have the lockdep problem */ +static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq, + handler, type, true, NULL); +} + #ifdef CONFIG_LOCKDEP #define gpiochip_irqchip_add(...) \ ( \ ({ \ static struct lock_class_key _key; \ - _gpiochip_irqchip_add(__VA_ARGS__, &_key); \ + _gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \ }) \ ) #else #define gpiochip_irqchip_add(...) \ - _gpiochip_irqchip_add(__VA_ARGS__, NULL) + _gpiochip_irqchip_add(__VA_ARGS__, false, NULL) #endif #endif /* CONFIG_GPIOLIB_IRQCHIP */ -- cgit From 3c62be17d4f562f43fe1d03b48194399caa35aa5 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 6 Oct 2016 19:02:05 -0700 Subject: f2fs: support multiple devices This patch implements multiple devices support for f2fs. Given multiple devices by mkfs.f2fs, f2fs shows them entirely as one big volume under one f2fs instance. Internal block management is very simple, but we will modify block allocation and background GC policy to boost IO speed by exploiting them accoording to each device speed. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 422630b8e588..cea41a124a80 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -52,10 +52,17 @@ #define VERSION_LEN 256 #define MAX_VOLUME_NAME 512 +#define MAX_PATH_LEN 64 +#define MAX_DEVICES 8 /* * For superblock */ +struct f2fs_device { + __u8 path[MAX_PATH_LEN]; + __le32 total_segments; +} __packed; + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -94,7 +101,8 @@ struct f2fs_super_block { __le32 feature; /* defined features */ __u8 encryption_level; /* versioning level for encryption */ __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ - __u8 reserved[871]; /* valid reserved region */ + struct f2fs_device devs[MAX_DEVICES]; /* device list */ + __u8 reserved[327]; /* valid reserved region */ } __packed; /* -- cgit From 3007098494bec614fb55dee7bc0410bb7db5ad18 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 23 Nov 2016 16:52:26 +0100 Subject: cgroup: add support for eBPF programs This patch adds two sets of eBPF program pointers to struct cgroup. One for such that are directly pinned to a cgroup, and one for such that are effective for it. To illustrate the logic behind that, assume the following example cgroup hierarchy. A - B - C \ D - E If only B has a program attached, it will be effective for B, C, D and E. If D then attaches a program itself, that will be effective for both D and E, and the program in B will only affect B and C. Only one program of a given type is effective for a cgroup. Attaching and detaching programs will be done through the bpf(2) syscall. For now, ingress and egress inet socket filtering are the only supported use-cases. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 79 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/cgroup-defs.h | 4 +++ 2 files changed, 83 insertions(+) create mode 100644 include/linux/bpf-cgroup.h (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h new file mode 100644 index 000000000000..ec80d0c0953e --- /dev/null +++ b/include/linux/bpf-cgroup.h @@ -0,0 +1,79 @@ +#ifndef _BPF_CGROUP_H +#define _BPF_CGROUP_H + +#include +#include +#include + +struct sock; +struct cgroup; +struct sk_buff; + +#ifdef CONFIG_CGROUP_BPF + +extern struct static_key_false cgroup_bpf_enabled_key; +#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) + +struct cgroup_bpf { + /* + * Store two sets of bpf_prog pointers, one for programs that are + * pinned directly to this cgroup, and one for those that are effective + * when this cgroup is accessed. + */ + struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; + struct bpf_prog *effective[MAX_BPF_ATTACH_TYPE]; +}; + +void cgroup_bpf_put(struct cgroup *cgrp); +void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); + +void __cgroup_bpf_update(struct cgroup *cgrp, + struct cgroup *parent, + struct bpf_prog *prog, + enum bpf_attach_type type); + +/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ +void cgroup_bpf_update(struct cgroup *cgrp, + struct bpf_prog *prog, + enum bpf_attach_type type); + +int __cgroup_bpf_run_filter(struct sock *sk, + struct sk_buff *skb, + enum bpf_attach_type type); + +/* Wrappers for __cgroup_bpf_run_filter() guarded by cgroup_bpf_enabled. */ +#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter(sk, skb, \ + BPF_CGROUP_INET_INGRESS); \ + \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ + typeof(sk) __sk = sk_to_full_sk(sk); \ + if (sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter(__sk, skb, \ + BPF_CGROUP_INET_EGRESS); \ + } \ + __ret; \ +}) + +#else + +struct cgroup_bpf {}; +static inline void cgroup_bpf_put(struct cgroup *cgrp) {} +static inline void cgroup_bpf_inherit(struct cgroup *cgrp, + struct cgroup *parent) {} + +#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) + +#endif /* CONFIG_CGROUP_BPF */ + +#endif /* _BPF_CGROUP_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 5b17de62c962..861b4677fc5b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -300,6 +301,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to store eBPF programs */ + struct cgroup_bpf bpf; + /* ids of the ancestors at each level including self */ int ancestor_ids[]; }; -- cgit From 7fd8329ba502ef76dd91db561c7aed696b2c7720 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 21 Sep 2016 13:47:22 +0200 Subject: taint/module: Clean up global and module taint flags handling The commit 66cc69e34e86a231 ("Fix: module signature vs tracepoints: add new TAINT_UNSIGNED_MODULE") updated module_taint_flags() to potentially print one more character. But it did not increase the size of the corresponding buffers in m_show() and print_modules(). We have recently done the same mistake when adding a taint flag for livepatching, see https://lkml.kernel.org/r/cfba2c823bb984690b73572aaae1db596b54a082.1472137475.git.jpoimboe@redhat.com Also struct module uses an incompatible type for mod-taints flags. It survived from the commit 2bc2d61a9638dab670d ("[PATCH] list module taint flags in Oops/panic"). There was used "int" for the global taint flags at these times. But only the global tain flags was later changed to "unsigned long" by the commit 25ddbb18aae33ad2 ("Make the taint flags reliable"). This patch defines TAINT_FLAGS_COUNT that can be used to create arrays and buffers of the right size. Note that we could not use enum because the taint flag indexes are used also in assembly code. Then it reworks the table that describes the taint flags. The TAINT_* numbers can be used as the index. Instead, we add information if the taint flag is also shown per-module. Finally, it uses "unsigned long", bit operations, and the updated taint_flags table also for mod->taints. It is not optimal because only few taint flags can be printed by module_taint_flags(). But better be on the safe side. IMHO, it is not worth the optimization and this is a good compromise. Signed-off-by: Petr Mladek Link: http://lkml.kernel.org/r/1474458442-21581-1-git-send-email-pmladek@suse.com [jeyu@redhat.com: fix broken lkml link in changelog] Signed-off-by: Jessica Yu --- include/linux/kernel.h | 9 +++++++++ include/linux/module.h | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc6ed52a39b9..441def77246d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -506,6 +506,15 @@ extern enum system_states { #define TAINT_UNSIGNED_MODULE 13 #define TAINT_SOFTLOCKUP 14 #define TAINT_LIVEPATCH 15 +#define TAINT_FLAGS_COUNT 16 + +struct taint_flag { + char true; /* character printed when tainted */ + char false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ +}; + +extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] diff --git a/include/linux/module.h b/include/linux/module.h index 0c3207d26ac0..f6ee569c62bb 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -399,7 +399,7 @@ struct module { /* Arch-specific module values */ struct mod_arch_specific arch; - unsigned int taints; /* same bits as kernel:tainted */ + unsigned long taints; /* same bits as kernel:taint_flags */ #ifdef CONFIG_GENERIC_BUG /* Support for BUG */ -- cgit From c714965f580accdb6715cb28285eeccea18dafdb Mon Sep 17 00:00:00 2001 From: Anson Jacob Date: Wed, 19 Oct 2016 19:12:18 -0400 Subject: module: remove trailing whitespace Fix checkpatch.pl warning: ERROR: trailing whitespace Signed-off-by: Anson Jacob Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f6ee569c62bb..7c84273d60b9 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -412,7 +412,7 @@ struct module { /* Protected by RCU and/or module_mutex: use rcu_dereference() */ struct mod_kallsyms *kallsyms; struct mod_kallsyms core_kallsyms; - + /* Section attributes */ struct module_sect_attrs *sect_attrs; -- cgit From 5a717f4f8f2830f297b5511022481bdc27b9d576 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 24 Nov 2016 07:04:08 +0200 Subject: netdevice: fix sparse warning for HARD_TX_LOCK sparse warns about context imbalance in any code that uses HARD_TX_LOCK/UNLOCK - this is because it's unable to determine that flags don't change so lock and unlock are paired. Seems easy enough to fix by adding __acquire/__release calls. With this patch af_packet.c is now sparse-clean, Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ff57cd2eba3b..4ffcd874cc20 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3462,6 +3462,17 @@ static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) txq->xmit_lock_owner = cpu; } +static inline bool __netif_tx_acquire(struct netdev_queue *txq) +{ + __acquire(&txq->_xmit_lock); + return true; +} + +static inline void __netif_tx_release(struct netdev_queue *txq) +{ + __release(&txq->_xmit_lock); +} + static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); @@ -3563,17 +3574,21 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) #define HARD_TX_LOCK(dev, txq, cpu) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_lock(txq, cpu); \ + } else { \ + __netif_tx_acquire(txq); \ } \ } #define HARD_TX_TRYLOCK(dev, txq) \ (((dev->features & NETIF_F_LLTX) == 0) ? \ __netif_tx_trylock(txq) : \ - true ) + __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ + } else { \ + __netif_tx_release(txq); \ } \ } -- cgit From 39290b389ea2654f9190e3b48c57d27b24def83e Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Mon, 14 Nov 2016 15:15:05 +0900 Subject: module: extend 'rodata=off' boot cmdline parameter to module mappings The current "rodata=off" parameter disables read-only kernel mappings under CONFIG_DEBUG_RODATA: commit d2aa1acad22f ("mm/init: Add 'rodata=off' boot cmdline parameter to disable read-only kernel mappings") This patch is a logical extension to module mappings ie. read-only mappings at module loading can be disabled even if CONFIG_DEBUG_SET_MODULE_RONX (mainly for debug use). Please note, however, that it only affects RO/RW permissions, keeping NX set. This is the first step to make CONFIG_DEBUG_SET_MODULE_RONX mandatory (always-on) in the future as CONFIG_DEBUG_RODATA on x86 and arm64. Suggested-by: and Acked-by: Mark Rutland Signed-off-by: AKASHI Takahiro Reviewed-by: Kees Cook Acked-by: Rusty Russell Link: http://lkml.kernel.org/r/20161114061505.15238-1-takahiro.akashi@linaro.org Signed-off-by: Jessica Yu --- include/linux/init.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index e30104ceb86d..885c3e6d0f9d 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -126,6 +126,9 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); +#if defined(CONFIG_DEBUG_RODATA) || defined(CONFIG_DEBUG_SET_MODULE_RONX) +extern bool rodata_enabled; +#endif #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); #endif -- cgit From ec76d819d27040e418801d1a57bd3bdfde51019e Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Fri, 14 Oct 2016 11:53:19 +1100 Subject: KVM: Export kvm module parameter variables The kvm module has the parameters halt_poll_ns, halt_poll_ns_grow, and halt_poll_ns_shrink. Halt polling was recently added to the powerpc kvm-hv module and these parameters were essentially duplicated for that. There is no benefit to this duplication and it can lead to confusion when trying to tune halt polling. Thus move the definition of these variables to kvm_host.h and export them. This will allow the kvm-hv module to use the same module parameters by accessing these variables, which will be implemented in the next patch, meaning that they will no longer be duplicated. Signed-off-by: Suraj Jitindar Singh Signed-off-by: Paul Mackerras --- include/linux/kvm_host.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01c0b9cc3915..29b500a857d1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1107,6 +1107,10 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) extern bool kvm_rebooting; +extern unsigned int halt_poll_ns; +extern unsigned int halt_poll_ns_grow; +extern unsigned int halt_poll_ns_shrink; + struct kvm_device { struct kvm_device_ops *ops; struct kvm *kvm; -- cgit From 88575199cc65de99a156888629a68180c830eff2 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 26 Nov 2016 01:28:04 +0100 Subject: bpf: drop unnecessary context cast from BPF_PROG_RUN Since long already bpf_func is not only about struct sk_buff * as input anymore. Make it generic as void *, so that callers don't need to cast for it each time they call BPF_PROG_RUN(). Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1f09c521adfe..7f246a281435 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -408,8 +408,8 @@ struct bpf_prog { enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ - unsigned int (*bpf_func)(const struct sk_buff *skb, - const struct bpf_insn *filter); + unsigned int (*bpf_func)(const void *ctx, + const struct bpf_insn *insn); /* Instructions for interpreter */ union { struct sock_filter insns[0]; @@ -504,7 +504,7 @@ static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, u32 ret; rcu_read_lock(); - ret = BPF_PROG_RUN(prog, (void *)xdp); + ret = BPF_PROG_RUN(prog, xdp); rcu_read_unlock(); return ret; -- cgit From c491680f8f489926eebfdf2cd006767fc8bdaa49 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 26 Nov 2016 01:28:06 +0100 Subject: bpf: reuse dev_is_mac_header_xmit for redirect Commit dcf800344a91 ("net/sched: act_mirred: Refactor detection whether dev needs xmit at mac header") added dev_is_mac_header_xmit(); since it's also useful elsewhere, move it to if_arp.h and reuse it for BPF. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/if_arp.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index f563907ed776..3355efc89781 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -44,4 +44,20 @@ static inline int arp_hdr_len(struct net_device *dev) return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } + +static inline bool dev_is_mac_header_xmit(const struct net_device *dev) +{ + switch (dev->type) { + case ARPHRD_TUNNEL: + case ARPHRD_TUNNEL6: + case ARPHRD_SIT: + case ARPHRD_IPGRE: + case ARPHRD_VOID: + case ARPHRD_NONE: + return false; + default: + return true; + } +} + #endif /* _LINUX_IF_ARP_H */ -- cgit From 72d19459d7919f966594576bb042d15a451f27ea Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 25 Nov 2016 14:27:21 +0100 Subject: HID: input: rework HID_QUIRK_MULTI_INPUT The purpose of HID_QUIRK_MULTI_INPUT is to have an input device per report id. This is useful when the HID device presents several HID collections of different device types. The current implementation of hid-input creates one input node per id per type (input or output). This is problematic for the LEDs of a keyboard as they are often set through an output report. The current code creates one input node with all the keyboard keys, and one other with only the LEDs. To solve this, we use a two-passes way: - first, we initialize all input nodes and associate one per report id - then, we register all the input nodes Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index b2ec82712baa..596b9232c19e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -479,6 +479,7 @@ struct hid_input { struct list_head list; struct hid_report *report; struct input_dev *input; + bool registered; }; enum hid_type { -- cgit From 3a6a931dfb8e49a7377825b465d84e110fe89f68 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Sun, 27 Nov 2016 17:02:04 +0200 Subject: net/mlx5e: Support DCBX CEE API Add DCBX CEE API interface for ConnectX-4. Configurations are stored in a temporary structure and are applied to the card's firmware when the CEE's setall callback function is called. Note: priority group in CEE is equivalent to traffic class in ConnectX-4 hardware spec. bw allocation per priority in CEE is not supported because ConnectX-4 only supports bw allocation per traffic class. user priority in CEE does not have an equivalent term in ConnectX-4. Therefore, user priority to priority mapping in CEE is not supported. Signed-off-by: Huy Nguyen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index dde8c7ec5ff1..bdee439f8cf3 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -141,8 +141,12 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, int mlx5_max_tc(struct mlx5_core_dev *mdev); int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); +int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev, + u8 prio, u8 *tc); int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); +int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev, + u8 tc, u8 *bw_pct); int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, u8 *max_bw_value, u8 *max_bw_unit); -- cgit From 341c5ee2fb78420ffc441df36f93226be8069b0a Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Sun, 27 Nov 2016 17:02:06 +0200 Subject: net/mlx5: Add DCBX firmware commands support Add set/query commands for DCBX_PARAM register Signed-off-by: Huy Nguyen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 7 +++++++ include/linux/mlx5/port.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ae1f451e8f89..68b85efc3908 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -104,6 +104,8 @@ enum { enum { MLX5_REG_QETCR = 0x4005, MLX5_REG_QTCT = 0x400a, + MLX5_REG_DCBX_PARAM = 0x4020, + MLX5_REG_DCBX_APP = 0x4021, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, @@ -124,6 +126,11 @@ enum { MLX5_REG_MPCNT = 0x9051, }; +enum mlx5_dcbx_oper_mode { + MLX5E_DCBX_PARAM_VER_OPER_HOST = 0x0, + MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3, +}; + enum { MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0, MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index bdee439f8cf3..e527732fb31b 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -162,4 +162,6 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported, int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, u16 offset, u16 size, u8 *data); +int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); +int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); #endif /* __MLX5_PORT_H__ */ -- cgit From 50fcbbbb79de4b95a765ea170677c9810fcb9cee Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Wed, 12 Oct 2016 10:50:37 +0800 Subject: mmc: core: expose the capability of gpio card detect Add new helper API mmc_can_gpio_cd for slot-gpio to make host drivers know whether it supports gpio card detect. Signed-off-by: Shawn Lin Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/slot-gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 3945a8c9d3cb..a7972cd3bc14 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -29,5 +29,6 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, void mmc_gpio_set_cd_isr(struct mmc_host *host, irqreturn_t (*isr)(int irq, void *dev_id)); void mmc_gpiod_request_cd_irq(struct mmc_host *host); +bool mmc_can_gpio_cd(struct mmc_host *host); #endif -- cgit From 8e8b3f514c12a3b800bba8a7766c71139ad75b89 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 4 Nov 2016 11:05:19 +0100 Subject: mmc: core: use enum mmc_blk_status properly There were several instances of code using the enum mmc_blk_status by arbitrarily converting it to an int and throwing it around to different functions. This makes the code hard to understand to may give rise to strange errors. Especially the function prototype mmc_start_req() had to be modified to take a pointer to an enum mmc_blk_status and the function pointer .err_check() inside struct mmc_async_req needed to return an enum mmc_blk_status. In every case: instead of assigning the block layer error code to an int, use the enum, also change the signature of all functions actually passing this enum to use the enum. To make it possible to use the enum everywhere applicable, move it to so that all code actually using it can also see it. An interesting case was encountered in the MMC test code which did not return a enum mmc_blk_status at all in the .err_check function supposed to check whether asynchronous requests worked or not: instead it returned a normal -ERROR or even the test frameworks internal error codes. The test code would also pass on enum mmc_blk_status codes as error codes inside the test code instead of converting them to the local RESULT_* codes. I have tried to fix all instances properly and run some tests on the result. Cc: Chunyan Zhang Cc: Baolin Wang Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 12 ------------ include/linux/mmc/core.h | 15 ++++++++++++++- include/linux/mmc/host.h | 2 +- 3 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 73fad83acbcb..e49a3ff9d0e0 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -207,18 +207,6 @@ struct sdio_func_tuple; #define SDIO_MAX_FUNCS 7 -enum mmc_blk_status { - MMC_BLK_SUCCESS = 0, - MMC_BLK_PARTIAL, - MMC_BLK_CMD_ERR, - MMC_BLK_RETRY, - MMC_BLK_ABORT, - MMC_BLK_DATA_ERR, - MMC_BLK_ECC_ERR, - MMC_BLK_NOMEDIUM, - MMC_BLK_NEW_REQUEST, -}; - /* The number of MMC physical partitions. These consist of: * boot partitions (2), general purpose partitions (4) and * RPMB partition (1) in MMC v4.4. diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 2b953eb8ceae..0ce928b3ce90 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -15,6 +15,18 @@ struct request; struct mmc_data; struct mmc_request; +enum mmc_blk_status { + MMC_BLK_SUCCESS = 0, + MMC_BLK_PARTIAL, + MMC_BLK_CMD_ERR, + MMC_BLK_RETRY, + MMC_BLK_ABORT, + MMC_BLK_DATA_ERR, + MMC_BLK_ECC_ERR, + MMC_BLK_NOMEDIUM, + MMC_BLK_NEW_REQUEST, +}; + struct mmc_command { u32 opcode; u32 arg; @@ -150,7 +162,8 @@ struct mmc_async_req; extern int mmc_stop_bkops(struct mmc_card *); extern int mmc_read_bkops_status(struct mmc_card *); extern struct mmc_async_req *mmc_start_req(struct mmc_host *, - struct mmc_async_req *, int *); + struct mmc_async_req *, + enum mmc_blk_status *); extern int mmc_interrupt_hpi(struct mmc_card *); extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *); extern void mmc_wait_for_req_done(struct mmc_host *host, diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0b2439441cc8..5310f94be0ab 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -173,7 +173,7 @@ struct mmc_async_req { * Check error status of completed mmc request. * Returns 0 if success otherwise non zero. */ - int (*err_check) (struct mmc_card *, struct mmc_async_req *); + enum mmc_blk_status (*err_check)(struct mmc_card *, struct mmc_async_req *); }; /** -- cgit From 8185e51f358a8dd4801b67e8c66f03eb9eeaba75 Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Mon, 12 Sep 2016 10:15:06 -0400 Subject: mmc: tmio-mmc: add support for 32bit data port For the r7s72100 SOC, the DATA_PORT register was changed to 32-bits wide. Therefore a new flag has been created that will allow 32-bit reads/writes to the DATA_PORT register instead of 16-bit (because 16-bits accesses are not supported). Signed-off-by: Chris Brandt Reviewed-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 7a26286db895..fba44abd05ba 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -99,6 +99,11 @@ */ #define TMIO_MMC_SDIO_STATUS_QUIRK (1 << 8) +/* + * Some controllers have a 32-bit wide data port register + */ +#define TMIO_MMC_32BIT_DATA_PORT (1 << 9) + /* * Some controllers allows to set SDx actual clock */ -- cgit From c820af5f18ec248b3cb61a9a9ce47ef0f2e9ec63 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 3 Nov 2016 15:15:59 +0100 Subject: mmc: core: Add helper to see if a host can be retuned This is in preparation for restoring saved tuning parameters when resuming the TMIO driver. Signed-off-by: Simon Horman Acked-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 5310f94be0ab..68639295148d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -546,6 +546,11 @@ static inline void mmc_retune_recheck(struct mmc_host *host) host->retune_now = 1; } +static inline bool mmc_can_retune(struct mmc_host *host) +{ + return host->can_retune == 1; +} + void mmc_retune_pause(struct mmc_host *host); void mmc_retune_unpause(struct mmc_host *host); -- cgit From a4cc7eb4416fda59f18e744925ba3a347f7ecac5 Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Thu, 17 Nov 2016 16:40:38 +0900 Subject: mmc: dw_mmc: use the cookie's enum values for post/pre_req() This patch removed the meaningless value. Instead, use the cookie's enum values for executing correctly. Signed-off-by: Jaehoon Chung Tested-by: Heiko Stuebner Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index f5af2bd35e7f..15db6f83f53f 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -39,6 +39,12 @@ enum { EVENT_DATA_ERROR, }; +enum dw_mci_cookie { + COOKIE_UNMAPPED, + COOKIE_PRE_MAPPED, /* mapped by pre_req() of dwmmc */ + COOKIE_MAPPED, /* mapped by prepare_data() of dwmmc */ +}; + struct mmc_data; enum { -- cgit From d3c6aac3bdfe97b8b44db6a8aba59786cb9531dc Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 23 Nov 2016 11:02:24 +0100 Subject: mmc: delete is_first_req parameter from pre-request callback The void (*pre_req) callback in the struct mmc_host_ops vtable is passing an argument "is_first_req" indicating whether this is the first request or not. None of the in-kernel users use this parameter: instead, since they all just do variants of dma_map* they use the DMA cookie to indicate whether a pre* callback has already been done for a request when they decide how to handle it. Delete the parameter from the callback and all users, as it is just pointless cruft. Signed-off-by: Linus Walleij Acked-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 68639295148d..2a6418d0c343 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -93,8 +93,7 @@ struct mmc_host_ops { */ void (*post_req)(struct mmc_host *host, struct mmc_request *req, int err); - void (*pre_req)(struct mmc_host *host, struct mmc_request *req, - bool is_first_req); + void (*pre_req)(struct mmc_host *host, struct mmc_request *req); void (*request)(struct mmc_host *host, struct mmc_request *req); /* -- cgit From 03d640ae1f9b24b1d2a11f747143a1ecc0745019 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 25 Nov 2016 10:35:00 +0100 Subject: mmc: block: delete packed command support I've had it with this code now. The packed command support is a complex hurdle in the MMC/SD block layer, around 500+ lines of code which was introduced in 2013 in commit ce39f9d17c14 ("mmc: support packed write command for eMMC4.5 devices") commit abd9ac144947 ("mmc: add packed command feature of eMMC4.5") ...and since then it has been rotting. The original author of the code has disappeared from the community and the mail address is bouncing. For the code to be exercised the host must flag that it supports packed commands, so in mmc_blk_prep_packed_list() which is called for every single request, the following construction appears: u8 max_packed_rw = 0; if ((rq_data_dir(cur) == WRITE) && mmc_host_packed_wr(card->host)) max_packed_rw = card->ext_csd.max_packed_writes; if (max_packed_rw == 0) goto no_packed; This has the following logical deductions: - Only WRITE commands can really be packed, so the solution is only half-done: we support packed WRITE but not packed READ. The packed command support has not been finalized by supporting reads in three years! - mmc_host_packed_wr() is just a static inline that checks host->caps2 & MMC_CAP2_PACKED_WR. The problem with this is that NO upstream host sets this capability flag! No driver in the kernel is using it, and we can't test it. Packed command may be supported in out-of-tree code, but I doubt it. I doubt that the code is even working anymore due to other refactorings in the MMC block layer, who would notice if patches affecting it broke packed commands? No one. - There is no Device Tree binding or code to mark a host as supporting packed read or write commands, just this flag in caps2, so for sure there are not any DT systems using it either. It has other problems as well: mmc_blk_prep_packed_list() is speculatively picking requests out of the request queue with blk_fetch_request() making the MMC/SD stack harder to convert to the multiqueue block layer. By this we get rid of an obstacle. The way I see it this is just cruft littering the MMC/SD stack. Cc: Namjae Jeon Cc: Maya Erez Acked-by: Jaehoon Chung Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 2a6418d0c343..2ce32fefb41c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -494,11 +494,6 @@ static inline int mmc_host_uhs(struct mmc_host *host) MMC_CAP_UHS_DDR50); } -static inline int mmc_host_packed_wr(struct mmc_host *host) -{ - return host->caps2 & MMC_CAP2_PACKED_WR; -} - static inline int mmc_card_hs(struct mmc_card *card) { return card->host->ios.timing == MMC_TIMING_SD_HS || -- cgit From a6fc3b698130230a2342baacd7821eea0405154c Mon Sep 17 00:00:00 2001 From: yangbo lu Date: Wed, 9 Nov 2016 11:14:08 +0800 Subject: soc: fsl: add GUTS driver for QorIQ platforms The global utilities block controls power management, I/O device enabling, power-onreset(POR) configuration monitoring, alternate function selection for multiplexed signals,and clock control. This patch adds a driver to manage and access global utilities block. Initially only reading SVR and registering soc device are supported. Other guts accesses, such as reading RCW, should eventually be moved into this driver as well. Signed-off-by: Yangbo Lu Acked-by: Arnd Bergmann Signed-off-by: Ulf Hansson --- include/linux/fsl/guts.h | 125 +++++++++++++++++++++++++++++------------------ 1 file changed, 77 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index 649e9171a9b3..3efa3b861d44 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -29,83 +29,112 @@ * #ifdefs. */ struct ccsr_guts { - __be32 porpllsr; /* 0x.0000 - POR PLL Ratio Status Register */ - __be32 porbmsr; /* 0x.0004 - POR Boot Mode Status Register */ - __be32 porimpscr; /* 0x.0008 - POR I/O Impedance Status and Control Register */ - __be32 pordevsr; /* 0x.000c - POR I/O Device Status Register */ - __be32 pordbgmsr; /* 0x.0010 - POR Debug Mode Status Register */ - __be32 pordevsr2; /* 0x.0014 - POR device status register 2 */ + u32 porpllsr; /* 0x.0000 - POR PLL Ratio Status Register */ + u32 porbmsr; /* 0x.0004 - POR Boot Mode Status Register */ + u32 porimpscr; /* 0x.0008 - POR I/O Impedance Status and + * Control Register + */ + u32 pordevsr; /* 0x.000c - POR I/O Device Status Register */ + u32 pordbgmsr; /* 0x.0010 - POR Debug Mode Status Register */ + u32 pordevsr2; /* 0x.0014 - POR device status register 2 */ u8 res018[0x20 - 0x18]; - __be32 porcir; /* 0x.0020 - POR Configuration Information Register */ + u32 porcir; /* 0x.0020 - POR Configuration Information + * Register + */ u8 res024[0x30 - 0x24]; - __be32 gpiocr; /* 0x.0030 - GPIO Control Register */ + u32 gpiocr; /* 0x.0030 - GPIO Control Register */ u8 res034[0x40 - 0x34]; - __be32 gpoutdr; /* 0x.0040 - General-Purpose Output Data Register */ + u32 gpoutdr; /* 0x.0040 - General-Purpose Output Data + * Register + */ u8 res044[0x50 - 0x44]; - __be32 gpindr; /* 0x.0050 - General-Purpose Input Data Register */ + u32 gpindr; /* 0x.0050 - General-Purpose Input Data + * Register + */ u8 res054[0x60 - 0x54]; - __be32 pmuxcr; /* 0x.0060 - Alternate Function Signal Multiplex Control */ - __be32 pmuxcr2; /* 0x.0064 - Alternate function signal multiplex control 2 */ - __be32 dmuxcr; /* 0x.0068 - DMA Mux Control Register */ + u32 pmuxcr; /* 0x.0060 - Alternate Function Signal + * Multiplex Control + */ + u32 pmuxcr2; /* 0x.0064 - Alternate function signal + * multiplex control 2 + */ + u32 dmuxcr; /* 0x.0068 - DMA Mux Control Register */ u8 res06c[0x70 - 0x6c]; - __be32 devdisr; /* 0x.0070 - Device Disable Control */ + u32 devdisr; /* 0x.0070 - Device Disable Control */ #define CCSR_GUTS_DEVDISR_TB1 0x00001000 #define CCSR_GUTS_DEVDISR_TB0 0x00004000 - __be32 devdisr2; /* 0x.0074 - Device Disable Control 2 */ + u32 devdisr2; /* 0x.0074 - Device Disable Control 2 */ u8 res078[0x7c - 0x78]; - __be32 pmjcr; /* 0x.007c - 4 Power Management Jog Control Register */ - __be32 powmgtcsr; /* 0x.0080 - Power Management Status and Control Register */ - __be32 pmrccr; /* 0x.0084 - Power Management Reset Counter Configuration Register */ - __be32 pmpdccr; /* 0x.0088 - Power Management Power Down Counter Configuration Register */ - __be32 pmcdr; /* 0x.008c - 4Power management clock disable register */ - __be32 mcpsumr; /* 0x.0090 - Machine Check Summary Register */ - __be32 rstrscr; /* 0x.0094 - Reset Request Status and Control Register */ - __be32 ectrstcr; /* 0x.0098 - Exception reset control register */ - __be32 autorstsr; /* 0x.009c - Automatic reset status register */ - __be32 pvr; /* 0x.00a0 - Processor Version Register */ - __be32 svr; /* 0x.00a4 - System Version Register */ + u32 pmjcr; /* 0x.007c - 4 Power Management Jog Control + * Register + */ + u32 powmgtcsr; /* 0x.0080 - Power Management Status and + * Control Register + */ + u32 pmrccr; /* 0x.0084 - Power Management Reset Counter + * Configuration Register + */ + u32 pmpdccr; /* 0x.0088 - Power Management Power Down Counter + * Configuration Register + */ + u32 pmcdr; /* 0x.008c - 4Power management clock disable + * register + */ + u32 mcpsumr; /* 0x.0090 - Machine Check Summary Register */ + u32 rstrscr; /* 0x.0094 - Reset Request Status and + * Control Register + */ + u32 ectrstcr; /* 0x.0098 - Exception reset control register */ + u32 autorstsr; /* 0x.009c - Automatic reset status register */ + u32 pvr; /* 0x.00a0 - Processor Version Register */ + u32 svr; /* 0x.00a4 - System Version Register */ u8 res0a8[0xb0 - 0xa8]; - __be32 rstcr; /* 0x.00b0 - Reset Control Register */ + u32 rstcr; /* 0x.00b0 - Reset Control Register */ u8 res0b4[0xc0 - 0xb4]; - __be32 iovselsr; /* 0x.00c0 - I/O voltage select status register + u32 iovselsr; /* 0x.00c0 - I/O voltage select status register Called 'elbcvselcr' on 86xx SOCs */ u8 res0c4[0x100 - 0xc4]; - __be32 rcwsr[16]; /* 0x.0100 - Reset Control Word Status registers + u32 rcwsr[16]; /* 0x.0100 - Reset Control Word Status registers There are 16 registers */ u8 res140[0x224 - 0x140]; - __be32 iodelay1; /* 0x.0224 - IO delay control register 1 */ - __be32 iodelay2; /* 0x.0228 - IO delay control register 2 */ + u32 iodelay1; /* 0x.0224 - IO delay control register 1 */ + u32 iodelay2; /* 0x.0228 - IO delay control register 2 */ u8 res22c[0x604 - 0x22c]; - __be32 pamubypenr; /* 0x.604 - PAMU bypass enable register */ + u32 pamubypenr; /* 0x.604 - PAMU bypass enable register */ u8 res608[0x800 - 0x608]; - __be32 clkdvdr; /* 0x.0800 - Clock Divide Register */ + u32 clkdvdr; /* 0x.0800 - Clock Divide Register */ u8 res804[0x900 - 0x804]; - __be32 ircr; /* 0x.0900 - Infrared Control Register */ + u32 ircr; /* 0x.0900 - Infrared Control Register */ u8 res904[0x908 - 0x904]; - __be32 dmacr; /* 0x.0908 - DMA Control Register */ + u32 dmacr; /* 0x.0908 - DMA Control Register */ u8 res90c[0x914 - 0x90c]; - __be32 elbccr; /* 0x.0914 - eLBC Control Register */ + u32 elbccr; /* 0x.0914 - eLBC Control Register */ u8 res918[0xb20 - 0x918]; - __be32 ddr1clkdr; /* 0x.0b20 - DDR1 Clock Disable Register */ - __be32 ddr2clkdr; /* 0x.0b24 - DDR2 Clock Disable Register */ - __be32 ddrclkdr; /* 0x.0b28 - DDR Clock Disable Register */ + u32 ddr1clkdr; /* 0x.0b20 - DDR1 Clock Disable Register */ + u32 ddr2clkdr; /* 0x.0b24 - DDR2 Clock Disable Register */ + u32 ddrclkdr; /* 0x.0b28 - DDR Clock Disable Register */ u8 resb2c[0xe00 - 0xb2c]; - __be32 clkocr; /* 0x.0e00 - Clock Out Select Register */ + u32 clkocr; /* 0x.0e00 - Clock Out Select Register */ u8 rese04[0xe10 - 0xe04]; - __be32 ddrdllcr; /* 0x.0e10 - DDR DLL Control Register */ + u32 ddrdllcr; /* 0x.0e10 - DDR DLL Control Register */ u8 rese14[0xe20 - 0xe14]; - __be32 lbcdllcr; /* 0x.0e20 - LBC DLL Control Register */ - __be32 cpfor; /* 0x.0e24 - L2 charge pump fuse override register */ + u32 lbcdllcr; /* 0x.0e20 - LBC DLL Control Register */ + u32 cpfor; /* 0x.0e24 - L2 charge pump fuse override + * register + */ u8 rese28[0xf04 - 0xe28]; - __be32 srds1cr0; /* 0x.0f04 - SerDes1 Control Register 0 */ - __be32 srds1cr1; /* 0x.0f08 - SerDes1 Control Register 0 */ + u32 srds1cr0; /* 0x.0f04 - SerDes1 Control Register 0 */ + u32 srds1cr1; /* 0x.0f08 - SerDes1 Control Register 0 */ u8 resf0c[0xf2c - 0xf0c]; - __be32 itcr; /* 0x.0f2c - Internal transaction control register */ + u32 itcr; /* 0x.0f2c - Internal transaction control + * register + */ u8 resf30[0xf40 - 0xf30]; - __be32 srds2cr0; /* 0x.0f40 - SerDes2 Control Register 0 */ - __be32 srds2cr1; /* 0x.0f44 - SerDes2 Control Register 0 */ + u32 srds2cr0; /* 0x.0f40 - SerDes2 Control Register 0 */ + u32 srds2cr1; /* 0x.0f44 - SerDes2 Control Register 0 */ } __attribute__ ((packed)); +u32 fsl_guts_get_svr(void); /* Alternate function signal multiplex control */ #define MPC85xx_PMUXCR_QE(x) (0x8000 >> (x)) -- cgit From 937d3a0af521ece133a8716c1bf2d8044e15faa0 Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 15 Sep 2016 14:44:03 +0200 Subject: mfd: Add support for Allwinner SoCs ADC The Allwinner SoCs all have an ADC that can also act as a touchscreen controller and a thermal sensor. For now, only the ADC and the thermal sensor drivers are probed by the MFD, the touchscreen controller support will be added later. Signed-off-by: Quentin Schulz Acked-by: Maxime Ripard Acked-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/sun4i-gpadc.h | 94 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 include/linux/mfd/sun4i-gpadc.h (limited to 'include/linux') diff --git a/include/linux/mfd/sun4i-gpadc.h b/include/linux/mfd/sun4i-gpadc.h new file mode 100644 index 000000000000..d7a29f246d64 --- /dev/null +++ b/include/linux/mfd/sun4i-gpadc.h @@ -0,0 +1,94 @@ +/* Header of ADC MFD core driver for sunxi platforms + * + * Copyright (c) 2016 Quentin Schulz + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. + */ + +#ifndef __SUN4I_GPADC__H__ +#define __SUN4I_GPADC__H__ + +#define SUN4I_GPADC_CTRL0 0x00 + +#define SUN4I_GPADC_CTRL0_ADC_FIRST_DLY(x) ((GENMASK(7, 0) & (x)) << 24) +#define SUN4I_GPADC_CTRL0_ADC_FIRST_DLY_MODE BIT(23) +#define SUN4I_GPADC_CTRL0_ADC_CLK_SELECT BIT(22) +#define SUN4I_GPADC_CTRL0_ADC_CLK_DIVIDER(x) ((GENMASK(1, 0) & (x)) << 20) +#define SUN4I_GPADC_CTRL0_FS_DIV(x) ((GENMASK(3, 0) & (x)) << 16) +#define SUN4I_GPADC_CTRL0_T_ACQ(x) (GENMASK(15, 0) & (x)) + +#define SUN4I_GPADC_CTRL1 0x04 + +#define SUN4I_GPADC_CTRL1_STYLUS_UP_DEBOUNCE(x) ((GENMASK(7, 0) & (x)) << 12) +#define SUN4I_GPADC_CTRL1_STYLUS_UP_DEBOUNCE_EN BIT(9) +#define SUN4I_GPADC_CTRL1_TOUCH_PAN_CALI_EN BIT(6) +#define SUN4I_GPADC_CTRL1_TP_DUAL_EN BIT(5) +#define SUN4I_GPADC_CTRL1_TP_MODE_EN BIT(4) +#define SUN4I_GPADC_CTRL1_TP_ADC_SELECT BIT(3) +#define SUN4I_GPADC_CTRL1_ADC_CHAN_SELECT(x) (GENMASK(2, 0) & (x)) + +/* TP_CTRL1 bits for sun6i SOCs */ +#define SUN6I_GPADC_CTRL1_TOUCH_PAN_CALI_EN BIT(7) +#define SUN6I_GPADC_CTRL1_TP_DUAL_EN BIT(6) +#define SUN6I_GPADC_CTRL1_TP_MODE_EN BIT(5) +#define SUN6I_GPADC_CTRL1_TP_ADC_SELECT BIT(4) +#define SUN6I_GPADC_CTRL1_ADC_CHAN_SELECT(x) (GENMASK(3, 0) & BIT(x)) + +#define SUN4I_GPADC_CTRL2 0x08 + +#define SUN4I_GPADC_CTRL2_TP_SENSITIVE_ADJUST(x) ((GENMASK(3, 0) & (x)) << 28) +#define SUN4I_GPADC_CTRL2_TP_MODE_SELECT(x) ((GENMASK(1, 0) & (x)) << 26) +#define SUN4I_GPADC_CTRL2_PRE_MEA_EN BIT(24) +#define SUN4I_GPADC_CTRL2_PRE_MEA_THRE_CNT(x) (GENMASK(23, 0) & (x)) + +#define SUN4I_GPADC_CTRL3 0x0c + +#define SUN4I_GPADC_CTRL3_FILTER_EN BIT(2) +#define SUN4I_GPADC_CTRL3_FILTER_TYPE(x) (GENMASK(1, 0) & (x)) + +#define SUN4I_GPADC_TPR 0x18 + +#define SUN4I_GPADC_TPR_TEMP_ENABLE BIT(16) +#define SUN4I_GPADC_TPR_TEMP_PERIOD(x) (GENMASK(15, 0) & (x)) + +#define SUN4I_GPADC_INT_FIFOC 0x10 + +#define SUN4I_GPADC_INT_FIFOC_TEMP_IRQ_EN BIT(18) +#define SUN4I_GPADC_INT_FIFOC_TP_OVERRUN_IRQ_EN BIT(17) +#define SUN4I_GPADC_INT_FIFOC_TP_DATA_IRQ_EN BIT(16) +#define SUN4I_GPADC_INT_FIFOC_TP_DATA_XY_CHANGE BIT(13) +#define SUN4I_GPADC_INT_FIFOC_TP_FIFO_TRIG_LEVEL(x) ((GENMASK(4, 0) & (x)) << 8) +#define SUN4I_GPADC_INT_FIFOC_TP_DATA_DRQ_EN BIT(7) +#define SUN4I_GPADC_INT_FIFOC_TP_FIFO_FLUSH BIT(4) +#define SUN4I_GPADC_INT_FIFOC_TP_UP_IRQ_EN BIT(1) +#define SUN4I_GPADC_INT_FIFOC_TP_DOWN_IRQ_EN BIT(0) + +#define SUN4I_GPADC_INT_FIFOS 0x14 + +#define SUN4I_GPADC_INT_FIFOS_TEMP_DATA_PENDING BIT(18) +#define SUN4I_GPADC_INT_FIFOS_FIFO_OVERRUN_PENDING BIT(17) +#define SUN4I_GPADC_INT_FIFOS_FIFO_DATA_PENDING BIT(16) +#define SUN4I_GPADC_INT_FIFOS_TP_IDLE_FLG BIT(2) +#define SUN4I_GPADC_INT_FIFOS_TP_UP_PENDING BIT(1) +#define SUN4I_GPADC_INT_FIFOS_TP_DOWN_PENDING BIT(0) + +#define SUN4I_GPADC_CDAT 0x1c +#define SUN4I_GPADC_TEMP_DATA 0x20 +#define SUN4I_GPADC_DATA 0x24 + +#define SUN4I_GPADC_IRQ_FIFO_DATA 0 +#define SUN4I_GPADC_IRQ_TEMP_DATA 1 + +/* 10s delay before suspending the IP */ +#define SUN4I_GPADC_AUTOSUSPEND_DELAY 10000 + +struct sun4i_gpadc_dev { + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *regmap_irqc; + void __iomem *base; +}; + +#endif -- cgit From 054814b863b32a19a5094edb78a14c3c441f57dd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Sep 2016 13:35:30 +0200 Subject: mfd: tps65912: Move regmap config into core driver When building with extra warnings enabled, most files including linux/mfd/tps65912.h warn about a static variable defined in the header: include/linux/mfd/tps65912.h:331:35: warning: 'tps65912_regmap_config' defined but not used [-Wunused-const-variable=] We also duplicate the data structure between the i2c and spi front-end drivers. Moving it into the driver code avoids the warning and the duplication. Signed-off-by: Arnd Bergmann Signed-off-by: Lee Jones --- include/linux/mfd/tps65912.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 1a603701550e..b25d0297ba88 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -319,21 +319,7 @@ struct tps65912 { struct regmap_irq_chip_data *irq_data; }; -static const struct regmap_range tps65912_yes_ranges[] = { - regmap_reg_range(TPS65912_INT_STS, TPS65912_GPIO5), -}; - -static const struct regmap_access_table tps65912_volatile_table = { - .yes_ranges = tps65912_yes_ranges, - .n_yes_ranges = ARRAY_SIZE(tps65912_yes_ranges), -}; - -static const struct regmap_config tps65912_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .cache_type = REGCACHE_RBTREE, - .volatile_table = &tps65912_volatile_table, -}; +extern const struct regmap_config tps65912_regmap_config; int tps65912_device_init(struct tps65912 *tps); int tps65912_device_exit(struct tps65912 *tps); -- cgit From b2e2c85091710159b305735d557f4ef4695f5dff Mon Sep 17 00:00:00 2001 From: Jianhong Chen Date: Mon, 17 Oct 2016 17:03:10 +0800 Subject: mfd: rk808: RK818 uses DEV_OFF to power off supplies DEV_OFF and DEV_OFF_RST functions for RK808 are designed error that only DEV_OFF_RST can power off supplies. RK818 has been fixed this issue, so that DEV_OFF is used to power off supplies. Signed-off-by: Jianhong Chen Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 6d435a3c06bc..83701ef7d3c7 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -290,6 +290,7 @@ enum rk818_reg { #define SWITCH2_EN BIT(6) #define SWITCH1_EN BIT(5) #define DEV_OFF_RST BIT(3) +#define DEV_OFF BIT(0) #define VB_LO_ACT BIT(4) #define VB_LO_SEL_3500MV (7 << 0) -- cgit From 8ca9edc837932469b81b8b47ea43a074b6add970 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 27 Oct 2016 08:38:08 +0000 Subject: mfd: davinci_voicecodec: Tidyup header difinitions mach/hardware.h is needed on C source code side, not header. And struct davinci_vc is duplicated definition. Signed-off-by: Kuninori Morimoto Signed-off-by: Lee Jones --- include/linux/mfd/davinci_voicecodec.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h index 8e1cdbef3dad..2c0127cb06c5 100644 --- a/include/linux/mfd/davinci_voicecodec.h +++ b/include/linux/mfd/davinci_voicecodec.h @@ -28,8 +28,6 @@ #include #include -#include - struct regmap; /* @@ -99,8 +97,6 @@ struct davinci_vcif { dma_addr_t dma_rx_addr; }; -struct davinci_vc; - struct davinci_vc { /* Device data */ struct device *dev; -- cgit From 34d9030b5d06ec0072796b3ab6a3fa24e53ece3d Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 11 Nov 2016 11:29:52 +0800 Subject: mfd: axp20x: Add address extension registers for AXP806 regmap The AXP806 supports either master/standalone or slave mode. Slave mode allows sharing the serial bus, even with multiple AXP806 which all have the same hardware address. This is done with extra "serial interface address extension", or AXP806_BUS_ADDR_EXT, and "register address extension", or AXP806_REG_ADDR_EXT, registers. The former is read-only, with 1 bit customizable at the factory, and 1 bit depending on the state of an external pin. The latter is writable. Only when the these device addressing bits (in the upper 4 bits of the registers) match, will the device respond to operations on its other registers. Add these 2 registers to the regmap so we can access them. Signed-off-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 6349496f09fc..a4860bc9b73d 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -115,6 +115,8 @@ enum { #define AXP806_CLDO2_V_CTRL 0x25 #define AXP806_CLDO3_V_CTRL 0x26 #define AXP806_VREF_TEMP_WARN_L 0xf3 +#define AXP806_BUS_ADDR_EXT 0xfe +#define AXP806_REG_ADDR_EXT 0xff /* Interrupt */ #define AXP152_IRQ1_EN 0x40 -- cgit From c5e589a171728c9f5c587f9254ec6b343153c2ce Mon Sep 17 00:00:00 2001 From: Pierre-Hugues Husson Date: Sat, 5 Nov 2016 17:19:24 +0100 Subject: mfd: rn5t618: Add Ricoh RC5T619 PMIC support The Ricoh RN5T567 is from the same family as the Ricoh RN5T618 is, the differences are: + DCDC4/DCDC5 + LDO7-10 + Slightly different output voltage/currents + 32kHz Output + RTC + USB Charger detection Signed-off-by: Pierre-Hugues Husson Acked-by: Rob Herring Signed-off-by: Lee Jones --- include/linux/mfd/rn5t618.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h index cadc6543909d..e5a6cdeb77db 100644 --- a/include/linux/mfd/rn5t618.h +++ b/include/linux/mfd/rn5t618.h @@ -58,10 +58,13 @@ #define RN5T618_DC3CTL2 0x31 #define RN5T618_DC4CTL 0x32 #define RN5T618_DC4CTL2 0x33 +#define RN5T618_DC5CTL 0x34 +#define RN5T618_DC5CTL2 0x35 #define RN5T618_DC1DAC 0x36 #define RN5T618_DC2DAC 0x37 #define RN5T618_DC3DAC 0x38 #define RN5T618_DC4DAC 0x39 +#define RN5T618_DC5DAC 0x3a #define RN5T618_DC1DAC_SLP 0x3b #define RN5T618_DC2DAC_SLP 0x3c #define RN5T618_DC3DAC_SLP 0x3d @@ -77,6 +80,11 @@ #define RN5T618_LDO3DAC 0x4e #define RN5T618_LDO4DAC 0x4f #define RN5T618_LDO5DAC 0x50 +#define RN5T618_LDO6DAC 0x51 +#define RN5T618_LDO7DAC 0x52 +#define RN5T618_LDO8DAC 0x53 +#define RN5T618_LDO9DAC 0x54 +#define RN5T618_LDO10DAC 0x55 #define RN5T618_LDORTCDAC 0x56 #define RN5T618_LDORTC2DAC 0x57 #define RN5T618_LDO1DAC_SLP 0x58 @@ -231,6 +239,7 @@ enum { enum { RN5T567 = 0, RN5T618, + RC5T619, }; struct rn5t618 { -- cgit From 6d2c2b9f806a4ec81833af533d57395db856d5a3 Mon Sep 17 00:00:00 2001 From: Milo Kim Date: Tue, 15 Nov 2016 22:02:13 +0900 Subject: mfd: tps65217: Update register interrupt mask bits instead of writing operation TPS65217 interrupt register includes read/writeable mask bits with read-only status bits. (bit 4, 5, 6 are R/W, bit 0, 1, 2 are RO) And reserved bit is not required. Register update operation is preferred for disabling all interrupts during the device initialisation. Signed-off-by: Milo Kim Signed-off-by: Lee Jones --- include/linux/mfd/tps65217.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 4ccda8969639..dfa9f0d0ae2b 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -73,13 +73,14 @@ #define TPS65217_PPATH_AC_CURRENT_MASK 0x0C #define TPS65217_PPATH_USB_CURRENT_MASK 0x03 -#define TPS65217_INT_RESERVEDM BIT(7) #define TPS65217_INT_PBM BIT(6) #define TPS65217_INT_ACM BIT(5) #define TPS65217_INT_USBM BIT(4) #define TPS65217_INT_PBI BIT(2) #define TPS65217_INT_ACI BIT(1) #define TPS65217_INT_USBI BIT(0) +#define TPS65217_INT_MASK (TPS65217_INT_PBM | TPS65217_INT_ACM | \ + TPS65217_INT_USBM) #define TPS65217_CHGCONFIG0_TREG BIT(7) #define TPS65217_CHGCONFIG0_DPPM BIT(6) -- cgit From fa9170522b362aefb4fef58b5cbff45dbefec258 Mon Sep 17 00:00:00 2001 From: Milo Kim Date: Tue, 15 Nov 2016 22:02:14 +0900 Subject: mfd: tps65217: Make an interrupt handler simpler Rework the IRQ handler by using HW IRQ number and status bit. Each HW IRQ number is matched with TPS65217 register layout[*]. (USB IRQ number is 0, AC is 1, Push button is 2) When an interrupt is enabled, mask bit should be cleared (unmasked). If an interrupt is disabled, then mask bit should be set (masked). This mask value is updated into the TPS65217 register in irq_sync_unlock(). Mask bit and interrupt status bit can be handled with HW IRQ number. Eventually, additional IRQ data, 'tps65217_irqs[]' and the function, 'irq_to_tps65217_irq()' are not necessary. [*] TPS65217 interrupt register layout Bit7 6 5 4 3 2 1 0 ---------------------------------------------- | x | PBM | ACM | USBM | x | PBI | ACI | USBI PBM: Push button status change interrupt mask ACM: AC interrupt mask USBM: USB power status change interrupt mask PBI: Push button status change interrupt ACI: AC power status change interrupt USBI: USB power status change interrupt x: Not used Signed-off-by: Milo Kim Signed-off-by: Lee Jones --- include/linux/mfd/tps65217.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index dfa9f0d0ae2b..20d9dd3d74f1 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -79,6 +79,7 @@ #define TPS65217_INT_PBI BIT(2) #define TPS65217_INT_ACI BIT(1) #define TPS65217_INT_USBI BIT(0) +#define TPS65217_INT_SHIFT 4 #define TPS65217_INT_MASK (TPS65217_INT_PBM | TPS65217_INT_ACM | \ TPS65217_INT_USBM) -- cgit From b11283eb89b0697984cadee6016dabbcf511af27 Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Wed, 2 Nov 2016 11:54:03 +0000 Subject: irqchip/gic-v3-its: Change unsigned types for AArch32 compatibility Make sure that constants which are supposed to be applied on 64-bit data is actually unsigned long long, so they won't be truncated when used in 32-bit mode. Signed-off-by: Vladimir Murzin Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index b7e34313cdfe..5118d3a0c9ca 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -239,7 +239,7 @@ #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HWCOLLCNT_SHIFT 24 -#define GITS_CBASER_VALID (1UL << 63) +#define GITS_CBASER_VALID (1ULL << 63) #define GITS_CBASER_SHAREABILITY_SHIFT (10) #define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59) #define GITS_CBASER_OUTER_CACHEABILITY_SHIFT (53) @@ -265,7 +265,7 @@ #define GITS_BASER_NR_REGS 8 -#define GITS_BASER_VALID (1UL << 63) +#define GITS_BASER_VALID (1ULL << 63) #define GITS_BASER_INDIRECT (1ULL << 62) #define GITS_BASER_INNER_CACHEABILITY_SHIFT (59) -- cgit From bb8313b603eb8fd52de48a079bfcd72dcab2ef1e Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Mon, 28 Nov 2016 23:03:04 -0800 Subject: cpuidle: Allow enforcing deepest idle state selection When idle injection is used to cap power, we need to override the governor's choice of idle states. For this reason, make it possible the deepest idle state selection to be enforced by setting a flag on a given CPU to achieve the maximum potential power draw reduction. Signed-off-by: Jacob Pan [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 15deea449edc..da346f2817a8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -74,6 +74,7 @@ struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; + unsigned int use_deepest_state:1; unsigned int cpu; int last_residency; @@ -192,11 +193,12 @@ static inline struct cpuidle_driver *cpuidle_get_cpu_driver( static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #endif -#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) +#ifdef CONFIG_CPU_IDLE extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev); +extern void cpuidle_use_deepest_state(bool enable); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) @@ -204,6 +206,9 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } +static inline void cpuidle_use_deepest_state(bool enable) +{ +} #endif /* kernel/sched/idle.c */ -- cgit From c1de45ca831acee9b72c9320dde447edafadb43f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 28 Nov 2016 23:03:05 -0800 Subject: sched/idle: Add support for tasks that inject idle Idle injection drivers such as Intel powerclamp and ACPI PAD drivers use realtime tasks to take control of CPU then inject idle. There are two issues with this approach: 1. Low efficiency: injected idle task is treated as busy so sched ticks do not stop during injected idle period, the result of these unwanted wakeups can be ~20% loss in power savings. 2. Idle accounting: injected idle time is presented to user as busy. This patch addresses the issues by introducing a new PF_IDLE flag which allows any given task to be treated as idle task while the flag is set. Therefore, idle injection tasks can run through the normal flow of NOHZ idle enter/exit to get the correct accounting as well as tick stop when possible. The implication is that idle task is then no longer limited to PID == 0. Acked-by: Ingo Molnar Signed-off-by: Peter Zijlstra Signed-off-by: Jacob Pan Signed-off-by: Rafael J. Wysocki --- include/linux/cpu.h | 2 ++ include/linux/sched.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b886dc17f2f3..ac0efae38072 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -245,6 +245,8 @@ void arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); +void play_idle(unsigned long duration_ms); + #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); bool cpu_report_death(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..114c7fcb6af6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2254,6 +2254,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, /* * Per process flags */ +#define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ @@ -2609,7 +2610,7 @@ extern struct task_struct *idle_task(int cpu); */ static inline bool is_idle_task(const struct task_struct *p) { - return p->pid == 0; + return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); -- cgit From 027b25b26447aaf597c8b7729dd3b1fbebc6d5e8 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:33 +0000 Subject: ACPI: Add FWNODE_ACPI_STATIC fwnode type On systems booting with a device tree, every struct device is associated with a struct device_node, that provides its DT firmware representation. The device node can be used in generic kernel contexts (eg IRQ translation, IOMMU streamid mapping), to retrieve the properties associated with the device and carry out kernel operations accordingly. Owing to the 1:1 relationship between the device and its device_node, the device_node can also be used as a look-up token for the device (eg looking up a device through its device_node), to retrieve the device in kernel paths where the device_node is available. On systems booting with ACPI, the same abstraction provided by the device_node is required to provide look-up functionality. The struct acpi_device, that represents firmware objects in the ACPI namespace already includes a struct fwnode_handle of type FWNODE_ACPI as their member; the same abstraction is missing though for devices that are instantiated out of static ACPI tables entries (eg ARM SMMU devices). Add a new fwnode_handle type to associate devices created out of static ACPI table entries to the respective firmware components and create a simple ACPI core layer interface to dynamically allocate and free the corresponding firmware nodes so that kernel subsystems can use it to instantiate the nodes and associate them with the respective devices. Signed-off-by: Lorenzo Pieralisi Acked-by: Rafael J. Wysocki Reviewed-by: Hanjun Guo Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: "Rafael J. Wysocki" Signed-off-by: Will Deacon --- include/linux/acpi.h | 21 +++++++++++++++++++++ include/linux/fwnode.h | 3 ++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 61a3d90f32b3..996a29cdaccd 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -56,6 +56,27 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) +static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) +{ + struct fwnode_handle *fwnode; + + fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); + if (!fwnode) + return NULL; + + fwnode->type = FWNODE_ACPI_STATIC; + + return fwnode; +} + +static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) +{ + if (WARN_ON(!fwnode || fwnode->type != FWNODE_ACPI_STATIC)) + return; + + kfree(fwnode); +} + /** * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with * the PCI-defined class-code information diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 851671742790..8bd28ce6d76e 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -17,8 +17,9 @@ enum fwnode_type { FWNODE_OF, FWNODE_ACPI, FWNODE_ACPI_DATA, + FWNODE_ACPI_STATIC, FWNODE_PDATA, - FWNODE_IRQCHIP, + FWNODE_IRQCHIP }; struct fwnode_handle { -- cgit From 34ceea275f626ae624b55f2b388a07f806988a55 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:34 +0000 Subject: ACPI/IORT: Introduce linker section for IORT entries probing Since commit e647b532275b ("ACPI: Add early device probing infrastructure") the kernel has gained the infrastructure that allows adding linker script section entries to execute ACPI driver callbacks (ie probe routines) for all subsystems that register a table entry in the respective kernel section (eg clocksource, irqchip). Since ARM IOMMU devices data is described through IORT tables when booting with ACPI, the ARM IOMMU drivers must be made able to hook ACPI callback routines that are called to probe IORT entries and initialize the respective IOMMU devices. To avoid adding driver specific hooks into IORT table initialization code (breaking therefore code modularity - ie ACPI IORT code must be made aware of ARM SMMU drivers ACPI init callbacks), this patch adds code that allows ARM SMMU drivers to take advantage of the ACPI early probing infrastructure, so that they can add linker script section entries containing drivers callback to be executed on IORT tables detection. Since IORT nodes are differentiated by a type, the callback routines can easily parse the IORT table entries, check the IORT nodes and carry out some actions whenever the IORT node type associated with the driver specific callback is matched. Signed-off-by: Lorenzo Pieralisi Reviewed-by: Hanjun Guo Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: Tomasz Nowicki Cc: "Rafael J. Wysocki" Cc: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/acpi_iort.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 0e32dac8fd03..d16fddaf230e 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -39,4 +39,7 @@ static inline struct irq_domain *iort_get_device_domain(struct device *dev, { return NULL; } #endif +#define IORT_ACPI_DECLARE(name, table_id, fn) \ + ACPI_DECLARE_PROBE_ENTRY(iort, name, table_id, 0, NULL, 0, fn) + #endif /* __ACPI_IORT_H__ */ -- cgit From e4f10ffe4c9b500e545b874b816ffea5e8659b05 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:36 +0000 Subject: iommu: Make of_iommu_set/get_ops() DT agnostic The of_iommu_{set/get}_ops() API is used to associate a device tree node with a specific set of IOMMU operations. The same kernel interface is required on systems booting with ACPI, where devices are not associated with a device tree node, therefore the interface requires generalization. The struct device fwnode member represents the fwnode token associated with the device and the struct it points at is firmware specific; regardless, it is initialized on both ACPI and DT systems and makes an ideal candidate to use it to associate a set of IOMMU operations to a given device, through its struct device.fwnode member pointer, paving the way for representing per-device iommu_ops (ie an iommu instance associated with a device). Convert the DT specific of_iommu_{set/get}_ops() interface to use struct device.fwnode as a look-up token, making the interface usable on ACPI systems and rename the data structures and the registration API so that they are made to represent their usage more clearly. Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Reviewed-by: Robin Murphy Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: Will Deacon Cc: Hanjun Guo Cc: Robin Murphy Cc: Joerg Roedel Signed-off-by: Will Deacon --- include/linux/iommu.h | 14 ++++++++++++++ include/linux/of_iommu.h | 12 ++++++++++-- 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 436dc21318af..f2960e4de344 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -351,6 +351,9 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids); +void iommu_register_instance(struct fwnode_handle *fwnode, + const struct iommu_ops *ops); +const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode); #else /* CONFIG_IOMMU_API */ @@ -580,6 +583,17 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, return -ENODEV; } +static inline void iommu_register_instance(struct fwnode_handle *fwnode, + const struct iommu_ops *ops) +{ +} + +static inline +const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode) +{ + return NULL; +} + #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index e80b9c762a03..6a7fc5051099 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -31,8 +31,16 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, #endif /* CONFIG_OF_IOMMU */ -void of_iommu_set_ops(struct device_node *np, const struct iommu_ops *ops); -const struct iommu_ops *of_iommu_get_ops(struct device_node *np); +static inline void of_iommu_set_ops(struct device_node *np, + const struct iommu_ops *ops) +{ + iommu_register_instance(&np->fwnode, ops); +} + +static inline const struct iommu_ops *of_iommu_get_ops(struct device_node *np) +{ + return iommu_get_instance(&np->fwnode); +} extern struct of_device_id __iommu_of_table; -- cgit From d760a1baf20e067d3a063aa134834ddd3d183e2f Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:39 +0000 Subject: ACPI: Implement acpi_dma_configure On DT based systems, the of_dma_configure() API implements DMA configuration for a given device. On ACPI systems an API equivalent to of_dma_configure() is missing which implies that it is currently not possible to set-up DMA operations for devices through the ACPI generic kernel layer. This patch fills the gap by introducing acpi_dma_configure/deconfigure() calls that for now are just wrappers around arch_setup_dma_ops() and arch_teardown_dma_ops() and also updates ACPI and PCI core code to use the newly introduced acpi_dma_configure/acpi_dma_deconfigure functions. Since acpi_dma_configure() is used to configure DMA operations, the function initializes the dma/coherent_dma masks to sane default values if the current masks are uninitialized (also to keep the default values consistent with DT systems) to make sure the device has a complete default DMA set-up. The DMA range size passed to arch_setup_dma_ops() is sized according to the device coherent_dma_mask (starting at address 0x0), mirroring the DT probing path behaviour when a dma-ranges property is not provided for the device being probed; this changes the current arch_setup_dma_ops() call parameters in the ACPI probing case, but since arch_setup_dma_ops() is a NOP on all architectures but ARM/ARM64 this patch does not change the current kernel behaviour on them. Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas [pci] Acked-by: Rafael J. Wysocki Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: Bjorn Helgaas Cc: Robin Murphy Cc: Tomasz Nowicki Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Signed-off-by: Will Deacon --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 996a29cdaccd..8d15fc59719f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -765,6 +765,11 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) return DEV_DMA_NOT_SUPPORTED; } +static inline void acpi_dma_configure(struct device *dev, + enum dev_dma_attr attr) { } + +static inline void acpi_dma_deconfigure(struct device *dev) { } + #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) -- cgit From bdca0c077fc5c2a7bb405281263270070c67f917 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:40 +0000 Subject: ACPI/IORT: Add node match function Device drivers (eg ARM SMMU) need to know if a specific component is part of the IORT table, so that kernel data structures are not initialized at initcalls time if the respective component is not part of the IORT table. To this end, this patch adds a trivial function that allows detecting if a given IORT node type is present or not in the ACPI table, providing an ACPI IORT equivalent for of_find_matching_node(). Signed-off-by: Lorenzo Pieralisi Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Acked-by: Hanjun Guo Cc: Hanjun Guo Cc: Tomasz Nowicki Cc: "Rafael J. Wysocki" Signed-off-by: Will Deacon --- include/linux/acpi_iort.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index d16fddaf230e..17bb078073de 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -28,10 +28,12 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); +bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); #else static inline void acpi_iort_init(void) { } +static inline bool iort_node_match(u8 type) { return false; } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) { return req_id; } static inline struct irq_domain *iort_get_device_domain(struct device *dev, -- cgit From d6fcd3b149f3eab3b94cc107ca846bea8461cc2f Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:45 +0000 Subject: iommu/arm-smmu: Add IORT configuration In ACPI based systems, in order to be able to create platform devices and initialize them for ARM SMMU components, the IORT kernel implementation requires a set of static functions to be used by the IORT kernel layer to configure platform devices for ARM SMMU components. Add static configuration functions to the IORT kernel layer for the ARM SMMU components, so that the ARM SMMU driver can initialize its respective platform device by relying on the IORT kernel infrastructure and by adding a corresponding ACPI device early probe section entry. Signed-off-by: Lorenzo Pieralisi Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: Will Deacon Cc: Robin Murphy Cc: Joerg Roedel Signed-off-by: Will Deacon --- include/linux/acpi_iort.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 17bb078073de..79ba1bb50950 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -23,6 +23,9 @@ #include #include +#define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL) +#define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL) + int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); -- cgit From 643b8e4d86f8b1a62cf5cd9ea221e9bc0d531d18 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 21 Nov 2016 10:01:48 +0000 Subject: ACPI/IORT: Introduce iort_iommu_configure DT based systems have a generic kernel API to configure IOMMUs for devices (ie of_iommu_configure()). On ARM based ACPI systems, the of_iommu_configure() equivalent can be implemented atop ACPI IORT kernel API, with the corresponding functions to map device identifiers to IOMMUs and retrieve the corresponding IOMMU operations necessary for DMA operations set-up. By relying on the iommu_fwspec generic kernel infrastructure, implement the IORT based IOMMU configuration for ARM ACPI systems and hook it up in the ACPI kernel layer that implements DMA configuration for a device. Signed-off-by: Lorenzo Pieralisi Acked-by: Rafael J. Wysocki [ACPI core] Reviewed-by: Tomasz Nowicki Tested-by: Hanjun Guo Tested-by: Tomasz Nowicki Cc: Hanjun Guo Cc: Tomasz Nowicki Cc: "Rafael J. Wysocki" Signed-off-by: Will Deacon --- include/linux/acpi_iort.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 79ba1bb50950..dcb2b601e152 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -34,6 +34,8 @@ void acpi_iort_init(void); bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +/* IOMMU interface */ +const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } static inline bool iort_node_match(u8 type) { return false; } @@ -42,6 +44,10 @@ static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) static inline struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id) { return NULL; } +/* IOMMU interface */ +static inline +const struct iommu_ops *iort_iommu_configure(struct device *dev) +{ return NULL; } #endif #define IORT_ACPI_DECLARE(name, table_id, fn) \ -- cgit From ba58d1020a54933c6b087a3107661c8513556cb8 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Mon, 28 Nov 2016 14:35:19 -0800 Subject: timekeeping: Ignore the bogus sleep time if pm_trace is enabled Power management suspend/resume tracing (ab)uses the RTC to store suspend/resume information persistently. As a consequence the RTC value is clobbered when timekeeping is resumed and tries to inject the sleep time. Commit a4f8f6667f09 ("timekeeping: Cap array access in timekeeping_debug") plugged a out of bounds array access in the timekeeping debug code which was caused by the clobbered RTC value, but we still use the clobbered RTC value for sleep time injection into kernel timekeeping, which will result in random adjustments depending on the stored "hash" value. To prevent this keep track of the RTC clobbering and ignore the invalid RTC timestamp at resume. If the system resumed successfully clear the flag, which marks the RTC as unusable, warn the user about the RTC clobber and recommend to adjust the RTC with 'ntpdate' or 'rdate'. [jstultz: Fixed up pr_warn formating, and implemented suggestions from Ingo] [ tglx: Rewrote changelog ] Originally-from: Thomas Gleixner Signed-off-by: Chen Yu Signed-off-by: John Stultz Acked-by: Pavel Machek Acked-by: Thomas Gleixner Cc: Prarit Bhargava Cc: "Rafael J. Wysocki" Cc: Richard Cochran Cc: Xunlei Pang Cc: Len Brown Link: http://lkml.kernel.org/r/1480372524-15181-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/mc146818rtc.h | 1 + include/linux/pm-trace.h | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index a585b4b5fa0e..0661af17a758 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -16,6 +16,7 @@ #include /* register access macros */ #include #include +#include #ifdef __KERNEL__ #include /* spinlock_t */ diff --git a/include/linux/pm-trace.h b/include/linux/pm-trace.h index ecbde7a5548e..7b78793f07d7 100644 --- a/include/linux/pm-trace.h +++ b/include/linux/pm-trace.h @@ -1,11 +1,17 @@ #ifndef PM_TRACE_H #define PM_TRACE_H +#include #ifdef CONFIG_PM_TRACE #include -#include extern int pm_trace_enabled; +extern bool pm_trace_rtc_abused; + +static inline bool pm_trace_rtc_valid(void) +{ + return !pm_trace_rtc_abused; +} static inline int pm_trace_is_enabled(void) { @@ -24,6 +30,7 @@ extern int show_trace_dev_match(char *buf, size_t size); #else +static inline bool pm_trace_rtc_valid(void) { return true; } static inline int pm_trace_is_enabled(void) { return 0; } #define TRACE_DEVICE(dev) do { } while (0) -- cgit From ec4101e8903e318b9fd4e3bbf72b1eaba53c64e1 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Mon, 28 Nov 2016 14:35:20 -0800 Subject: timekeeping/clocksource_cyc2ns: Document intended range limitation The "cycles" argument should not be an absolute clocksource cycle value, as the implementation's arithmetic will overflow relatively easily with wide (64 bit) clocksource counters. For performance, the implementation is simple and fast, since the function is intended for only relatively small delta values of clocksource cycles. [jstultz: Fixed up to merge against HEAD & commit message tweaks, also included rewording suggestion by Ingo] Signed-off-by: Chris Metcalf Signed-off-by: John Stultz Cc: Prarit Bhargava Cc: Richard Cochran Link: http://lkml.kernel.org/r/1480372524-15181-4-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 08398182f56e..65602d395a52 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -169,7 +169,10 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) * - * Converts cycles to nanoseconds, using the given mult and shift. + * Converts clocksource cycles to nanoseconds, using the given @mult and @shift. + * The code is optimized for performance and is not intended to work + * with absolute clocksource cycles (as those will easily overflow), + * but is only intended to be used with relative (delta) clocksource cycles. * * XXX - This could use some mult_lxl_ll() asm optimization */ -- cgit From 948a5312f41658f7b76a598a139ef1f4dea09ca9 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Mon, 28 Nov 2016 14:35:22 -0800 Subject: timekeeping: Add a fast and NMI safe boot clock This boot clock can be used as a tracing clock and will account for suspend time. To keep it NMI safe since we're accessing from tracing, we're not using a separate timekeeper with updates to monotonic clock and boot offset protected with seqlocks. This has the following minor side effects: (1) Its possible that a timestamp be taken after the boot offset is updated but before the timekeeper is updated. If this happens, the new boot offset is added to the old timekeeping making the clock appear to update slightly earlier: CPU 0 CPU 1 timekeeping_inject_sleeptime64() __timekeeping_inject_sleeptime(tk, delta); timestamp(); timekeeping_update(tk, TK_CLEAR_NTP...); (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be partially updated. Since the tk->offs_boot update is a rare event, this should be a rare occurrence which postprocessing should be able to handle. Signed-off-by: Joel Fernandes Signed-off-by: John Stultz Reviewed-by: Thomas Gleixner Cc: Prarit Bhargava Cc: Richard Cochran Cc: Steven Rostedt Link: http://lkml.kernel.org/r/1480372524-15181-6-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/timekeeping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 09168c52ab64..361f8bf1429d 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -249,6 +249,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); +extern u64 ktime_get_boot_fast_ns(void); /* * Timespec interfaces utilizing the ktime based ones -- cgit From 3dc87dd048dc442bab633e85bfb96c893612d765 Mon Sep 17 00:00:00 2001 From: Matias Bjørling Date: Mon, 28 Nov 2016 22:38:53 +0100 Subject: nvme: lightnvm: attach lightnvm sysfs to nvme block device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously, LBA read and write were not supported in the lightnvm specification. Now that it supports it, lets use the traditional NVMe gendisk, and attach the lightnvm sysfs geometry export. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d190786e4ad8..fb2e601d674e 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -352,8 +352,6 @@ struct nvm_dev { /* Backend device */ struct request_queue *q; - struct device dev; - struct device *parent_dev; char name[DISK_NAME_LEN]; void *private_data; -- cgit From bb3149792e0ed52cf5f457dda4c9bf9c5bda1542 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:38:54 +0100 Subject: lightnvm: enable to send hint to erase command MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Erases might be subject to host hints. An example is multi-plane programming to erase blocks in parallel. Enable targets to specify this hint. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index fb2e601d674e..d87be02edc39 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -470,8 +470,7 @@ typedef int (nvmm_open_blk_fn)(struct nvm_dev *, struct nvm_block *); typedef int (nvmm_close_blk_fn)(struct nvm_dev *, struct nvm_block *); typedef void (nvmm_flush_blk_fn)(struct nvm_dev *, struct nvm_block *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); -typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, - unsigned long); +typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); typedef int (nvmm_reserve_lun)(struct nvm_dev *, int); @@ -537,8 +536,8 @@ extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, const struct ppa_addr *, int, int); extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); -extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int); -extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *); +extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int); +extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *, int); extern void nvm_end_io(struct nvm_rq *, int); extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int, void *, int); -- cgit From a24ba4644b7ae5af3cd2eb6992c237cb4548c45e Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:38:56 +0100 Subject: lightnvm: export set bad block table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bad blocks should be managed by block owners. This would be either targets for data blocks or sysblk for system blocks. In order to support this, export two functions: One to mark a block as an specific type (e.g., bad block) and another to update the bad block table on the device. Move bad block management to rrpc. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d87be02edc39..4480d1c6a1a5 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -423,6 +423,15 @@ static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev, return ppa; } +static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2) +{ + if (ppa_empty(ppa1) || ppa_empty(ppa2)) + return 0; + + return ((ppa1.g.ch == ppa2.g.ch) && (ppa1.g.lun == ppa2.g.lun) && + (ppa1.g.blk == ppa2.g.blk)); +} + static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg) { return dev->lptbl[slc_pg]; @@ -528,7 +537,9 @@ extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); -void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type); +extern void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type); +extern int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, + int nr_ppas, int type); extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); -- cgit From 402ab9a89d7b5bab08a5534027b39d80085ec19b Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:38:57 +0100 Subject: lightnvm: add ECC error codes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add ECC error codes to enable the appropriate handling in the target. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 4480d1c6a1a5..6b26a3289bce 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -107,6 +107,8 @@ enum { NVM_RSP_NOT_CHANGEABLE = 0x1, NVM_RSP_ERR_FAILWRITE = 0x40ff, NVM_RSP_ERR_EMPTYPAGE = 0x42ff, + NVM_RSP_ERR_FAILECC = 0x4281, + NVM_RSP_WARN_HIGHECC = 0x4700, /* Device opcodes */ NVM_OP_HBREAD = 0x02, -- cgit From 7e4f64a9b3004ce592f21653c3b7781628862232 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:00 +0100 Subject: lightnvm: cleanup unused target operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cleanup definition leftovers from old gennvm interface Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 6b26a3289bce..e598308882aa 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -477,9 +477,6 @@ typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, struct nvm_lun *, unsigned long); typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); -typedef int (nvmm_open_blk_fn)(struct nvm_dev *, struct nvm_block *); -typedef int (nvmm_close_blk_fn)(struct nvm_dev *, struct nvm_block *); -typedef void (nvmm_flush_blk_fn)(struct nvm_dev *, struct nvm_block *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); @@ -504,9 +501,6 @@ struct nvmm_type { /* Block administration callbacks */ nvmm_get_blk_fn *get_blk; nvmm_put_blk_fn *put_blk; - nvmm_open_blk_fn *open_blk; - nvmm_close_blk_fn *close_blk; - nvmm_flush_blk_fn *flush_blk; nvmm_submit_io_fn *submit_io; nvmm_erase_blk_fn *erase_blk; -- cgit From 0e5c3246dbb96b6870634e7d51b2490f05c976cf Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:01 +0100 Subject: lightnvm: make address conversion functions global MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Targets are assumed to used the same generic ppa format, where the address is partitioned on ch:lun:block:pg:pl:sec. Thus, make the function in charge of transforming the ppa address from a linear format to the generic one available to all targets. This function will be needed by the media manager in order to do target mapping translations when targets are divided on different physical partitions. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e598308882aa..98278a9fcb1f 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -361,6 +361,36 @@ struct nvm_dev { spinlock_t lock; }; +static inline struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + int secs, pgs, blks, luns; + sector_t ppa = r.ppa; + + l.ppa = 0; + + div_u64_rem(ppa, dev->sec_per_pg, &secs); + l.g.sec = secs; + + sector_div(ppa, dev->sec_per_pg); + div_u64_rem(ppa, dev->pgs_per_blk, &pgs); + l.g.pg = pgs; + + sector_div(ppa, dev->pgs_per_blk); + div_u64_rem(ppa, dev->blks_per_lun, &blks); + l.g.blk = blks; + + sector_div(ppa, dev->blks_per_lun); + div_u64_rem(ppa, dev->luns_per_chnl, &luns); + l.g.lun = luns; + + sector_div(ppa, dev->luns_per_chnl); + l.g.ch = ppa; + + return l; +} + static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, struct ppa_addr r) { -- cgit From de93434fcf74d41754a48e45365a5914e00bc0be Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:04 +0100 Subject: lightnvm: remove gen_lun abstraction MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The gen_lun abstraction in the generic media manager was conceived on the assumption that a single target would instantiated on top of it. This has complicated target design to implement multi-instances. Remove this abstraction and move its logic to nvm_lun, which manages physical lun geometry and operations. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 98278a9fcb1f..33940bdc18a9 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -275,7 +275,17 @@ struct nvm_lun { spinlock_t lock; + /* lun block lists */ + struct list_head used_list; /* In-use blocks */ + struct list_head free_list; /* Not used blocks i.e. released + * and ready for use + */ + struct list_head bb_list; /* Bad blocks. Mutually exclusive with + * free_list and used_list + */ unsigned int nr_free_blocks; /* Number of unused blocks */ + int reserved_blocks; + struct nvm_block *blocks; }; -- cgit From 8176117b82e49e043d045f214ba7a892fba6b827 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:05 +0100 Subject: lightnvm: manage lun partitions internally in mm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit LUNs are exclusively owned by targets implementing a block device FTL. Doing this reservation requires at the moment a 2-way callback gennvm <-> target. The reason behind this is that LUNs were not assumed to always be exclusively owned by targets. However, this design decision goes against I/O determinism QoS (two targets would mix I/O on the same parallel unit in the device). This patch makes LUN reservation as part of the target creation on the media manager. This makes that LUNs are always exclusively owned by the target instantiated on top of them. LUN stripping and/or sharing should be implemented on the target itself or the layers on top. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 33940bdc18a9..89c695483d55 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -210,6 +210,7 @@ struct nvm_id { struct nvm_target { struct list_head list; + struct list_head lun_list; struct nvm_dev *dev; struct nvm_tgt_type *type; struct gendisk *disk; @@ -273,6 +274,7 @@ struct nvm_lun { int lun_id; int chnl_id; + struct list_head list; spinlock_t lock; /* lun block lists */ @@ -521,8 +523,6 @@ typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); -typedef int (nvmm_reserve_lun)(struct nvm_dev *, int); -typedef void (nvmm_release_lun)(struct nvm_dev *, int); typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); @@ -550,8 +550,6 @@ struct nvmm_type { /* Configuration management */ nvmm_get_lun_fn *get_lun; - nvmm_reserve_lun *reserve_lun; - nvmm_release_lun *release_lun; /* Statistics */ nvmm_lun_info_print_fn *lun_info_print; -- cgit From 8e79b5cb1d3b8eceaf6862995952dd4de431dd99 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:06 +0100 Subject: lightnvm: move block provisioning to targets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to naturally support multi-target instances on an Open-Channel SSD, targets should own the LUNs they get blocks from and manage provisioning internally. This is done in several steps. This patch moves the block provisioning inside of the target and removes the get/put block interface from the media manager. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 133 +++++++++++++++++++++++++---------------------- 1 file changed, 72 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 89c695483d55..1f1588c2557e 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -211,7 +211,7 @@ struct nvm_id { struct nvm_target { struct list_head list; struct list_head lun_list; - struct nvm_dev *dev; + struct nvm_tgt_dev *dev; struct nvm_tgt_type *type; struct gendisk *disk; }; @@ -286,7 +286,6 @@ struct nvm_lun { * free_list and used_list */ unsigned int nr_free_blocks; /* Number of unused blocks */ - int reserved_blocks; struct nvm_block *blocks; }; @@ -315,22 +314,12 @@ struct nvm_sb_info { struct ppa_addr fs_ppa; }; -struct nvm_dev { - struct nvm_dev_ops *ops; - - struct list_head devices; - - /* Media manager */ - struct nvmm_type *mt; - void *mp; - - /* System blocks */ - struct nvm_sb_info sb; - - /* Device information */ +/* Device generic information */ +struct nvm_geo { int nr_chnls; + int nr_luns; + int luns_per_chnl; /* -1 if channels are not symmetric */ int nr_planes; - int luns_per_chnl; int sec_per_pg; /* only sectors for a single page */ int pgs_per_blk; int blks_per_lun; @@ -350,14 +339,43 @@ struct nvm_dev { int sec_per_pl; /* all sectors across planes */ int sec_per_blk; int sec_per_lun; +}; + +struct nvm_tgt_dev { + /* Device information */ + struct nvm_geo geo; + + sector_t total_secs; + + struct nvm_id identity; + struct request_queue *q; + + struct nvmm_type *mt; + struct nvm_dev_ops *ops; + + void *parent; +}; + +struct nvm_dev { + struct nvm_dev_ops *ops; + + struct list_head devices; + + /* Media manager */ + struct nvmm_type *mt; + void *mp; + + /* System blocks */ + struct nvm_sb_info sb; + + /* Device information */ + struct nvm_geo geo; /* lower page table */ int lps_per_blk; int *lptbl; - unsigned long total_blocks; unsigned long total_secs; - int nr_luns; unsigned long *lun_map; void *dma_pool; @@ -373,7 +391,7 @@ struct nvm_dev { spinlock_t lock; }; -static inline struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev, +static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo, struct ppa_addr r) { struct ppa_addr l; @@ -382,22 +400,22 @@ static inline struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev, l.ppa = 0; - div_u64_rem(ppa, dev->sec_per_pg, &secs); + div_u64_rem(ppa, geo->sec_per_pg, &secs); l.g.sec = secs; - sector_div(ppa, dev->sec_per_pg); - div_u64_rem(ppa, dev->pgs_per_blk, &pgs); + sector_div(ppa, geo->sec_per_pg); + div_u64_rem(ppa, geo->pgs_per_blk, &pgs); l.g.pg = pgs; - sector_div(ppa, dev->pgs_per_blk); - div_u64_rem(ppa, dev->blks_per_lun, &blks); + sector_div(ppa, geo->pgs_per_blk); + div_u64_rem(ppa, geo->blks_per_lun, &blks); l.g.blk = blks; - sector_div(ppa, dev->blks_per_lun); - div_u64_rem(ppa, dev->luns_per_chnl, &luns); + sector_div(ppa, geo->blks_per_lun); + div_u64_rem(ppa, geo->luns_per_chnl, &luns); l.g.lun = luns; - sector_div(ppa, dev->luns_per_chnl); + sector_div(ppa, geo->luns_per_chnl); l.g.ch = ppa; return l; @@ -406,14 +424,15 @@ static inline struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev, static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, struct ppa_addr r) { + struct nvm_geo *geo = &dev->geo; struct ppa_addr l; - l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset; - l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset; - l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset; - l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset; - l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset; - l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset; + l.ppa = ((u64)r.g.blk) << geo->ppaf.blk_offset; + l.ppa |= ((u64)r.g.pg) << geo->ppaf.pg_offset; + l.ppa |= ((u64)r.g.sec) << geo->ppaf.sect_offset; + l.ppa |= ((u64)r.g.pl) << geo->ppaf.pln_offset; + l.ppa |= ((u64)r.g.lun) << geo->ppaf.lun_offset; + l.ppa |= ((u64)r.g.ch) << geo->ppaf.ch_offset; return l; } @@ -421,24 +440,25 @@ static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, struct ppa_addr r) { + struct nvm_geo *geo = &dev->geo; struct ppa_addr l; l.ppa = 0; /* * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. */ - l.g.blk = (r.ppa >> dev->ppaf.blk_offset) & - (((1 << dev->ppaf.blk_len) - 1)); - l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) & - (((1 << dev->ppaf.pg_len) - 1)); - l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) & - (((1 << dev->ppaf.sect_len) - 1)); - l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) & - (((1 << dev->ppaf.pln_len) - 1)); - l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) & - (((1 << dev->ppaf.lun_len) - 1)); - l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) & - (((1 << dev->ppaf.ch_len) - 1)); + l.g.blk = (r.ppa >> geo->ppaf.blk_offset) & + (((1 << geo->ppaf.blk_len) - 1)); + l.g.pg |= (r.ppa >> geo->ppaf.pg_offset) & + (((1 << geo->ppaf.pg_len) - 1)); + l.g.sec |= (r.ppa >> geo->ppaf.sect_offset) & + (((1 << geo->ppaf.sect_len) - 1)); + l.g.pl |= (r.ppa >> geo->ppaf.pln_offset) & + (((1 << geo->ppaf.pln_len) - 1)); + l.g.lun |= (r.ppa >> geo->ppaf.lun_offset) & + (((1 << geo->ppaf.lun_len) - 1)); + l.g.ch |= (r.ppa >> geo->ppaf.ch_offset) & + (((1 << geo->ppaf.ch_len) - 1)); return l; } @@ -456,11 +476,12 @@ static inline void ppa_set_empty(struct ppa_addr *ppa_addr) static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev, struct nvm_block *blk) { + struct nvm_geo *geo = &dev->geo; struct ppa_addr ppa; struct nvm_lun *lun = blk->lun; ppa.ppa = 0; - ppa.g.blk = blk->id % dev->blks_per_lun; + ppa.g.blk = blk->id % geo->blks_per_lun; ppa.g.lun = lun->lun_id; ppa.g.ch = lun->chnl_id; @@ -483,7 +504,8 @@ static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg) typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -typedef void *(nvm_tgt_init_fn)(struct nvm_dev *, struct gendisk *, int, int); +typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int, + int); typedef void (nvm_tgt_exit_fn)(void *); struct nvm_tgt_type { @@ -516,9 +538,6 @@ typedef void (nvmm_unregister_fn)(struct nvm_dev *); typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); -typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, - struct nvm_lun *, unsigned long); -typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); @@ -538,10 +557,6 @@ struct nvmm_type { nvmm_create_tgt_fn *create_tgt; nvmm_remove_tgt_fn *remove_tgt; - /* Block administration callbacks */ - nvmm_get_blk_fn *get_blk; - nvmm_put_blk_fn *put_blk; - nvmm_submit_io_fn *submit_io; nvmm_erase_blk_fn *erase_blk; @@ -563,10 +578,6 @@ struct nvmm_type { extern int nvm_register_mgr(struct nvmm_type *); extern void nvm_unregister_mgr(struct nvmm_type *); -extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *, - unsigned long); -extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *); - extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); @@ -611,10 +622,10 @@ extern int nvm_init_sysblock(struct nvm_dev *, struct nvm_sb_info *); extern int nvm_dev_factory(struct nvm_dev *, int flags); -#define nvm_for_each_lun_ppa(dev, ppa, chid, lunid) \ - for ((chid) = 0, (ppa).ppa = 0; (chid) < (dev)->nr_chnls; \ +#define nvm_for_each_lun_ppa(geo, ppa, chid, lunid) \ + for ((chid) = 0, (ppa).ppa = 0; (chid) < (geo)->nr_chnls; \ (chid)++, (ppa).g.ch = (chid)) \ - for ((lunid) = 0; (lunid) < (dev)->luns_per_chnl; \ + for ((lunid) = 0; (lunid) < (geo)->luns_per_chnl; \ (lunid)++, (ppa).g.lun = (lunid)) #else /* CONFIG_NVM */ -- cgit From 0ac4072eb10c9627415eb1ca511121156e20012c Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:07 +0100 Subject: lightnvm: remove get_lun operation on gennvm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since LUNs are managed internally on the target, there is no need for the media manager to implement a get_lun operation. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 1f1588c2557e..e56c35227249 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -504,8 +504,8 @@ static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg) typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int, - int); +typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, + struct list_head *lun_list); typedef void (nvm_tgt_exit_fn)(void *); struct nvm_tgt_type { @@ -541,7 +541,6 @@ typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); -typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); @@ -563,9 +562,6 @@ struct nvmm_type { /* Bad block mgmt */ nvmm_mark_blk_fn *mark_blk; - /* Configuration management */ - nvmm_get_lun_fn *get_lun; - /* Statistics */ nvmm_lun_info_print_fn *lun_info_print; -- cgit From eec44565e9ab13bbf5b48864a68871eabf1115c1 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:08 +0100 Subject: lightnvm: remove debug lun statistics from gennvm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since LUNs are managed internally on targets, the media manager has no access to the free LUN lists. Thus, debug functions that show LUN information on the device should not be implemented on the media manager, but rather on the target in itself. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e56c35227249..ed04fa642371 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -541,8 +541,6 @@ typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); -typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); - typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); @@ -562,9 +560,6 @@ struct nvmm_type { /* Bad block mgmt */ nvmm_mark_blk_fn *mark_blk; - /* Statistics */ - nvmm_lun_info_print_fn *lun_info_print; - nvmm_get_area_fn *get_area; nvmm_put_area_fn *put_area; -- cgit From 2a02e627c245bfa987b97707123d7747d7b0e486 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:09 +0100 Subject: lightnvm: eliminate nvm_block abstraction on mm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to naturally support multi-target instances on an Open-Channel SSD, targets should own the LUNs they get blocks from and manage provisioning internally. This is done in several steps. A part of this transformation is that targets manage their blocks internally. This patch eliminates the nvm_block abstraction and moves block management to the target logic. The rrpc target is transformed. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 48 ++---------------------------------------------- 1 file changed, 2 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ed04fa642371..cc210cc85c6d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -266,8 +266,6 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) return rqdata + 1; } -struct nvm_block; - struct nvm_lun { int id; @@ -275,19 +273,6 @@ struct nvm_lun { int chnl_id; struct list_head list; - spinlock_t lock; - - /* lun block lists */ - struct list_head used_list; /* In-use blocks */ - struct list_head free_list; /* Not used blocks i.e. released - * and ready for use - */ - struct list_head bb_list; /* Bad blocks. Mutually exclusive with - * free_list and used_list - */ - unsigned int nr_free_blocks; /* Number of unused blocks */ - - struct nvm_block *blocks; }; enum { @@ -296,15 +281,6 @@ enum { NVM_BLK_ST_BAD = 0x8, /* Bad block */ }; -struct nvm_block { - struct list_head list; - struct nvm_lun *lun; - unsigned long id; - - void *priv; - int state; -}; - /* system block cpu representation */ struct nvm_sb_info { unsigned long seqnr; @@ -473,21 +449,6 @@ static inline void ppa_set_empty(struct ppa_addr *ppa_addr) ppa_addr->ppa = ADDR_EMPTY; } -static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev, - struct nvm_block *blk) -{ - struct nvm_geo *geo = &dev->geo; - struct ppa_addr ppa; - struct nvm_lun *lun = blk->lun; - - ppa.ppa = 0; - ppa.g.blk = blk->id % geo->blks_per_lun; - ppa.g.lun = lun->lun_id; - ppa.g.ch = lun->chnl_id; - - return ppa; -} - static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2) { if (ppa_empty(ppa1) || ppa_empty(ppa2)) @@ -539,8 +500,7 @@ typedef void (nvmm_unregister_fn)(struct nvm_dev *); typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); -typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, int); -typedef void (nvmm_mark_blk_fn)(struct nvm_dev *, struct ppa_addr, int); +typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct ppa_addr *, int); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); @@ -557,9 +517,6 @@ struct nvmm_type { nvmm_submit_io_fn *submit_io; nvmm_erase_blk_fn *erase_blk; - /* Bad block mgmt */ - nvmm_mark_blk_fn *mark_blk; - nvmm_get_area_fn *get_area; nvmm_put_area_fn *put_area; @@ -573,7 +530,6 @@ extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); -extern void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type); extern int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas, int type); @@ -584,7 +540,7 @@ extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, const struct ppa_addr *, int, int); extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int); -extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *, int); +extern int nvm_erase_blk(struct nvm_dev *, struct ppa_addr *, int); extern void nvm_end_io(struct nvm_rq *, int); extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int, void *, int); -- cgit From 8e53624d44c1de31b1b0d4f500703669418a4c67 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:10 +0100 Subject: lightnvm: eliminate nvm_lun abstraction in mm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to naturally support multi-target instances on an Open-Channel SSD, targets should own the LUNs they get blocks from and manage provisioning internally. This is done in several steps. Since targets own the LUNs the are instantiated on top of and manage the free block list internally, there is no need for a LUN abstraction in the media manager. LUNs are intrinsically managed as in the physical layout (ch:0,lun:0, ..., ch:0,lun:n, ch:1,lun:0, ch:1,lun:n, ..., ch:m,lun:0, ch:m,lun:n) and given to the targets based on the target creation ioctl. This simplifies LUN management and clears the path for a partition manager to sit directly underneath LightNVM targets. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 41 ++++++++++++++++++++++------------------- 1 file changed, 22 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index cc210cc85c6d..2222853ef969 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -47,6 +47,7 @@ struct ppa_addr { struct nvm_rq; struct nvm_id; struct nvm_dev; +struct nvm_tgt_dev; typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *); @@ -210,7 +211,6 @@ struct nvm_id { struct nvm_target { struct list_head list; - struct list_head lun_list; struct nvm_tgt_dev *dev; struct nvm_tgt_type *type; struct gendisk *disk; @@ -231,7 +231,7 @@ typedef void (nvm_end_io_fn)(struct nvm_rq *); struct nvm_rq { struct nvm_tgt_instance *ins; - struct nvm_dev *dev; + struct nvm_tgt_dev *dev; struct bio *bio; @@ -266,15 +266,6 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) return rqdata + 1; } -struct nvm_lun { - int id; - - int lun_id; - int chnl_id; - - struct list_head list; -}; - enum { NVM_BLK_ST_FREE = 0x1, /* Free block */ NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ @@ -321,6 +312,9 @@ struct nvm_tgt_dev { /* Device information */ struct nvm_geo geo; + /* Base ppas for target LUNs */ + struct ppa_addr *luns; + sector_t total_secs; struct nvm_id identity; @@ -330,6 +324,7 @@ struct nvm_tgt_dev { struct nvm_dev_ops *ops; void *parent; + void *map; }; struct nvm_dev { @@ -363,16 +358,18 @@ struct nvm_dev { char name[DISK_NAME_LEN]; void *private_data; + void *rmap; + struct mutex mlock; spinlock_t lock; }; static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo, - struct ppa_addr r) + u64 pba) { struct ppa_addr l; int secs, pgs, blks, luns; - sector_t ppa = r.ppa; + sector_t ppa = pba; l.ppa = 0; @@ -465,8 +462,7 @@ static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg) typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, - struct list_head *lun_list); +typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *); typedef void (nvm_tgt_exit_fn)(void *); struct nvm_tgt_type { @@ -499,10 +495,11 @@ typedef void (nvmm_unregister_fn)(struct nvm_dev *); typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); -typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); -typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct ppa_addr *, int); +typedef int (nvmm_submit_io_fn)(struct nvm_tgt_dev *, struct nvm_rq *); +typedef int (nvmm_erase_blk_fn)(struct nvm_tgt_dev *, struct ppa_addr *, int); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); +typedef void (nvmm_part_to_tgt_fn)(struct nvm_dev *, sector_t*, int); struct nvmm_type { const char *name; @@ -520,6 +517,8 @@ struct nvmm_type { nvmm_get_area_fn *get_area; nvmm_put_area_fn *put_area; + nvmm_part_to_tgt_fn *part_to_tgt; + struct list_head list; }; @@ -533,14 +532,18 @@ extern void nvm_unregister(struct nvm_dev *); extern int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas, int type); -extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); +extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, const struct ppa_addr *, int, int); extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int); -extern int nvm_erase_blk(struct nvm_dev *, struct ppa_addr *, int); +extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int); +extern int nvm_get_l2p_tbl(struct nvm_dev *, u64, u32, nvm_l2p_update_fn *, + void *); +extern int nvm_get_area(struct nvm_dev *, sector_t *, sector_t); +extern void nvm_put_area(struct nvm_dev *, sector_t); extern void nvm_end_io(struct nvm_rq *, int); extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int, void *, int); -- cgit From 959e911b31981b52ed3f3d6e351b107bcb9163ef Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:11 +0100 Subject: lightnvm: introduce helpers for generic ops in rrpc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Avoid calling media manager and device-specific operations directly from rrpc. Create helper functions on lightnvm's core instead. Signed-off-by: Javier González Made it work with null_blk as well. Signed-off-by: Matias Bjørling Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 2222853ef969..99cd1e70e451 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -320,10 +320,7 @@ struct nvm_tgt_dev { struct nvm_id identity; struct request_queue *q; - struct nvmm_type *mt; - struct nvm_dev_ops *ops; - - void *parent; + struct nvm_dev *parent; void *map; }; -- cgit From a279006afa3377493c4240395c70430f2a9b0d2b Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:12 +0100 Subject: lightnvm: introduce max_phys_sects helper function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Target devices do not have access to the device driver operations. Introduce a helper function that exposes the max. number of physical sectors supported by the underlying device. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 99cd1e70e451..96375317b479 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -529,6 +529,7 @@ extern void nvm_unregister(struct nvm_dev *); extern int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas, int type); +extern int nvm_max_phys_sects(struct nvm_tgt_dev *); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); -- cgit From da2d7cb828ce2714c603827ac5a6e1c98a02e861 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:13 +0100 Subject: lightnvm: use target nvm on target-specific ops. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On target-specific operations pass on nvm_tgt_dev instead of the generic nvm device. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 96375317b479..e76f9c4aa49b 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -538,10 +538,10 @@ extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int); extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int); -extern int nvm_get_l2p_tbl(struct nvm_dev *, u64, u32, nvm_l2p_update_fn *, +extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *, void *); -extern int nvm_get_area(struct nvm_dev *, sector_t *, sector_t); -extern void nvm_put_area(struct nvm_dev *, sector_t); +extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t); +extern void nvm_put_area(struct nvm_tgt_dev *, sector_t); extern void nvm_end_io(struct nvm_rq *, int); extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int, void *, int); -- cgit From 333ba053d145d6f9152f6b0311a345b876f0fed1 Mon Sep 17 00:00:00 2001 From: Javier González Date: Mon, 28 Nov 2016 22:39:14 +0100 Subject: lightnvm: transform target get/set bad block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since targets are given a virtual target device, it is necessary to translate all communication between targets and the backend device. Implement the translation layer for get/set bad block table. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e76f9c4aa49b..7c273bbc5351 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -496,8 +496,15 @@ typedef int (nvmm_submit_io_fn)(struct nvm_tgt_dev *, struct nvm_rq *); typedef int (nvmm_erase_blk_fn)(struct nvm_tgt_dev *, struct ppa_addr *, int); typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); +typedef struct ppa_addr (nvmm_trans_ppa_fn)(struct nvm_tgt_dev *, + struct ppa_addr, int); typedef void (nvmm_part_to_tgt_fn)(struct nvm_dev *, sector_t*, int); +enum { + TRANS_TGT_TO_DEV = 0x0, + TRANS_DEV_TO_TGT = 0x1, +}; + struct nvmm_type { const char *name; unsigned int version[3]; @@ -514,6 +521,7 @@ struct nvmm_type { nvmm_get_area_fn *get_area; nvmm_put_area_fn *put_area; + nvmm_trans_ppa_fn *trans_ppa; nvmm_part_to_tgt_fn *part_to_tgt; struct list_head list; @@ -526,9 +534,9 @@ extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); -extern int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, - int nr_ppas, int type); - +extern int nvm_set_bb_tbl(struct nvm_dev *, struct ppa_addr *, int, int); +extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, + int, int); extern int nvm_max_phys_sects(struct nvm_tgt_dev *); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); @@ -549,6 +557,7 @@ extern int nvm_submit_ppa_list(struct nvm_dev *, struct ppa_addr *, int, int, int, void *, int); extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); extern int nvm_get_bb_tbl(struct nvm_dev *, struct ppa_addr, u8 *); +extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); /* sysblk.c */ #define NVM_SYSBLK_MAGIC 0x4E564D53 /* "NVMS" */ -- cgit From ced6473e7486702f530a49f886b73195e4977734 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 28 Nov 2016 16:41:41 +0100 Subject: driver core: class: add class_groups support struct class needs to have a set of default groups that are added, as adding individual attributes does not work well in the long run. So add support for that. Future patches will convert the existing usages of class_attrs to use class_groups and then class_attrs will go away. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4264caacebb9..4cd8e52033b0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -362,6 +362,7 @@ int subsys_virtual_register(struct bus_type *subsys, * @name: Name of the class. * @owner: The module owner. * @class_attrs: Default attributes of this class. + * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a @@ -390,6 +391,7 @@ struct class { struct module *owner; struct class_attribute *class_attrs; + const struct attribute_group **class_groups; const struct attribute_group **dev_groups; struct kobject *dev_kobj; -- cgit From 1d7f1589d341344c0c598b00de44891a7968c6a0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 22 Nov 2016 18:22:09 +0000 Subject: fpga: Clarify how write_init works streaming modes This interface was designed for streaming, but write_init's buf argument has an unclear purpose. Define it to be the first bytes of the bitstream. Each driver gets to set how many bytes (at most) it wants to see. Short bitstreams will be passed through as-is, while long ones will be truncated. The intent is to allow drivers to peek at the header before the transfer actually starts. Signed-off-by: Jason Gunthorpe Acked-by: Alan Tull --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 96a1a3311649..16551d5eac36 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -84,6 +84,7 @@ struct fpga_image_info { /** * struct fpga_manager_ops - ops for low level fpga manager drivers + * @initial_header_size: Maximum number of bytes that should be passed into write_init * @state: returns an enum value of the FPGA's state * @write_init: prepare the FPGA to receive confuration data * @write: write count bytes of configuration data to the FPGA @@ -95,6 +96,7 @@ struct fpga_image_info { * called, so leaving them out is fine. */ struct fpga_manager_ops { + size_t initial_header_size; enum fpga_mgr_states (*state)(struct fpga_manager *mgr); int (*write_init)(struct fpga_manager *mgr, struct fpga_image_info *info, -- cgit From d853d145ea3e63387a2ac759aa41d5e43876e561 Mon Sep 17 00:00:00 2001 From: jbrunet Date: Mon, 28 Nov 2016 10:46:46 +0100 Subject: net: phy: add an option to disable EEE advertisement MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds an option to disable EEE advertisement in the generic PHY by providing a mask of prohibited modes corresponding to the value found in the MDIO_AN_EEE_ADV register. On some platforms, PHY Low power idle seems to be causing issues, even breaking the link some cases. The patch provides a convenient way for these platforms to disable EEE advertisement and work around the issue. Signed-off-by: Jerome Brunet Tested-by: Yegor Yefremov Tested-by: Andreas Färber Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index edde28ce163a..b53177fd38af 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -417,6 +417,9 @@ struct phy_device { u32 advertising; u32 lp_advertising; + /* Energy efficient ethernet modes which should be prohibited */ + u32 eee_broken_modes; + int autoneg; int link_timeout; -- cgit From 3816199506c7826983096fc65ed46f2733a47bb8 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 31 Oct 2016 11:59:24 -0600 Subject: block: add bio_iov_iter_get_pages() This is a helper that pins down a range from an iov_iter and adds it to a bio without requiring a separate memory allocation for the page array. It will be used for upcoming direct I/O implementations for block devices and iomap based file systems. Signed-off-by: Kent Overstreet [hch: ported to the iov_iter interface, renamed and added comments. All blame should be directed to me and all fame should go to Kent after this!] Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe (cherry picked from commit 9cd56d916aa481ce8f56d9c5302a6ed90c2e0b5f) --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 97cb48f03dc7..66228c28c621 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -430,6 +430,7 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, const struct iov_iter *, gfp_t); -- cgit From 54cd255808761ecfd0e000eb78eb74dde8cd0c96 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 29 Nov 2016 16:23:41 +0200 Subject: dmaengine: dma_slave_config: add support for slave port window Some slave devices uses address window instead of single register for read and/or write of data. With the src/dst_port_window_size the address window can be specified and the DMAengine driver should use this information to correctly set up the transfer to loop within the provided window. Signed-off-by: Peter Ujfalusi Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cc535a478bae..feee6ec6a13b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -336,6 +336,12 @@ enum dma_slave_buswidth { * may or may not be applicable on memory sources. * @dst_maxburst: same as src_maxburst but for destination target * mutatis mutandis. + * @src_port_window_size: The length of the register area in words the data need + * to be accessed on the device side. It is only used for devices which is using + * an area instead of a single register to receive the data. Typically the DMA + * loops in this area in order to transfer the data. + * @dst_port_window_size: same as src_port_window_size but for the destination + * port. * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill * with 'true' if peripheral should be flow controller. Direction will be * selected at Runtime. @@ -363,6 +369,8 @@ struct dma_slave_config { enum dma_slave_buswidth dst_addr_width; u32 src_maxburst; u32 dst_maxburst; + u32 src_port_window_size; + u32 dst_port_window_size; bool device_fc; unsigned int slave_id; }; -- cgit From bd2c6636cc59c4626a04d9918953a107f88eaff9 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 25 Nov 2016 17:59:07 +0300 Subject: dmaengine: DW DMAC: add multi-block property to device tree Several versions of DW DMAC have multi block transfers hardware support. Hardware support of multi block transfers is disabled by default if we use DT to configure DMAC and software emulation of multi block transfers used instead. Add multi-block property, so it is possible to enable hardware multi block transfers (if present) via DT. Switch from per device is_nollp variable to multi_block array to be able enable/disable multi block transfers separately per channel. Acked-by: Andy Shevchenko Signed-off-by: Eugeniy Paltsev Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 5f0e11e7354c..e69e415d0d98 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -14,6 +14,7 @@ #include #define DW_DMA_MAX_NR_MASTERS 4 +#define DW_DMA_MAX_NR_CHANNELS 8 /** * struct dw_dma_slave - Controller-specific information about a slave @@ -40,19 +41,18 @@ struct dw_dma_slave { * @is_private: The device channels should be marked as private and not for * by the general purpose DMA channel allocator. * @is_memcpy: The device channels do support memory-to-memory transfers. - * @is_nollp: The device channels does not support multi block transfers. * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller * @nr_masters: Number of AHB masters supported by the controller * @data_width: Maximum data width supported by hardware per AHB master * (in bytes, power of 2) + * @multi_block: Multi block transfers supported by hardware per channel. */ struct dw_dma_platform_data { unsigned int nr_channels; bool is_private; bool is_memcpy; - bool is_nollp; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ unsigned char chan_allocation_order; @@ -62,6 +62,7 @@ struct dw_dma_platform_data { unsigned int block_size; unsigned char nr_masters; unsigned char data_width[DW_DMA_MAX_NR_MASTERS]; + unsigned char multi_block[DW_DMA_MAX_NR_CHANNELS]; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit From f8319483f57f1ca22370f4150bb990aca7728a67 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Nov 2016 14:32:25 +1100 Subject: locking/lockdep: Provide a type check for lock_is_held Christoph requested lockdep_assert_held() variants that distinguish between held-for-read or held-for-write. Provide: int lock_is_held_type(struct lockdep_map *lock, int read) which takes the same argument as lock_acquire(.read) and matches it to the held_lock instance. Use of this function should be gated by the debug_locks variable. When that is 0 the return value of the lock_is_held_type() function is undefined. This is done to allow both negative and positive tests for holding locks. By default we provide (positive) lockdep_assert_held{,_exclusive,_read}() macros. Requested-by: Christoph Hellwig Signed-off-by: Peter Zijlstra (Intel) Tested-by: Jens Axboe Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- include/linux/lockdep.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c1458fede1f9..1e327bb80838 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -338,9 +338,18 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); -#define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) +/* + * Same "read" as for lock_acquire(), except -1 means any. + */ +extern int lock_is_held_type(struct lockdep_map *lock, int read); + +static inline int lock_is_held(struct lockdep_map *lock) +{ + return lock_is_held_type(lock, -1); +} -extern int lock_is_held(struct lockdep_map *lock); +#define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) +#define lockdep_is_held_type(lock, r) lock_is_held_type(&(lock)->dep_map, (r)) extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, @@ -372,6 +381,14 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) +#define lockdep_assert_held_exclusive(l) do { \ + WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ + } while (0) + +#define lockdep_assert_held_read(l) do { \ + WARN_ON(debug_locks && !lockdep_is_held_type(l, 1)); \ + } while (0) + #define lockdep_assert_held_once(l) do { \ WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) @@ -428,7 +445,11 @@ struct lock_class_key { }; #define lockdep_depth(tsk) (0) +#define lockdep_is_held_type(l, r) (1) + #define lockdep_assert_held(l) do { (void)(l); } while (0) +#define lockdep_assert_held_exclusive(l) do { (void)(l); } while (0) +#define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_recursing(tsk) (0) -- cgit From ff6a9292e6f633d596826be5ba70d3ef90cc3300 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Nov 2016 14:36:01 +1100 Subject: iomap: implement direct I/O This adds a full fledget direct I/O implementation using the iomap interface. Full fledged in this case means all features are supported: AIO, vectored I/O, any iov_iter type including kernel pointers, bvecs and pipes, support for hole filling and async apending writes. It does not mean supporting all the warts of the old generic code. We expect i_rwsem to be held over the duration of the call, and we expect to maintain i_dio_count ourselves, and we pass on any kinds of mapping to the file system for now. The algorithm used is very simple: We use iomap_apply to iterate over the range of the I/O, and then we use the new bio_iov_iter_get_pages helper to lock down the user range for the size of the extent. bio_iov_iter_get_pages can currently lock down twice as many pages as the old direct I/O code did, which means that we will have a better batch factor for everything but overwrites of badly fragmented files. Signed-off-by: Christoph Hellwig Reviewed-by: Kent Overstreet Tested-by: Jens Axboe Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- include/linux/iomap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f185156de74d..a4c94b86401e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -50,6 +50,7 @@ struct iomap { #define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */ #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ +#define IOMAP_DIRECT (1 << 4) /* direct I/O */ struct iomap_ops { /* @@ -83,4 +84,14 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, struct iomap_ops *ops); +/* + * Flags for direct I/O ->end_io: + */ +#define IOMAP_DIO_UNWRITTEN (1 << 0) /* covers unwritten extent(s) */ +#define IOMAP_DIO_COW (1 << 1) /* covers COW extent(s) */ +typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret, + unsigned flags); +ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + struct iomap_ops *ops, iomap_dio_end_io_t end_io); + #endif /* LINUX_IOMAP_H */ -- cgit From c3b004460d77bf3f980d877be539016f2df4df12 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 23 Nov 2016 14:04:55 +0100 Subject: quota: Remove dqonoff_mutex The only places that were grabbing dqonoff_mutex are functions turning quotas on and off and these are properly serialized using s_umount semaphore. Remove dqonoff_mutex. Signed-off-by: Jan Kara --- include/linux/quota.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 55107a8ff887..b281d198ee5b 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -520,7 +520,6 @@ static inline void quota_send_warning(struct kqid qid, dev_t dev, struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ struct mutex dqio_mutex; /* lock device while I/O in progress */ - struct mutex dqonoff_mutex; /* Serialize quotaon & quotaoff */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ -- cgit From 60fe3910bb029e3671ce7ac080a7acb7e032b9e0 Mon Sep 17 00:00:00 2001 From: Thiago Jung Bauermann Date: Tue, 29 Nov 2016 23:45:47 +1100 Subject: kexec_file: Allow arch-specific memory walking for kexec_add_buffer Allow architectures to specify a different memory walking function for kexec_add_buffer. x86 uses iomem to track reserved memory ranges, but PowerPC uses the memblock subsystem. Signed-off-by: Thiago Jung Bauermann Acked-by: Dave Young Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- include/linux/kexec.h | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 406c33dcae13..5e320ddaaa82 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -148,7 +148,34 @@ struct kexec_file_ops { kexec_verify_sig_t *verify_sig; #endif }; -#endif + +/** + * struct kexec_buf - parameters for finding a place for a buffer in memory + * @image: kexec image in which memory to search. + * @buffer: Contents which will be copied to the allocated memory. + * @bufsz: Size of @buffer. + * @mem: On return will have address of the buffer in memory. + * @memsz: Size for the buffer in memory. + * @buf_align: Minimum alignment needed. + * @buf_min: The buffer can't be placed below this address. + * @buf_max: The buffer can't be placed above this address. + * @top_down: Allocate from top of memory. + */ +struct kexec_buf { + struct kimage *image; + char *buffer; + unsigned long bufsz; + unsigned long mem; + unsigned long memsz; + unsigned long buf_align; + unsigned long buf_min; + unsigned long buf_max; + bool top_down; +}; + +int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, + int (*func)(u64, u64, void *)); +#endif /* CONFIG_KEXEC_FILE */ struct kimage { kimage_entry_t head; -- cgit From ec2b9bfaac44ea889625a6b9473d33898b10d35f Mon Sep 17 00:00:00 2001 From: Thiago Jung Bauermann Date: Tue, 29 Nov 2016 23:45:48 +1100 Subject: kexec_file: Change kexec_add_buffer to take kexec_buf as argument. This is done to simplify the kexec_add_buffer argument list. Adapt all callers to set up a kexec_buf to pass to kexec_add_buffer. In addition, change the type of kexec_buf.buffer from char * to void *. There is no particular reason for it to be a char *, and the change allows us to get rid of 3 existing casts to char * in the code. Signed-off-by: Thiago Jung Bauermann Acked-by: Dave Young Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- include/linux/kexec.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 5e320ddaaa82..437ef1b47428 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -163,7 +163,7 @@ struct kexec_file_ops { */ struct kexec_buf { struct kimage *image; - char *buffer; + void *buffer; unsigned long bufsz; unsigned long mem; unsigned long memsz; @@ -175,6 +175,7 @@ struct kexec_buf { int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)); +extern int kexec_add_buffer(struct kexec_buf *kbuf); #endif /* CONFIG_KEXEC_FILE */ struct kimage { @@ -239,11 +240,6 @@ extern asmlinkage long sys_kexec_load(unsigned long entry, struct kexec_segment __user *segments, unsigned long flags); extern int kernel_kexec(void); -extern int kexec_add_buffer(struct kimage *image, char *buffer, - unsigned long bufsz, unsigned long memsz, - unsigned long buf_align, unsigned long buf_min, - unsigned long buf_max, bool top_down, - unsigned long *load_addr); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); extern int kexec_load_purgatory(struct kimage *image, unsigned long min, -- cgit From e2e806f9e437b46a3fc8f3174a225c73f2e38c3d Mon Sep 17 00:00:00 2001 From: Thiago Jung Bauermann Date: Tue, 29 Nov 2016 23:45:49 +1100 Subject: kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer. kexec_locate_mem_hole will be used by the PowerPC kexec_file_load implementation to find free memory for the purgatory stack. Signed-off-by: Thiago Jung Bauermann Acked-by: Dave Young Signed-off-by: Michael Ellerman --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 437ef1b47428..a33f63351f86 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -176,6 +176,7 @@ struct kexec_buf { int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); +int kexec_locate_mem_hole(struct kexec_buf *kbuf); #endif /* CONFIG_KEXEC_FILE */ struct kimage { -- cgit From 05b055e89121394058c75dc354e9a46e1e765579 Mon Sep 17 00:00:00 2001 From: Francis Yan Date: Sun, 27 Nov 2016 23:07:13 -0800 Subject: tcp: instrument tcp sender limits chronographs This patch implements the skeleton of the TCP chronograph instrumentation on sender side limits: 1) idle (unspec) 2) busy sending data other than 3-4 below 3) rwnd-limited 4) sndbuf-limited The limits are enumerated 'tcp_chrono'. Since a connection in theory can idle forever, we do not track the actual length of this uninteresting idle period. For the rest we track how long the sender spends in each limit. At any point during the life time of a connection, the sender must be in one of the four states. If there are multiple conditions worthy of tracking in a chronograph then the highest priority enum takes precedence over the other conditions. So that if something "more interesting" starts happening, stop the previous chrono and start a new one. The time unit is jiffy(u32) in order to save space in tcp_sock. This implies application must sample the stats no longer than every 49 days of 1ms jiffy. Signed-off-by: Francis Yan Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 32a7c7e35b71..d5d3bd814338 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -211,8 +211,11 @@ struct tcp_sock { u8 reord; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ - u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ - unused:7; + u32 chrono_start; /* Start time in jiffies of a TCP chrono */ + u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ + u8 chrono_type:2, /* current chronograph type */ + rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + unused:5; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ -- cgit From 1c885808e45601b2b6f68b30ac1d999e10b6f606 Mon Sep 17 00:00:00 2001 From: Francis Yan Date: Sun, 27 Nov 2016 23:07:18 -0800 Subject: tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING This patch exports the sender chronograph stats via the socket SO_TIMESTAMPING channel. Currently we can instrument how long a particular application unit of data was queued in TCP by tracking SOF_TIMESTAMPING_TX_SOFTWARE and SOF_TIMESTAMPING_TX_SCHED. Having these sender chronograph stats exported simultaneously along with these timestamps allow further breaking down the various sender limitation. For example, a video server can tell if a particular chunk of video on a connection takes a long time to deliver because TCP was experiencing small receive window. It is not possible to tell before this patch without packet traces. To prepare these stats, the user needs to set SOF_TIMESTAMPING_OPT_STATS and SOF_TIMESTAMPING_OPT_TSONLY flags while requesting other SOF_TIMESTAMPING TX timestamps. When the timestamps are available in the error queue, the stats are returned in a separate control message of type SCM_TIMESTAMPING_OPT_STATS, in a list of TLVs (struct nlattr) of types: TCP_NLA_BUSY_TIME, TCP_NLA_RWND_LIMITED, TCP_NLA_SNDBUF_LIMITED. Unit is microsecond. Signed-off-by: Francis Yan Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d5d3bd814338..00e0ee8f001f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -428,4 +428,6 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); + #endif /* _LINUX_TCP_H */ -- cgit From 820ee17b8d3b2a57b1ea20b247cc6a1dddaf8b8d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 29 Nov 2016 09:57:17 -0800 Subject: net: phy: broadcom: Add support code for reading PHY counters Broadcom PHYs expose a number of PHY error counters: receive errors, false carrier sense, SerDes BER count, local and remote receive errors. Add support code to allow retrieving these error counters. Since the Broadcom PHY library code is used by several drivers, make it possible for them to specify the storage for the software copy of the statistics. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index f9f8aaf9c943..4f7d8be9ddbf 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -244,6 +244,9 @@ #define LPI_FEATURE_EN_DIG1000X 0x4000 /* Core register definitions*/ +#define MII_BRCM_CORE_BASE12 0x12 +#define MII_BRCM_CORE_BASE13 0x13 +#define MII_BRCM_CORE_BASE14 0x14 #define MII_BRCM_CORE_BASE1E 0x1E #define MII_BRCM_CORE_EXPB0 0xB0 #define MII_BRCM_CORE_EXPB1 0xB1 -- cgit From 85de8576a0b14aecc99136cfbf90e367fa2142cb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 28 Nov 2016 23:16:54 +0100 Subject: bpf, xdp: allow to pass flags to dev_change_xdp_fd Add an IFLA_XDP_FLAGS attribute that can be passed for setting up XDP along with IFLA_XDP_FD, which eventually allows user space to implement typical add/replace/delete logic for programs. Right now, calling into dev_change_xdp_fd() will always replace previous programs. When passed XDP_FLAGS_UPDATE_IF_NOEXIST, we can handle this more graceful when requested by returning -EBUSY in case we try to attach a new program, but we find that another one is already attached. This will be used by upcoming front-end for iproute2 as well. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4ffcd874cc20..3755317cc6a9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3253,7 +3253,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd); +int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit From 9e421b7c60860f150aa29e9f7bc902f003d87e68 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 29 Nov 2016 17:41:50 -0800 Subject: Input: synaptics-rmi4 - fix documentation of rmi_2d_sensor_platform_data Typos... Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 8499b6aa2221..27dd9aa4090c 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -108,7 +108,7 @@ struct rmi_2d_sensor_platform_data { * @buttonpad - the touchpad is a buttonpad, so enable only the first actual * button that is found. * @trackstick_buttons - Set when the function 30 is handling the physical - * buttons of the trackstick (as a PD/2 passthrough device. + * buttons of the trackstick (as a PS/2 passthrough device). * @disable - the touchpad incorrectly reports F30 and it should be ignored. * This is a special case which is due to misconfigured firmware. */ -- cgit From 0d37d63a001202b4932f6b14b05d8d055a0a45b6 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 29 Nov 2016 17:42:01 -0800 Subject: Input: synaptics-rmi4 - remove unused fields in struct rmi_driver_data These fields are not used anywhere, there is no point in carrying them. Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 27dd9aa4090c..0b118ab47b8d 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -340,7 +340,6 @@ struct rmi_driver_data { struct rmi_function *f34_container; bool f01_bootloader_mode; - u32 attn_count; int num_of_irq_regs; int irq_count; void *irq_memory; @@ -352,14 +351,11 @@ struct rmi_driver_data { struct input_dev *input; u8 pdt_props; - u8 bsr; u8 num_rx_electrodes; u8 num_tx_electrodes; bool enabled; - - void *data; }; int rmi_register_transport_device(struct rmi_transport_dev *xport); -- cgit From a64ea311f1e4bc090c89960650637423e86c35c0 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 29 Nov 2016 17:42:13 -0800 Subject: Input: synaptics-rmi4 - add rmi_enable/disable_irq Set the .enabled boolean and trigger an event processing when enabling for edge-triggered systems. Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 0b118ab47b8d..621f098f1243 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -356,6 +356,7 @@ struct rmi_driver_data { u8 num_tx_electrodes; bool enabled; + struct mutex enabled_mutex; }; int rmi_register_transport_device(struct rmi_transport_dev *xport); -- cgit From b634d30a79ecc2d28e61cbe5b1f4443952f37a8f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Nov 2016 10:16:08 -0800 Subject: cgroup, bpf: remove unnecessary #include this #include is unnecessary and brings whole set of other headers into cgroup-defs.h. Remove it. Fixes: 3007098494be ("cgroup: add support for eBPF programs") Signed-off-by: Alexei Starovoitov Acked-by: Rami Rosen Acked-by: Daniel Borkmann Acked-by: Daniel Mack Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index ec80d0c0953e..0cf1adfadd2d 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -1,7 +1,6 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H -#include #include #include -- cgit From 6d937acfb3f166f6e10abd978fafafa120d6f0d7 Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Tue, 29 Nov 2016 16:47:01 +0200 Subject: qed: Optimize qed_chain datapath usage The chain structure and functions are widely used by the qed* modules, both for configuration and datapath. E.g., qede's Tx has one such chain and its Rx has two. Currently, the strucutre's fields which are required for datapath related functions [produce/consume] are intertwined with fields which are required only for configuration purposes [init/destroy/etc.]. This patch re-arranges the chain structure so that all the fields which are required for datapath usage could reside in a single cacheline instead of the two which are required today. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 144 +++++++++++++++++++++++------------------- 1 file changed, 80 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 72d88cf3ca25..37dfba101c6c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -56,23 +56,6 @@ struct qed_chain_pbl_u32 { u32 cons_page_idx; }; -struct qed_chain_pbl { - /* Base address of a pre-allocated buffer for pbl */ - dma_addr_t p_phys_table; - void *p_virt_table; - - /* Table for keeping the virtual addresses of the chain pages, - * respectively to the physical addresses in the pbl table. - */ - void **pp_virt_addr_tbl; - - /* Index to current used page by producer/consumer */ - union { - struct qed_chain_pbl_u16 pbl16; - struct qed_chain_pbl_u32 pbl32; - } u; -}; - struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ u16 prod_idx; @@ -86,46 +69,78 @@ struct qed_chain_u32 { }; struct qed_chain { - void *p_virt_addr; - dma_addr_t p_phys_addr; - void *p_prod_elem; - void *p_cons_elem; + /* fastpath portion of the chain - required for commands such + * as produce / consume. + */ + /* Point to next element to produce/consume */ + void *p_prod_elem; + void *p_cons_elem; + + /* Fastpath portions of the PBL [if exists] */ + struct { + /* Table for keeping the virtual addresses of the chain pages, + * respectively to the physical addresses in the pbl table. + */ + void **pp_virt_addr_tbl; - enum qed_chain_mode mode; - enum qed_chain_use_mode intended_use; /* used to produce/consume */ - enum qed_chain_cnt_type cnt_type; + union { + struct qed_chain_pbl_u16 u16; + struct qed_chain_pbl_u32 u32; + } c; + } pbl; union { struct qed_chain_u16 chain16; struct qed_chain_u32 chain32; } u; + /* Capacity counts only usable elements */ + u32 capacity; u32 page_cnt; - /* Number of elements - capacity is for usable elements only, - * while size will contain total number of elements [for entire chain]. + enum qed_chain_mode mode; + + /* Elements information for fast calculations */ + u16 elem_per_page; + u16 elem_per_page_mask; + u16 elem_size; + u16 next_page_mask; + u16 usable_per_page; + u8 elem_unusable; + + u8 cnt_type; + + /* Slowpath of the chain - required for initialization and destruction, + * but isn't involved in regular functionality. */ - u32 capacity; + + /* Base address of a pre-allocated buffer for pbl */ + struct { + dma_addr_t p_phys_table; + void *p_virt_table; + } pbl_sp; + + /* Address of first page of the chain - the address is required + * for fastpath operation [consume/produce] but only for the the SINGLE + * flavour which isn't considered fastpath [== SPQ]. + */ + void *p_virt_addr; + dma_addr_t p_phys_addr; + + /* Total number of elements [for entire chain] */ u32 size; - /* Elements information for fast calculations */ - u16 elem_per_page; - u16 elem_per_page_mask; - u16 elem_unusable; - u16 usable_per_page; - u16 elem_size; - u16 next_page_mask; - struct qed_chain_pbl pbl; + u8 intended_use; }; #define QED_CHAIN_PBL_ENTRY_SIZE (8) #define QED_CHAIN_PAGE_SIZE (0x1000) #define ELEMS_PER_PAGE(elem_size) (QED_CHAIN_PAGE_SIZE / (elem_size)) -#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ - ((mode == QED_CHAIN_MODE_NEXT_PTR) ? \ - (1 + ((sizeof(struct qed_chain_next) - 1) / \ - (elem_size))) : 0) +#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ + (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ + (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / \ + (elem_size))) : 0) #define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ ((u32)(ELEMS_PER_PAGE(elem_size) - \ @@ -186,7 +201,7 @@ static inline u16 qed_chain_get_usable_per_page(struct qed_chain *p_chain) return p_chain->usable_per_page; } -static inline u16 qed_chain_get_unusable_per_page(struct qed_chain *p_chain) +static inline u8 qed_chain_get_unusable_per_page(struct qed_chain *p_chain) { return p_chain->elem_unusable; } @@ -198,7 +213,7 @@ static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) { - return p_chain->pbl.p_phys_table; + return p_chain->pbl_sp.p_phys_table; } /** @@ -214,10 +229,10 @@ static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) static inline void qed_chain_advance_page(struct qed_chain *p_chain, void **p_next_elem, void *idx_to_inc, void *page_to_inc) - { struct qed_chain_next *p_next = NULL; u32 page_index = 0; + switch (p_chain->mode) { case QED_CHAIN_MODE_NEXT_PTR: p_next = *p_next_elem; @@ -305,7 +320,7 @@ static inline void *qed_chain_produce(struct qed_chain *p_chain) if ((p_chain->u.chain16.prod_idx & p_chain->elem_per_page_mask) == p_chain->next_page_mask) { p_prod_idx = &p_chain->u.chain16.prod_idx; - p_prod_page_idx = &p_chain->pbl.u.pbl16.prod_page_idx; + p_prod_page_idx = &p_chain->pbl.c.u16.prod_page_idx; qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, p_prod_idx, p_prod_page_idx); } @@ -314,7 +329,7 @@ static inline void *qed_chain_produce(struct qed_chain *p_chain) if ((p_chain->u.chain32.prod_idx & p_chain->elem_per_page_mask) == p_chain->next_page_mask) { p_prod_idx = &p_chain->u.chain32.prod_idx; - p_prod_page_idx = &p_chain->pbl.u.pbl32.prod_page_idx; + p_prod_page_idx = &p_chain->pbl.c.u32.prod_page_idx; qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, p_prod_idx, p_prod_page_idx); } @@ -378,7 +393,7 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) if ((p_chain->u.chain16.cons_idx & p_chain->elem_per_page_mask) == p_chain->next_page_mask) { p_cons_idx = &p_chain->u.chain16.cons_idx; - p_cons_page_idx = &p_chain->pbl.u.pbl16.cons_page_idx; + p_cons_page_idx = &p_chain->pbl.c.u16.cons_page_idx; qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, p_cons_idx, p_cons_page_idx); } @@ -387,8 +402,8 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) if ((p_chain->u.chain32.cons_idx & p_chain->elem_per_page_mask) == p_chain->next_page_mask) { p_cons_idx = &p_chain->u.chain32.cons_idx; - p_cons_page_idx = &p_chain->pbl.u.pbl32.cons_page_idx; - qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, + p_cons_page_idx = &p_chain->pbl.c.u32.cons_page_idx; + qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, p_cons_idx, p_cons_page_idx); } p_chain->u.chain32.cons_idx++; @@ -429,25 +444,26 @@ static inline void qed_chain_reset(struct qed_chain *p_chain) u32 reset_val = p_chain->page_cnt - 1; if (is_chain_u16(p_chain)) { - p_chain->pbl.u.pbl16.prod_page_idx = (u16)reset_val; - p_chain->pbl.u.pbl16.cons_page_idx = (u16)reset_val; + p_chain->pbl.c.u16.prod_page_idx = (u16)reset_val; + p_chain->pbl.c.u16.cons_page_idx = (u16)reset_val; } else { - p_chain->pbl.u.pbl32.prod_page_idx = reset_val; - p_chain->pbl.u.pbl32.cons_page_idx = reset_val; + p_chain->pbl.c.u32.prod_page_idx = reset_val; + p_chain->pbl.c.u32.cons_page_idx = reset_val; } } switch (p_chain->intended_use) { - case QED_CHAIN_USE_TO_CONSUME_PRODUCE: - case QED_CHAIN_USE_TO_PRODUCE: - /* Do nothing */ - break; - case QED_CHAIN_USE_TO_CONSUME: /* produce empty elements */ for (i = 0; i < p_chain->capacity; i++) qed_chain_recycle_consumed(p_chain); break; + + case QED_CHAIN_USE_TO_CONSUME_PRODUCE: + case QED_CHAIN_USE_TO_PRODUCE: + default: + /* Do nothing */ + break; } } @@ -473,13 +489,13 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain, p_chain->p_virt_addr = NULL; p_chain->p_phys_addr = 0; p_chain->elem_size = elem_size; - p_chain->intended_use = intended_use; + p_chain->intended_use = (u8)intended_use; p_chain->mode = mode; - p_chain->cnt_type = cnt_type; + p_chain->cnt_type = (u8)cnt_type; - p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); + p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); p_chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; + p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); p_chain->next_page_mask = (p_chain->usable_per_page & p_chain->elem_per_page_mask); @@ -488,8 +504,8 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain, p_chain->capacity = p_chain->usable_per_page * page_cnt; p_chain->size = p_chain->elem_per_page * page_cnt; - p_chain->pbl.p_phys_table = 0; - p_chain->pbl.p_virt_table = NULL; + p_chain->pbl_sp.p_phys_table = 0; + p_chain->pbl_sp.p_virt_table = NULL; p_chain->pbl.pp_virt_addr_tbl = NULL; } @@ -530,8 +546,8 @@ static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, dma_addr_t p_phys_pbl, void **pp_virt_addr_tbl) { - p_chain->pbl.p_phys_table = p_phys_pbl; - p_chain->pbl.p_virt_table = p_virt_pbl; + p_chain->pbl_sp.p_phys_table = p_phys_pbl; + p_chain->pbl_sp.p_virt_table = p_virt_pbl; p_chain->pbl.pp_virt_addr_tbl = pp_virt_addr_tbl; } -- cgit From 3da7a37ae6886cfba9ef35428eb976fc2ef561fa Mon Sep 17 00:00:00 2001 From: "Mintz, Yuval" Date: Tue, 29 Nov 2016 16:47:06 +0200 Subject: qed*: Handle-based L2-queues. The driver needs to maintain several FW/HW-indices for each one of its queues. Currently, that mapping is done by the QED where it uses an rx/tx array of so-called hw-cids, populating them whenever a new queue is opened and clearing them upon destruction of said queues. This maintenance is far from ideal - there's no real reason why QED needs to maintain such a data-structure. It becomes even worse when considering the fact that the PF's queues and its child VFs' queues are all mapped into the same data-structure. As a by-product, the set of parameters an interface needs to supply for queue APIs is non-trivial, and some of the variables in the API structures have different meaning depending on their exact place in the configuration flow. This patch re-organizes the way L2 queues are configured and maintained. In short: - Required parameters for queue init are now well-defined. - Qed would allocate a queue-cid based on parameters. Upon initialization success, it would return a handle to caller. - Queue-handle would be maintained by entity requesting queue-init, not necessarily qed. - All further queue-APIs [update, destroy] would use the opaque handle as reference for the queue instead of various indices. The possible owners of such handles: - PF queues [qede] - complete handles based on provided configuration. - VF queues [qede] - fw-context-less handles, containing only relative information; Only the PF-side would need the absolute indices for configuration, so they're omitted here. - VF queues [qed, PF-side] - complete handles based on VF initialization. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 56 ++++++++++++++++++++++-------------------- 1 file changed, 29 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 9755a3feb52e..7a52f7c58c37 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -15,6 +15,29 @@ #include #include +struct qed_queue_start_common_params { + /* Should always be relative to entity sending this. */ + u8 vport_id; + u16 queue_id; + + /* Relative, but relevant only for PFs */ + u8 stats_id; + + /* These are always absolute */ + u16 sb; + u8 sb_idx; +}; + +struct qed_rxq_start_ret_params { + void __iomem *p_prod; + void *p_handle; +}; + +struct qed_txq_start_ret_params { + void __iomem *p_doorbell; + void *p_handle; +}; + struct qed_dev_eth_info { struct qed_dev_info common; @@ -56,18 +79,6 @@ struct qed_start_vport_params { bool clear_stats; }; -struct qed_stop_rxq_params { - u8 rss_id; - u8 rx_queue_id; - u8 vport_id; - bool eq_completion_only; -}; - -struct qed_stop_txq_params { - u8 rss_id; - u8 tx_queue_id; -}; - enum qed_filter_rx_mode_type { QED_FILTER_RX_MODE_TYPE_REGULAR, QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC, @@ -112,15 +123,6 @@ struct qed_filter_params { union qed_filter_type_params filter; }; -struct qed_queue_start_common_params { - u8 rss_id; - u8 queue_id; - u8 vport_id; - u16 sb; - u16 sb_idx; - u16 vf_qid; -}; - struct qed_tunn_params { u16 vxlan_port; u8 update_vxlan_port; @@ -220,24 +222,24 @@ struct qed_eth_ops { struct qed_update_vport_params *params); int (*q_rx_start)(struct qed_dev *cdev, + u8 rss_num, struct qed_queue_start_common_params *params, u16 bd_max_bytes, dma_addr_t bd_chain_phys_addr, dma_addr_t cqe_pbl_addr, u16 cqe_pbl_size, - void __iomem **pp_prod); + struct qed_rxq_start_ret_params *ret_params); - int (*q_rx_stop)(struct qed_dev *cdev, - struct qed_stop_rxq_params *params); + int (*q_rx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle); int (*q_tx_start)(struct qed_dev *cdev, + u8 rss_num, struct qed_queue_start_common_params *params, dma_addr_t pbl_addr, u16 pbl_size, - void __iomem **pp_doorbell); + struct qed_txq_start_ret_params *ret_params); - int (*q_tx_stop)(struct qed_dev *cdev, - struct qed_stop_txq_params *params); + int (*q_tx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle); int (*filter_config)(struct qed_dev *cdev, struct qed_filter_params *params); -- cgit From 91291d9ad92faa65a56a9a19d658d8049b78d3d4 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 30 Nov 2016 16:21:25 +0530 Subject: PM / OPP: Pass opp_table to dev_pm_opp_put_regulator() Joonyoung Shim reported an interesting problem on his ARM octa-core Odoroid-XU3 platform. During system suspend, dev_pm_opp_put_regulator() was failing for a struct device for which dev_pm_opp_set_regulator() is called earlier. This happened because an earlier call to dev_pm_opp_of_cpumask_remove_table() function (from cpufreq-dt.c file) removed all the entries from opp_table->dev_list apart from the last CPU device in the cpumask of CPUs sharing the OPP. But both dev_pm_opp_set_regulator() and dev_pm_opp_put_regulator() routines get CPU device for the first CPU in the cpumask. And so the OPP core failed to find the OPP table for the struct device. This patch attempts to fix this problem by returning a pointer to the opp_table from dev_pm_opp_set_regulator() and using that as the parameter to dev_pm_opp_put_regulator(). This ensures that the dev_pm_opp_put_regulator() doesn't fail to find the opp table. Note that similar design problem also exists with other dev_pm_opp_put_*() APIs, but those aren't used currently by anyone and so we don't need to update them for now. Cc: 4.4+ # 4.4+ Reported-by: Joonyoung Shim Signed-off-by: Stephen Boyd Signed-off-by: Viresh Kumar [ Viresh: Wrote commit log and tested on exynos 5250 ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index bca26157f5b6..f6bc76501912 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -19,6 +19,7 @@ struct dev_pm_opp; struct device; +struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, @@ -62,8 +63,8 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); -int dev_pm_opp_set_regulator(struct device *dev, const char *name); -void dev_pm_opp_put_regulator(struct device *dev); +struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name); +void dev_pm_opp_put_regulator(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -170,12 +171,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} -static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +static inline struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name) { - return -ENOTSUPP; + return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_put_regulator(struct device *dev) {} +static inline void dev_pm_opp_put_regulator(struct opp_table *opp_table) {} static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { -- cgit From 5fdca6531434c1c1b2d584873afdda52e5ad448c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Nov 2016 11:04:42 -0500 Subject: svcrdma: Renovate sendto chunk list parsing The current sendto code appears to support clients that provide only one of a Read list, a Write list, or a Reply chunk. My reading of that code is that it doesn't support the following cases: - Read list + Write list - Read list + Reply chunk - Write list + Reply chunk - Read list + Write list + Reply chunk The protocol allows more than one Read or Write chunk in those lists. Some clients do send a Read list and Reply chunk simultaneously. NFSv4 WRITE uses a Read list for the data payload, and a Reply chunk because the GETATTR result in the reply can contain a large object like an ACL. Generalize one of the sendto code paths needed to support all of the above cases, and attempt to ensure that only one pass is done through the RPC Call's transport header to gather chunk list information for building the reply. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cc3ae16eac68..6aef63b9a669 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -236,8 +236,6 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *, struct svc_rdma_req_map *, bool); extern int svc_rdma_sendto(struct svc_rqst *); -extern struct rpcrdma_read_chunk * - svc_rdma_get_read_chunk(struct rpcrdma_msg *); extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, int); -- cgit From e4eb42cecc6dc546aac888ee4913d59121e886ee Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Nov 2016 11:04:50 -0500 Subject: svcrdma: Remove BH-disabled spin locking in svc_rdma_send() svcrdma's current SQ accounting algorithm takes sc_lock and disables bottom-halves while posting all RDMA Read, Write, and Send WRs. This is relatively heavyweight serialization. And note that Write and Send are already fully serialized by the xpt_mutex. Using a single atomic_t should be all that is necessary to guarantee that ib_post_send() is called only when there is enough space on the send queue. This is what the other RDMA-enabled storage targets do. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 6aef63b9a669..601cb07aa746 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -139,7 +139,7 @@ struct svcxprt_rdma { int sc_max_sge_rd; /* max sge for read target */ bool sc_snd_w_inv; /* OK to use Send With Invalidate */ - atomic_t sc_sq_count; /* Number of SQ WR on queue */ + atomic_t sc_sq_avail; /* SQEs ready to be consumed */ unsigned int sc_sq_depth; /* Depth of SQ */ unsigned int sc_rq_depth; /* Depth of RQ */ u32 sc_max_requests; /* Forward credits */ -- cgit From dd6fd213b05e7a1f590b470500343dd97c3a32c1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Nov 2016 11:04:58 -0500 Subject: svcrdma: Remove DMA map accounting Clean up: sc_dma_used is not required for correct operation. It is simply a debugging tool to report when svcrdma has leaked DMA maps. However, manipulating an atomic has a measurable CPU cost, and DMA map accounting specific to svcrdma will be meaningless once svcrdma is converted to use the new generic r/w API. A similar kind of debug accounting can be done simply by enabling the IOMMU or by using CONFIG_DMA_API_DEBUG, CONFIG_IOMMU_DEBUG, and CONFIG_IOMMU_LEAK. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 601cb07aa746..43d7c709d117 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -148,7 +148,6 @@ struct svcxprt_rdma { struct ib_pd *sc_pd; - atomic_t sc_dma_used; spinlock_t sc_ctxt_lock; struct list_head sc_ctxts; int sc_ctxt_used; @@ -200,7 +199,6 @@ static inline void svc_rdma_count_mappings(struct svcxprt_rdma *rdma, struct svc_rdma_op_ctxt *ctxt) { ctxt->mapped_sges++; - atomic_inc(&rdma->sc_dma_used); } /* svc_rdma_backchannel.c */ -- cgit From 96a58f9c1921f28fab5ed008be791adacb540cc6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Nov 2016 11:05:07 -0500 Subject: svcrdma: Remove svc_rdma_op_ctxt::wc_status Clean up: Completion status is already reported in the individual completion handlers. Save a few bytes in struct svc_rdma_op_ctxt. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 43d7c709d117..757fb963696c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -79,7 +79,6 @@ struct svc_rdma_op_ctxt { struct ib_cqe reg_cqe; struct ib_cqe inv_cqe; struct list_head dto_q; - enum ib_wc_status wc_status; u32 byte_len; u32 position; struct svcxprt_rdma *xprt; -- cgit From 0a135b88bceac40d0036e401c19cdbda65b38a8f Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 30 Nov 2016 17:01:50 -0800 Subject: Input: synaptics-rmi4 - have only one struct platform data If struct rmi_device_platform_data contains pointers to other struct, it gets difficult to allocate a fixed size struct and copy it over between drivers. Change the pointers into a struct and change the code in rmi4 accordingly. Reviewed-by: Andrew Duggan Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 621f098f1243..7780e40a2573 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -218,9 +218,9 @@ struct rmi_device_platform_data { struct rmi_device_platform_data_spi spi_data; /* function handler pdata */ - struct rmi_2d_sensor_platform_data *sensor_pdata; + struct rmi_2d_sensor_platform_data sensor_pdata; struct rmi_f01_power_management power_management; - struct rmi_f30_data *f30_data; + struct rmi_f30_data f30_data; }; /** -- cgit From e16769d4bca67218531505ad1a8365d227fedcf9 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Mon, 28 Nov 2016 13:22:42 +0100 Subject: fs: configfs: don't return anything from drop_link Documentation/filesystems/configfs/configfs.txt says: "When unlink(2) is called on the symbolic link, the source item is notified via the ->drop_link() method. Like the ->drop_item() method, this is a void function and cannot return failure." The ->drop_item() is indeed a void function, the ->drop_link() is actually not. This, together with the fact that the value of ->drop_link() is silently ignored suggests, that it is the ->drop_link() return type that should be corrected and changed to void. This patch changes drop_link() signature and all its users. Signed-off-by: Andrzej Pietrasiewicz [hch: reverted reformatting of some code] Signed-off-by: Christoph Hellwig --- include/linux/configfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index d9d6a9d77489..9a30b921f740 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -228,7 +228,7 @@ static struct configfs_bin_attribute _pfx##attr_##_name = { \ struct configfs_item_operations { void (*release)(struct config_item *); int (*allow_link)(struct config_item *src, struct config_item *target); - int (*drop_link)(struct config_item *src, struct config_item *target); + void (*drop_link)(struct config_item *src, struct config_item *target); }; struct configfs_group_operations { -- cgit From 864e0981fd1bc042c6e932d1731d358dde60fed9 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Wed, 30 Nov 2016 15:16:08 +0200 Subject: crypto: api - fix comment typo Signed-off-by: Baruch Siach Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 8348d83d8b5e..167aea29d41e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -90,7 +90,7 @@ #define CRYPTO_ALG_TESTED 0x00000400 /* - * Set if the algorithm is an instance that is build from templates. + * Set if the algorithm is an instance that is built from templates. */ #define CRYPTO_ALG_INSTANCE 0x00000800 -- cgit From 4a057549d6044c2dea47e80f8369a76225ec9d90 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 28 Nov 2016 14:35:21 -0800 Subject: alarmtimer: Add tracepoints for alarm timers Alarm timers are one of the mechanisms to wake up a system from suspend, but there exist no tracepoints to analyse which process/thread armed an alarmtimer. Add tracepoints for start/cancel/expire of individual alarm timers and one for tracing the suspend time decision when to resume the system. The following trace excerpt illustrates the new mechanism: Binder:3292_2-3304 [000] d..2 149.981123: alarmtimer_cancel: alarmtimer:ffffffc1319a7800 type:REALTIME expires:1325463120000000000 now:1325376810370370245 Binder:3292_2-3304 [000] d..2 149.981136: alarmtimer_start: alarmtimer:ffffffc1319a7800 type:REALTIME expires:1325376840000000000 now:1325376810370384591 Binder:3292_9-3953 [000] d..2 150.212991: alarmtimer_cancel: alarmtimer:ffffffc1319a5a00 type:BOOTTIME expires:179552000000 now:150154008122 Binder:3292_9-3953 [000] d..2 150.213006: alarmtimer_start: alarmtimer:ffffffc1319a5a00 type:BOOTTIME expires:179551000000 now:150154025622 system_server-3000 [002] ...1 162.701940: alarmtimer_suspend: alarmtimer type:REALTIME expires:1325376840000000000 The wakeup time which is selected at suspend time allows to map it back to the task arming the timer: Binder:3292_2. [ tglx: Store alarm timer expiry time instead of some useless RTC relative information, add proper type information for wakeups which are handled via the clock_nanosleep/freezer and massage the changelog. ] Signed-off-by: Baolin Wang Signed-off-by: John Stultz Acked-by: Steven Rostedt Cc: Prarit Bhargava Cc: Richard Cochran Link: http://lkml.kernel.org/r/1480372524-15181-5-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/alarmtimer.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 9d8031257a90..c70aac13244a 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -10,7 +10,12 @@ enum alarmtimer_type { ALARM_REALTIME, ALARM_BOOTTIME, + /* Supported types end here */ ALARM_NUMTYPE, + + /* Used for tracing information. No usable types. */ + ALARM_REALTIME_FREEZER, + ALARM_BOOTTIME_FREEZER, }; enum alarmtimer_restart { -- cgit From e73c23ff736e1ea371dfa419d7bf8e77ee53044a Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 30 Nov 2016 12:28:58 -0800 Subject: block: add async variant of blkdev_issue_zeroout Similar to __blkdev_issue_discard this variant allows submitting the final bio asynchronously and chaining multiple ranges into a single completion. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 541fdd8787a5..7e9d8a0895be 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1269,6 +1269,9 @@ extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct bio **biop); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); +extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, + bool discard); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, bool discard); static inline int sb_issue_discard(struct super_block *sb, sector_t block, -- cgit From a6f0788ec2881ac14e97ff7fa6a78a807f87b5ba Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 30 Nov 2016 12:28:59 -0800 Subject: block: add support for REQ_OP_WRITE_ZEROES This adds a new block layer operation to zero out a range of LBAs. This allows to implement zeroing for devices that don't use either discard with a predictable zero pattern or WRITE SAME of zeroes. The prominent example of that is NVMe with the Write Zeroes command, but in the future, this should also help with improving the way zeroing discards work. For this operation, suitable entry is exported in sysfs which indicate the number of maximum bytes allowed in one write zeroes operation by the device. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 25 ++++++++++++++----------- include/linux/blk_types.h | 2 ++ include/linux/blkdev.h | 19 +++++++++++++++++++ 3 files changed, 35 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 70a7244f08a7..b15323934a29 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -76,7 +76,8 @@ static inline bool bio_has_data(struct bio *bio) if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && - bio_op(bio) != REQ_OP_SECURE_ERASE) + bio_op(bio) != REQ_OP_SECURE_ERASE && + bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; @@ -86,7 +87,8 @@ static inline bool bio_no_advance_iter(struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_SAME; + bio_op(bio) == REQ_OP_WRITE_SAME || + bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline bool bio_mergeable(struct bio *bio) @@ -188,18 +190,19 @@ static inline unsigned bio_segments(struct bio *bio) struct bvec_iter iter; /* - * We special case discard/write same, because they interpret bi_size - * differently: + * We special case discard/write same/write zeroes, because they + * interpret bi_size differently: */ - if (bio_op(bio) == REQ_OP_DISCARD) - return 1; - - if (bio_op(bio) == REQ_OP_SECURE_ERASE) - return 1; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE_ZEROES: return 1; + default: + break; + } bio_for_each_segment(bv, bio, iter) segs++; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f57458a6a93b..519ea2c9df61 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -159,6 +159,8 @@ enum req_opf { REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, + /* write the zero filled sector many times */ + REQ_OP_WRITE_ZEROES = 8, REQ_OP_LAST, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e9d8a0895be..ebeef2b79c5a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -323,6 +323,7 @@ struct queue_limits { unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; + unsigned int max_write_zeroes_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -774,6 +775,9 @@ static inline bool rq_mergeable(struct request *rq) if (req_op(rq) == REQ_OP_FLUSH) return false; + if (req_op(rq) == REQ_OP_WRITE_ZEROES) + return false; + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) @@ -1004,6 +1008,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; + if (unlikely(op == REQ_OP_WRITE_ZEROES)) + return q->limits.max_write_zeroes_sectors; + return q->limits.max_sectors; } @@ -1107,6 +1114,8 @@ extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); +extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, + unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, @@ -1475,6 +1484,16 @@ static inline unsigned int bdev_write_same(struct block_device *bdev) return 0; } +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit From 3b7c33b28a44d4621e365e090bf8bd332ab232a1 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 30 Nov 2016 12:29:00 -0800 Subject: nvme.h: add Write Zeroes definitions Add the command structure, optional command set support (ONCS) bit and a new error code for the Write Zeroes command. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 18ce9f7cc881..0df9466a7c38 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -237,6 +237,7 @@ enum { NVME_CTRL_ONCS_COMPARE = 1 << 0, NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, + NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, NVME_CTRL_VWC_PRESENT = 1 << 0, }; @@ -543,6 +544,23 @@ struct nvme_dsm_range { __le64 slba; }; +struct nvme_write_zeroes_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2; + __le64 metadata; + union nvme_data_ptr dptr; + __le64 slba; + __le16 length; + __le16 control; + __le32 dsmgmt; + __le32 reftag; + __le16 apptag; + __le16 appmask; +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -839,6 +857,7 @@ struct nvme_command { struct nvme_download_firmware dlfw; struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; + struct nvme_write_zeroes_cmd write_zeroes; struct nvme_abort_cmd abort; struct nvme_get_log_page_command get_log_page; struct nvmf_common_command fabrics; @@ -918,6 +937,7 @@ enum { NVME_SC_BAD_ATTRIBUTES = 0x180, NVME_SC_INVALID_PI = 0x181, NVME_SC_READ_ONLY = 0x182, + NVME_SC_ONCS_NOT_SUPPORTED = 0x183, /* * I/O Command Set Specific - Fabrics commands: -- cgit From f4ed2fe34fb793755ef8cfc3509e783c4709ffc1 Mon Sep 17 00:00:00 2001 From: Raju Lakkaraju Date: Tue, 29 Nov 2016 15:16:46 +0530 Subject: net: phy: add mdix_ctrl to hold the user configuration. Add new parameter mdix_ctrl to hold the user configuration. Existing mdix maintain the current status of MDI(X) crossover performed or not. mdix_ctrl can configure either ETH_TP_MDI or ETH_TP_MDI_X orETH_TP_MDI_AUTO. Signed-off-by: Raju Lakkaraju Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index b53177fd38af..feb8a98e8dd3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -450,6 +450,7 @@ struct phy_device { struct net_device *attached_dev; u8 mdix; + u8 mdix_ctrl; void (*adjust_link)(struct net_device *dev); }; -- cgit From 22195cbd3451a75abaf30651a61cf85c89061327 Mon Sep 17 00:00:00 2001 From: Jike Song Date: Thu, 1 Dec 2016 13:20:05 +0800 Subject: vfio: vfio_register_notifier: classify iommu notifier Currently vfio_register_notifier assumes that there is only one notifier chain, which is in vfio_iommu. However, the user might also be interested in events other than vfio_iommu, for example, vfio_group. Refactor vfio_{un}register_notifier implementation to make it feasible. Cc: Paolo Bonzini Cc: Xiao Guangrong Reviewed-by: Kirti Wankhede Signed-off-by: Jike Song [aw: merge with commit 816ca69ea9c7 ("vfio: Fix handling of error returned by 'vfio_group_get_from_dev()'"), remove typedef] Signed-off-by: Alex Williamson --- include/linux/vfio.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 15ff0421b423..0e5201f207d3 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -81,6 +81,7 @@ struct vfio_iommu_driver_ops { int (*unpin_pages)(void *iommu_data, unsigned long *user_pfn, int npage); int (*register_notifier)(void *iommu_data, + unsigned long *events, struct notifier_block *nb); int (*unregister_notifier)(void *iommu_data, struct notifier_block *nb); @@ -107,12 +108,20 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage); -#define VFIO_IOMMU_NOTIFY_DMA_UNMAP (1) +/* each type has independent events */ +enum vfio_notify_type { + VFIO_IOMMU_NOTIFY = 0, +}; + +/* events for VFIO_IOMMU_NOTIFY */ +#define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) extern int vfio_register_notifier(struct device *dev, + enum vfio_notify_type type, + unsigned long *required_events, struct notifier_block *nb); - extern int vfio_unregister_notifier(struct device *dev, + enum vfio_notify_type type, struct notifier_block *nb); /* -- cgit From ccd46dbae77dbf0d33f42e04b59536f108c395e8 Mon Sep 17 00:00:00 2001 From: Jike Song Date: Thu, 1 Dec 2016 13:20:06 +0800 Subject: vfio: support notifier chain in vfio_group Beyond vfio_iommu events, users might also be interested in vfio_group events. For example, if a vfio_group is used along with Qemu/KVM, whenever kvm pointer is set to/cleared from the vfio_group, users could be notified. Currently only VFIO_GROUP_NOTIFY_SET_KVM supported. Cc: Kirti Wankhede Cc: Paolo Bonzini Cc: Xiao Guangrong Signed-off-by: Jike Song [aw: remove use of new typedef] Signed-off-by: Alex Williamson --- include/linux/vfio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 0e5201f207d3..edf9b2cad277 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -111,11 +111,15 @@ extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, + VFIO_GROUP_NOTIFY = 1, }; /* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) +/* events for VFIO_GROUP_NOTIFY */ +#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) + extern int vfio_register_notifier(struct device *dev, enum vfio_notify_type type, unsigned long *required_events, @@ -124,6 +128,9 @@ extern int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type, struct notifier_block *nb); +struct kvm; +extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm); + /* * Sub-module helpers */ -- cgit From 00710984eac523ffed4e92850511d7610cfe908b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 30 Nov 2016 14:47:13 -0600 Subject: ACPI: Add acpi_resource_consumer() to find device that claims a resource Add acpi_resource_consumer(). This takes a struct resource and searches the ACPI namespace for a device whose current resource settings (_CRS) includes the resource. It returns the device if it exists, or NULL if no device uses the resource. If more than one device uses the resource (this may happen in the case of bridges), acpi_resource_consumer() returns the first one found by acpi_get_devices() in its modified depth-first walk of the namespace. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ddbeda6dbdc8..b00ad73c946d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -419,6 +419,8 @@ static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } +struct acpi_device *acpi_resource_consumer(struct resource *res); + int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, @@ -762,6 +764,11 @@ static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) return -EINVAL; } +static inline struct acpi_device *acpi_resource_consumer(struct resource *res) +{ + return NULL; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit From cf80516579ceb87b91205e68fb31d5affd5aea8d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 15 Nov 2016 14:56:07 -0500 Subject: NFSv4: Add encode/decode of the layoutreturn op in CLOSE Add XDR encoding for the layoutreturn op, and storage for the layoutreturn arguments to the CLOSE compound. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index beb1e10f446e..44ed64bb66ae 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -469,6 +469,7 @@ struct nfs_closeargs { fmode_t fmode; u32 share_access; const u32 * bitmask; + struct nfs4_layoutreturn_args *lr_args; }; struct nfs_closeres { @@ -477,6 +478,8 @@ struct nfs_closeres { struct nfs_fattr * fattr; struct nfs_seqid * seqid; const struct nfs_server *server; + struct nfs4_layoutreturn_res *lr_res; + int lr_ret; }; /* * * Arguments to the lock,lockt, and locku call. -- cgit From 586f1c39daf5c840c742b9be1ec236429f26dc13 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 15 Nov 2016 15:03:33 -0500 Subject: NFSv4: Add encode/decode of the layoutreturn op in DELEGRETURN Add XDR encoding for the layoutreturn op, and storage for the layoutreturn arguments to the DELEGRETURN compound. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 44ed64bb66ae..bfbd0cace91b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -552,12 +552,15 @@ struct nfs4_delegreturnargs { const struct nfs_fh *fhandle; const nfs4_stateid *stateid; const u32 * bitmask; + struct nfs4_layoutreturn_args *lr_args; }; struct nfs4_delegreturnres { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; struct nfs_server *server; + struct nfs4_layoutreturn_res *lr_res; + int lr_ret; }; /* -- cgit From b184b5c38e4640585126e44ef84f2dbdd0d23d5a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 13 Oct 2016 15:26:47 +1100 Subject: NFS: remove l_pid field from nfs_lockowner this field is not used in any important way and probably should have been removed by Commit: 8003d3c4aaa5 ("nfs4: treat lock owners as opaque values") which removed the pid argument from nfs4_get_lock_state. Except in unusual and uninteresting cases, two threads with the same ->tgid will have the same ->files pointer, so keeping them both for comparison brings no benefit. Acked-by: Jeff Layton Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 810124b33327..bf8a713c45b4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -57,7 +57,6 @@ struct nfs_access_entry { struct nfs_lockowner { fl_owner_t l_owner; - pid_t l_pid; }; struct nfs_lock_context { -- cgit From 532d4def2f95623a9b8b2cef7723e14521377911 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 13 Oct 2016 15:26:47 +1100 Subject: NFSv4: add flock_owner to open context An open file description (struct file) in a given process can be associated with two different lock owners. It can have a Posix lock owner which will be different in each process that has a fd on the file. It can have a Flock owner which will be the same in all processes. When searching for a lock stateid to use, we need to consider both of these owners So add a new "flock_owner" to the "nfs_open_context" (of which there is one for each open file description). This flock_owner does not need to be reference-counted as there is a 1-1 relation between 'struct file' and nfs open contexts, and it will never be part of a list of contexts. So there is no need for a 'flock_context' - just the owner is enough. The io_count included in the (Posix) lock_context provides no guarantee that all read-aheads that could use the state have completed, so not supporting it for flock locks in not a serious problem. Synchronization between flock and read-ahead can be added later if needed. When creating an open_context for a non-openning create call, we don't have a 'struct file' to pass in, so the lock context gets initialized with a NULL owner, but this will never be used. The flock_owner is not used at all in this patch, that will come later. Acked-by: Jeff Layton Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf8a713c45b4..0adb02c4744d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -70,6 +70,7 @@ struct nfs_lock_context { struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; + fl_owner_t flock_owner; struct dentry *dentry; struct rpc_cred *cred; struct nfs4_state *state; @@ -357,7 +358,7 @@ extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode); -extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode); +extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp); extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); extern void nfs_file_clear_open_context(struct file *flip); -- cgit From d51fdb87a611f8ef50518df7187173ae10469fd0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 13 Oct 2016 15:26:47 +1100 Subject: NFS: discard nfs_lockowner structure. It now has only one field and is only used in one structure. So replaced it in that structure by the field it contains. Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 0adb02c4744d..db1002abc95e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -55,15 +55,11 @@ struct nfs_access_entry { struct rcu_head rcu_head; }; -struct nfs_lockowner { - fl_owner_t l_owner; -}; - struct nfs_lock_context { atomic_t count; struct list_head list; struct nfs_open_context *open_context; - struct nfs_lockowner lockowner; + fl_owner_t lockowner; atomic_t io_count; }; -- cgit From b32614c03413f8a6025d8677c2b7c0ee976e63d4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 27 Nov 2016 00:13:34 +0100 Subject: tracing/rb: Convert to hotplug state machine Install the callbacks via the state machine. The notifier in struct ring_buffer is replaced by the multi instance interface. Upon __ring_buffer_alloc() invocation, cpuhp_state_add_instance() will invoke the trace_rb_cpu_prepare() on each CPU. This callback may now fail. This means __ring_buffer_alloc() will fail and cleanup (like previously) and during a CPU up event this failure will not allow the CPU to come up. Signed-off-by: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161126231350.10321-7-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + include/linux/ring_buffer.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e3771fb959c0..18bcfeb2463e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -62,6 +62,7 @@ enum cpuhp_state { CPUHP_TOPOLOGY_PREPARE, CPUHP_NET_IUCV_PREPARE, CPUHP_ARM_BL_PREPARE, + CPUHP_TRACE_RB_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 4acc552e9279..b6d4568795a7 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -198,4 +198,10 @@ enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, }; +#ifdef CONFIG_RING_BUFFER +int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); +#else +#define trace_rb_cpu_prepare NULL +#endif + #endif /* _LINUX_RING_BUFFER_H */ -- cgit From 5438da977f83c945d4e72ee4f9c4508c0eb64e15 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Nov 2016 15:52:21 +0100 Subject: mm/vmstat: Convert to hotplug state machine Install the callbacks via the state machine, but do not invoke them as we can initialize the node state without calling the callbacks on all online CPUs. start_shepherd_timer() is now called outside the get_online_cpus() block which is safe as it only operates on cpu possible mask. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: linux-mm@kvack.org Cc: rt@linutronix.de Cc: Johannes Weiner Cc: Andrew Morton Cc: Mel Gorman Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20161129145221.ffc3kg3hd7lxiwj6@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 18bcfeb2463e..4ebd1bc27f8d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -20,6 +20,7 @@ enum cpuhp_state { CPUHP_VIRT_NET_DEAD, CPUHP_SLUB_DEAD, CPUHP_MM_WRITEBACK_DEAD, + CPUHP_MM_VMSTAT_DEAD, CPUHP_SOFTIRQ_DEAD, CPUHP_NET_MVNETA_DEAD, CPUHP_CPUIDLE_DEAD, -- cgit From 215c89d055e085c42cea4fd571a1d0db0b6d5648 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 27 Nov 2016 00:13:38 +0100 Subject: mm/zsmalloc: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Cc: Sergey Senozhatsky Cc: linux-mm@kvack.org Cc: Minchan Kim Cc: rt@linutronix.de Cc: Nitin Gupta Link: http://lkml.kernel.org/r/20161126231350.10321-11-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4ebd1bc27f8d..9f29dd996088 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -64,6 +64,7 @@ enum cpuhp_state { CPUHP_NET_IUCV_PREPARE, CPUHP_ARM_BL_PREPARE, CPUHP_TRACE_RB_PREPARE, + CPUHP_MM_ZS_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From ad7ed7708db9ff388450935645816d44bf08a56d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 27 Nov 2016 00:13:39 +0100 Subject: mm/zswap: Convert dst-mem to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Cc: linux-mm@kvack.org Cc: Seth Jennings Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161126231350.10321-12-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 9f29dd996088..62f51a4e8676 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -65,6 +65,7 @@ enum cpuhp_state { CPUHP_ARM_BL_PREPARE, CPUHP_TRACE_RB_PREPARE, CPUHP_MM_ZS_PREPARE, + CPUHP_MM_ZSWP_MEM_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From cab7a7e5b6c5c2638b00c72559ff9fb715583c98 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 27 Nov 2016 00:13:40 +0100 Subject: mm/zswap: Convert pool to hotplug state machine Install the callbacks via the state machine. Multi state is used to address the per-pool notifier. Uppon adding of the intance the callback is invoked for all online CPUs so the manual init can go. Signed-off-by: Sebastian Andrzej Siewior Cc: linux-mm@kvack.org Cc: Seth Jennings Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161126231350.10321-13-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 62f51a4e8676..c7d0d76ef0ee 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -66,6 +66,7 @@ enum cpuhp_state { CPUHP_TRACE_RB_PREPARE, CPUHP_MM_ZS_PREPARE, CPUHP_MM_ZSWP_MEM_PREPARE, + CPUHP_MM_ZSWP_POOL_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 21647615db288d9dacad0de6a5df846b39d51bea Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Sun, 27 Nov 2016 00:13:41 +0100 Subject: iommu/vt-d: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Cc: Joerg Roedel Cc: iommu@lists.linux-foundation.org Cc: rt@linutronix.de Cc: David Woodhouse Link: http://lkml.kernel.org/r/20161126231350.10321-14-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c7d0d76ef0ee..853f8176594d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -40,6 +40,7 @@ enum cpuhp_state { CPUHP_PAGE_ALLOC_DEAD, CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, + CPUHP_IOMMU_INTEL_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 3f7cd919f3df05918535de39273174710409eb40 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Sun, 27 Nov 2016 00:13:45 +0100 Subject: KVM/PPC/Book3S HV: Convert to hotplug state machine MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Install the callbacks via the state machine. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Cc: kvm@vger.kernel.org Cc: Radim Krčmář Cc: Benjamin Herrenschmidt Cc: linuxppc-dev@lists.ozlabs.org Cc: kvm-ppc@vger.kernel.org Cc: Paul Mackerras Cc: rt@linutronix.de Cc: Michael Ellerman Cc: Paolo Bonzini Cc: Alexander Graf Link: http://lkml.kernel.org/r/20161126231350.10321-18-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 853f8176594d..71c6822dd5be 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -68,6 +68,7 @@ enum cpuhp_state { CPUHP_MM_ZS_PREPARE, CPUHP_MM_ZSWP_MEM_PREPARE, CPUHP_MM_ZSWP_POOL_PREPARE, + CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 1dd6c834fa4a75a86fecefb6d1f1525f1cb755c7 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Sun, 27 Nov 2016 00:13:46 +0100 Subject: zram: Convert to hotplug state machine Install the callbacks via the state machine with multi instance support and let the core invoke the callbacks on the already online CPUs. [bigeasy: wire up the multi instance stuff] Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Sergey Senozhatsky Cc: Minchan Kim Cc: rt@linutronix.de Cc: Nitin Gupta Link: http://lkml.kernel.org/r/20161126231350.10321-19-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 71c6822dd5be..22acee76cf4c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -69,6 +69,7 @@ enum cpuhp_state { CPUHP_MM_ZSWP_MEM_PREPARE, CPUHP_MM_ZSWP_POOL_PREPARE, CPUHP_KVM_PPC_BOOK3S_PREPARE, + CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, -- cgit From 1c1b522808a18402f043c1418b4e48c7355480cc Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 30 Nov 2016 17:59:37 +0200 Subject: net/mlx5e: Implement Fragmented Work Queue (WQ) Add new type of struct mlx5_frag_buf which is used to allocate fragmented buffers rather than contiguous, and make the Completion Queues (CQs) use it as they are big (default of 2MB per CQ in Striding RQ). This fixes the failures of type: "mlx5e_open_locked: mlx5e_open_channels failed, -12" due to dma_zalloc_coherent insufficient contiguous coherent memory to satisfy the driver's request when the user tries to setup more or larger rings. Signed-off-by: Tariq Toukan Reported-by: Sebastian Ott Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 68b85efc3908..0ae55361e674 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -318,6 +318,13 @@ struct mlx5_buf { u8 page_shift; }; +struct mlx5_frag_buf { + struct mlx5_buf_list *frags; + int npages; + int size; + u8 page_shift; +}; + struct mlx5_eq_tasklet { struct list_head list; struct list_head process_list; @@ -822,6 +829,9 @@ int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); +int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, + struct mlx5_frag_buf *buf, int node); +void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, @@ -866,6 +876,7 @@ void mlx5_unregister_debugfs(void); int mlx5_eq_init(struct mlx5_core_dev *dev); void mlx5_eq_cleanup(struct mlx5_core_dev *dev); void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas); +void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn); void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type); #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING -- cgit From 3a0af8fd61f90920f6fa04e4f1e9a6a73c1b4fd2 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Wed, 30 Nov 2016 17:10:10 +0100 Subject: bpf: BPF for lightweight tunnel infrastructure Registers new BPF program types which correspond to the LWT hooks: - BPF_PROG_TYPE_LWT_IN => dst_input() - BPF_PROG_TYPE_LWT_OUT => dst_output() - BPF_PROG_TYPE_LWT_XMIT => lwtunnel_xmit() The separate program types are required to differentiate between the capabilities each LWT hook allows: * Programs attached to dst_input() or dst_output() are restricted and may only read the data of an skb. This prevent modification and possible invalidation of already validated packet headers on receive and the construction of illegal headers while the IP headers are still being assembled. * Programs attached to lwtunnel_xmit() are allowed to modify packet content as well as prepending an L2 header via a newly introduced helper bpf_skb_change_head(). This is safe as lwtunnel_xmit() is invoked after the IP header has been assembled completely. All BPF programs receive an skb with L3 headers attached and may return one of the following error codes: BPF_OK - Continue routing as per nexthop BPF_DROP - Drop skb and return EPERM BPF_REDIRECT - Redirect skb to device as per redirect() helper. (Only valid in lwtunnel_xmit() context) The return codes are binary compatible with their TC_ACT_ relatives to ease compatibility. Signed-off-by: Thomas Graf Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7f246a281435..7ba644626553 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -438,7 +438,7 @@ struct xdp_buff { }; /* compute the linear packet data range [data, data_end) which - * will be accessed by cls_bpf and act_bpf programs + * will be accessed by cls_bpf, act_bpf and lwt programs */ static inline void bpf_compute_data_end(struct sk_buff *skb) { -- cgit From 366cbf2f46048d70005c6c33dc289330f24b54b0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Nov 2016 22:16:06 +0100 Subject: bpf, xdp: drop rcu_read_lock from bpf_prog_run_xdp and move to caller After 326fe02d1ed6 ("net/mlx4_en: protect ring->xdp_prog with rcu_read_lock"), the rcu_read_lock() in bpf_prog_run_xdp() is superfluous, since callers need to hold rcu_read_lock() already to make sure BPF program doesn't get released in the background. Thus, drop it from bpf_prog_run_xdp(), as it can otherwise be misleading. Still keeping the bpf_prog_run_xdp() is useful as it allows for grepping in XDP supported drivers and to keep the typecheck on the context intact. For mlx4, this means we don't have a double rcu_read_lock() anymore. nfp can just make use of bpf_prog_run_xdp(), too. For qede, just move rcu_read_lock() out of the helper. When the driver gets atomic replace support, this will move to call-sites eventually. mlx5 needs actual fixing as it has the same issue as described already in 326fe02d1ed6 ("net/mlx4_en: protect ring->xdp_prog with rcu_read_lock"), that is, we're under RCU bh at this time, BPF programs are released via call_rcu(), and call_rcu() != call_rcu_bh(), so we need to properly mark read side as programs can get xchg()'ed in mlx5e_xdp_set() without queue reset. Fixes: 86994156c736 ("net/mlx5e: XDP fast RX drop bpf programs support") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/filter.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7ba644626553..97338134398f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -498,16 +498,16 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return BPF_PROG_RUN(prog, skb); } -static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, - struct xdp_buff *xdp) +static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, + struct xdp_buff *xdp) { - u32 ret; - - rcu_read_lock(); - ret = BPF_PROG_RUN(prog, xdp); - rcu_read_unlock(); - - return ret; + /* Caller needs to hold rcu_read_lock() (!), otherwise program + * can be released while still running, or map elements could be + * freed early while still having concurrent users. XDP fastpath + * already takes rcu_read_lock() when fetching the program, so + * it's not necessary here anymore. + */ + return BPF_PROG_RUN(prog, xdp); } static inline unsigned int bpf_prog_size(unsigned int proglen) -- cgit From f8c3cf9d7d7f04718e0d51c28f8430afa6058b3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 20 Oct 2016 10:12:45 -0400 Subject: NFSv4: Add a generic structure for managing layout-private information Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bfbd0cace91b..331a3200eb01 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -216,6 +216,20 @@ struct nfs4_get_lease_time_res { struct nfs_fsinfo *lr_fsinfo; }; +struct xdr_stream; +struct nfs4_xdr_opaque_data; + +struct nfs4_xdr_opaque_ops { + void (*encode)(struct xdr_stream *, const void *args, + const struct nfs4_xdr_opaque_data *); + void (*free)(struct nfs4_xdr_opaque_data *); +}; + +struct nfs4_xdr_opaque_data { + const struct nfs4_xdr_opaque_ops *ops; + void *data; +}; + #define PNFS_LAYOUT_MAXSIZE 4096 struct nfs4_layoutdriver_data { -- cgit From fc831825f99eb3a2f1bf3fe7307b392513b642a5 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Thu, 1 Dec 2016 00:21:06 -0800 Subject: qed: Add support for hardware offloaded iSCSI. This adds the backbone required for the various HW initalizations which are necessary for the iSCSI driver (qedi) for QLogic FastLinQ 4xxxx line of adapters - FW notification, resource initializations, etc. Signed-off-by: Arun Easi Signed-off-by: Yuval Mintz Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 2 + include/linux/qed/qed_iscsi_if.h | 229 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 231 insertions(+) create mode 100644 include/linux/qed/qed_iscsi_if.h (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ea095b4893aa..4b454f4f5b25 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -166,6 +166,7 @@ struct qed_iscsi_pf_params { u32 max_cwnd; u16 cq_num_entries; u16 cmdq_num_entries; + u32 two_msl_timer; u16 dup_ack_threshold; u16 tx_sws_timer; u16 min_rto; @@ -275,6 +276,7 @@ struct qed_dev_info { enum qed_sb_type { QED_SB_TYPE_L2_QUEUE, QED_SB_TYPE_CNQ, + QED_SB_TYPE_STORAGE, }; enum qed_protocol { diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h new file mode 100644 index 000000000000..d27912480cb3 --- /dev/null +++ b/include/linux/qed/qed_iscsi_if.h @@ -0,0 +1,229 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_ISCSI_IF_H +#define _QED_ISCSI_IF_H +#include +#include + +typedef int (*iscsi_event_cb_t) (void *context, + u8 fw_event_code, void *fw_handle); +struct qed_iscsi_stats { + u64 iscsi_rx_bytes_cnt; + u64 iscsi_rx_packet_cnt; + u64 iscsi_rx_new_ooo_isle_events_cnt; + u32 iscsi_cmdq_threshold_cnt; + u32 iscsi_rq_threshold_cnt; + u32 iscsi_immq_threshold_cnt; + + u64 iscsi_rx_dropped_pdus_task_not_valid; + + u64 iscsi_rx_data_pdu_cnt; + u64 iscsi_rx_r2t_pdu_cnt; + u64 iscsi_rx_total_pdu_cnt; + + u64 iscsi_tx_go_to_slow_start_event_cnt; + u64 iscsi_tx_fast_retransmit_event_cnt; + + u64 iscsi_tx_data_pdu_cnt; + u64 iscsi_tx_r2t_pdu_cnt; + u64 iscsi_tx_total_pdu_cnt; + + u64 iscsi_tx_bytes_cnt; + u64 iscsi_tx_packet_cnt; +}; + +struct qed_dev_iscsi_info { + struct qed_dev_info common; + + void __iomem *primary_dbq_rq_addr; + void __iomem *secondary_bdq_rq_addr; +}; + +struct qed_iscsi_id_params { + u8 mac[ETH_ALEN]; + u32 ip[4]; + u16 port; +}; + +struct qed_iscsi_params_offload { + u8 layer_code; + dma_addr_t sq_pbl_addr; + u32 initial_ack; + + struct qed_iscsi_id_params src; + struct qed_iscsi_id_params dst; + u16 vlan_id; + u8 tcp_flags; + u8 ip_version; + u8 default_cq; + + u8 ka_max_probe_cnt; + u8 dup_ack_theshold; + u32 rcv_next; + u32 snd_una; + u32 snd_next; + u32 snd_max; + u32 snd_wnd; + u32 rcv_wnd; + u32 snd_wl1; + u32 cwnd; + u32 ss_thresh; + u16 srtt; + u16 rtt_var; + u32 ts_time; + u32 ts_recent; + u32 ts_recent_age; + u32 total_rt; + u32 ka_timeout_delta; + u32 rt_timeout_delta; + u8 dup_ack_cnt; + u8 snd_wnd_probe_cnt; + u8 ka_probe_cnt; + u8 rt_cnt; + u32 flow_label; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u32 initial_rcv_wnd; + u8 ttl; + u8 tos_or_tc; + u16 remote_port; + u16 local_port; + u16 mss; + u8 snd_wnd_scale; + u8 rcv_wnd_scale; + u32 ts_ticks_per_second; + u16 da_timeout_value; + u8 ack_frequency; +}; + +struct qed_iscsi_params_update { + u8 update_flag; +#define QED_ISCSI_CONN_HD_EN BIT(0) +#define QED_ISCSI_CONN_DD_EN BIT(1) +#define QED_ISCSI_CONN_INITIAL_R2T BIT(2) +#define QED_ISCSI_CONN_IMMEDIATE_DATA BIT(3) + + u32 max_seq_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + u32 first_seq_length; + u32 exp_stat_sn; +}; + +#define MAX_TID_BLOCKS_ISCSI (512) +struct qed_iscsi_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_ISCSI]; +}; + +struct qed_iscsi_cb_ops { + struct qed_common_cb_ops common; +}; + +/** + * struct qed_iscsi_ops - qed iSCSI operations. + * @common: common operations pointer + * @ll2: light L2 operations pointer + * @fill_dev_info: fills iSCSI specific information + * @param cdev + * @param info + * @return 0 on sucesss, otherwise error value. + * @register_ops: register iscsi operations + * @param cdev + * @param ops - specified using qed_iscsi_cb_ops + * @param cookie - driver private + * @start: iscsi in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: iscsi in FW + * @param cdev + * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new iscsi connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * @return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired iscsi connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @update_conn: updates an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @clear_sq: clear all task in sq + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @get_stats: iSCSI related statistics + * @param cdev + * @param stats - pointer to struck that would be filled + * we stats + * @return 0 on success, error otherwise. + */ +struct qed_iscsi_ops { + const struct qed_common_ops *common; + + const struct qed_ll2_ops *ll2; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_iscsi_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_iscsi_cb_ops *ops, void *cookie); + + int (*start)(struct qed_dev *cdev, + struct qed_iscsi_tid *tasks, + void *event_context, iscsi_event_cb_t async_event_cb); + + int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_iscsi_params_offload *conn_info); + + int (*update_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_iscsi_params_update *conn_info); + + int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); + + int (*clear_sq)(struct qed_dev *cdev, u32 handle); + + int (*get_stats)(struct qed_dev *cdev, + struct qed_iscsi_stats *stats); +}; + +const struct qed_iscsi_ops *qed_get_iscsi_ops(void); +void qed_put_iscsi_ops(void); +#endif -- cgit From 95a22caee396cef0bb2ca8fafdd82966a49367bb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 1 Dec 2016 11:32:06 +0100 Subject: tcp: randomize tcp timestamp offsets for each connection jiffies based timestamps allow for easy inference of number of devices behind NAT translators and also makes tracking of hosts simpler. commit ceaa1fef65a7c2e ("tcp: adding a per-socket timestamp offset") added the main infrastructure that is needed for per-connection ts randomization, in particular writing/reading the on-wire tcp header format takes the offset into account so rest of stack can use normal tcp_time_stamp (jiffies). So only two items are left: - add a tsoffset for request sockets - extend the tcp isn generator to also return another 32bit number in addition to the ISN. Re-use of ISN generator also means timestamps are still monotonically increasing for same connection quadruple, i.e. PAWS will still work. Includes fixes from Eric Dumazet. Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 00e0ee8f001f..734bab4c3bef 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,6 +123,7 @@ struct tcp_request_sock { u32 txhash; u32 rcv_isn; u32 snt_isn; + u32 ts_off; u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# -- cgit From 7091d8c7055d7310339435ae3af2fb490a92524d Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 1 Dec 2016 14:06:37 +0200 Subject: net/sched: cls_flower: Add offload support using egress Hardware device In order to support hardware offloading when the device given by the tc rule is different from the Hardware underline device, extract the mirred (egress) device from the tc action when a filter is added, using the new tc_action_ops, get_dev(). Flower caches the information about the mirred device and use it for calling ndo_setup_tc in filter change, update stats and delete. Calling ndo_setup_tc of the mirred (egress) device instead of the ingress device will allow a resolution between the software ingress device and the underline hardware device. The resolution will take place inside the offloading driver using 'egress_device' flag added to tc_to_netdev struct which is provided to the offloading driver. Signed-off-by: Hadar Hen Zion Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3755317cc6a9..1ff5ea6e1221 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -802,6 +802,7 @@ struct tc_to_netdev { struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; }; + bool egress_dev; }; /* These structures hold the attributes of xdp state that are being passed -- cgit From b2cd12574aa3e1625f471ff57cde7f628a18a46b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:03 -0800 Subject: bpf: Refactor cgroups code in prep for new type Code move and rename only; no functional change intended. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0cf1adfadd2d..af2ca8b432c0 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -36,31 +36,31 @@ void cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type); -int __cgroup_bpf_run_filter(struct sock *sk, - struct sk_buff *skb, - enum bpf_attach_type type); - -/* Wrappers for __cgroup_bpf_run_filter() guarded by cgroup_bpf_enabled. */ -#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter(sk, skb, \ - BPF_CGROUP_INET_INGRESS); \ - \ - __ret; \ +int __cgroup_bpf_run_filter_skb(struct sock *sk, + struct sk_buff *skb, + enum bpf_attach_type type); + +/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ +#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ + BPF_CGROUP_INET_INGRESS); \ + \ + __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ - typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk)) \ - __ret = __cgroup_bpf_run_filter(__sk, skb, \ - BPF_CGROUP_INET_EGRESS); \ - } \ - __ret; \ +#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ + typeof(sk) __sk = sk_to_full_sk(sk); \ + if (sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ + BPF_CGROUP_INET_EGRESS); \ + } \ + __ret; \ }) #else -- cgit From 61023658760032e97869b07d54be9681d2529e77 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:04 -0800 Subject: bpf: Add new cgroup attach type to enable sock modifications Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run any time a process in the cgroup opens an AF_INET or AF_INET6 socket. Currently only sk_bound_dev_if is exported to userspace for modification by a bpf program. This allows a cgroup to be configured such that AF_INET{6} sockets opened by processes are automatically bound to a specific device. In turn, this enables the running of programs that do not support SO_BINDTODEVICE in a specific VRF context / L3 domain. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index af2ca8b432c0..7b6e5d168c95 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -40,6 +40,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sk(struct sock *sk, + enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -63,6 +66,16 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && sk) { \ + __ret = __cgroup_bpf_run_filter_sk(sk, \ + BPF_CGROUP_INET_SOCK_CREATE); \ + } \ + __ret; \ +}) + #else struct cgroup_bpf {}; @@ -72,6 +85,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ -- cgit From b908d3cd812abe3f4a74d7550bbf0a8cbcfbe6ed Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 2 Dec 2016 17:48:51 -0800 Subject: Input: synaptics-rmi4 - allow to add attention data The HID implementation of RMI4 provides the data during the interrupt (in the input report). We need to provide a way for this transport driver to provide the attention data while calling an IRQ. We use a fifo in rmi_core to not lose any incoming event. Signed-off-by: Benjamin Tissoires Reviewed-by: Andrew Duggan Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 7780e40a2573..1d4865621493 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -331,6 +332,12 @@ struct rmi_device { }; +struct rmi4_attn_data { + unsigned long irq_status; + size_t size; + void *data; +}; + struct rmi_driver_data { struct list_head function_list; @@ -357,11 +364,15 @@ struct rmi_driver_data { bool enabled; struct mutex enabled_mutex; + DECLARE_KFIFO(attn_fifo, struct rmi4_attn_data, 16); }; int rmi_register_transport_device(struct rmi_transport_dev *xport); void rmi_unregister_transport_device(struct rmi_transport_dev *xport); +void rmi_set_attn_data(struct rmi_device *rmi_dev, unsigned long irq_status, + void *data, size_t size); + int rmi_driver_suspend(struct rmi_device *rmi_dev, bool enable_wake); int rmi_driver_resume(struct rmi_device *rmi_dev, bool clear_wake); #endif -- cgit From ae9979c31007d5366b73640ee7dcbb271357053e Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 2 Dec 2016 17:49:10 -0800 Subject: Input: synaptics-rmi4 - store the attn data in the driver Now that we have a proper API to set the attention data, there is no point in keeping it in the transport driver. Signed-off-by: Benjamin Tissoires Reviewed-by: Andrew Duggan Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index 1d4865621493..ac910f730688 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -272,9 +272,6 @@ struct rmi_transport_dev { struct rmi_device_platform_data pdata; struct input_dev *input; - - void *attn_data; - int attn_size; }; /** @@ -364,6 +361,8 @@ struct rmi_driver_data { bool enabled; struct mutex enabled_mutex; + + struct rmi4_attn_data attn_data; DECLARE_KFIFO(attn_fifo, struct rmi4_attn_data, 16); }; -- cgit From fb5f51c7425ebc808d91329257cbc963e2421368 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Thu, 24 Nov 2016 08:03:41 +1100 Subject: vfs: change d_manage() to take a struct path For the autofs module to be able to reliably check if a dentry is a mountpoint in a multiple namespace environment the ->d_manage() dentry operation will need to take a path argument instead of a dentry. Link: http://lkml.kernel.org/r/20161011053352.27645.83962.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Al Viro Cc: Eric W. Biederman Cc: Omar Sandoval Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 5beed7b30561..bc529ce88ed0 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -139,7 +139,7 @@ struct dentry_operations { void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); - int (*d_manage)(struct dentry *, bool); + int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *, unsigned int); } ____cacheline_aligned; -- cgit From 4d796d751cefdb942a54c570bd3087d8be3bb893 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Sep 2016 11:38:08 -0400 Subject: pNFS: Allow layout drivers to manage private data in struct nfs4_layoutreturn Cleanup to allow layout drivers to attach private data to layoutreturn, and manage the data. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 331a3200eb01..b64177d669fd 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -320,6 +320,7 @@ struct nfs4_layoutreturn_args { struct pnfs_layout_range range; nfs4_stateid stateid; __u32 layout_type; + struct nfs4_xdr_opaque_data *ld_private; }; struct nfs4_layoutreturn_res { @@ -335,6 +336,7 @@ struct nfs4_layoutreturn { struct nfs_client *clp; struct inode *inode; int rpc_status; + struct nfs4_xdr_opaque_data ld_private; }; #define PNFS_LAYOUTSTATS_MAXSIZE 256 -- cgit From 422c93c881a1689b5ad99e231a65ee5c51d3b72a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 6 Oct 2016 17:53:20 -0400 Subject: pNFS/flexfiles: Minor refactoring before adding iostats to layoutreturn Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b64177d669fd..617cfaa20ffc 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -357,8 +357,7 @@ struct nfs42_layoutstat_devinfo { __u64 write_count; __u64 write_bytes; __u32 layout_type; - layoutstats_encode_t layoutstats_encode; - void *layout_private; + struct nfs4_xdr_opaque_data ld_private; }; struct nfs42_layoutstat_args { -- cgit From b1226c7db1d997fa6955cd3b54ba333bd0d8a29c Mon Sep 17 00:00:00 2001 From: Adit Ranadive Date: Sun, 2 Oct 2016 19:10:21 -0700 Subject: vmxnet3: Move PCI Id to pci_ids.h The VMXNet3 PCI Id will be shared with our paravirtual RDMA driver. Moved it to the shared location in pci_ids.h. Suggested-by: Leon Romanovsky Acked-by: Bjorn Helgaas Reviewed-by: Yuval Shaia Signed-off-by: Adit Ranadive Signed-off-by: Doug Ledford --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c58752fe16c4..98bb455302cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2251,6 +2251,7 @@ #define PCI_DEVICE_ID_RASTEL_2PORT 0x2000 #define PCI_VENDOR_ID_VMWARE 0x15ad +#define PCI_DEVICE_ID_VMWARE_VMXNET3 0x07b0 #define PCI_VENDOR_ID_ZOLTRIX 0x15b0 #define PCI_DEVICE_ID_ZOLTRIX_2BD0 0x2bd0 -- cgit From c6609c0a1c34fc097152b28b496236625673924f Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Thu, 24 Nov 2016 08:03:41 +1100 Subject: vfs: add path_is_mountpoint() helper d_mountpoint() can only be used reliably to establish if a dentry is not mounted in any namespace. It isn't aware of the possibility there may be multiple mounts using a given dentry that may be in a different namespace. Add helper functions, path_is_mountpoint(), that checks if a struct path is a mountpoint for this case. Link: http://lkml.kernel.org/r/20161011053358.27645.9729.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Al Viro Cc: Eric W. Biederman Cc: Omar Sandoval Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/mount.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 1172cce949a4..5b6dd004bfdc 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -98,4 +98,6 @@ extern dev_t name_to_dev_t(const char *name); extern unsigned int sysctl_mount_max; +extern bool path_is_mountpoint(const struct path *path); + #endif /* _LINUX_MOUNT_H */ -- cgit From 01619491a5f0766014fe863c5ae480665436e7a2 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Thu, 24 Nov 2016 08:03:41 +1100 Subject: vfs: add path_has_submounts() d_mountpoint() can only be used reliably to establish if a dentry is not mounted in any namespace. It isn't aware of the possibility there may be multiple mounts using the given dentry, possibly in a different namespace. Add function, path_has_submounts(), that checks is a struct path contains mounts (or is a mountpoint itself) to handle this case. Link: http://lkml.kernel.org/r/20161011053403.27645.55242.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Al Viro Cc: Eric W. Biederman Cc: Omar Sandoval Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bc529ce88ed0..0ffaf7aef9ae 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -255,6 +255,7 @@ extern void d_prune_aliases(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int have_submounts(struct dentry *); +extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. -- cgit From f74e7b33c37e5a7bae33bb73858c2766cb256626 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Thu, 24 Nov 2016 08:03:42 +1100 Subject: vfs: remove unused have_submounts() function Now that path_has_submounts() has been added have_submounts() is no longer used so remove it. Link: http://lkml.kernel.org/r/20161011053428.27645.12310.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Al Viro Cc: Eric W. Biederman Cc: Omar Sandoval Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 0ffaf7aef9ae..c965e4469499 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -254,7 +254,6 @@ extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); /* test whether we have any submounts in a subdir tree */ -extern int have_submounts(struct dentry *); extern int path_has_submounts(const struct path *); /* -- cgit From adc176c5472214971d77c1a61c83db9b01e9cdc7 Mon Sep 17 00:00:00 2001 From: Erik Nordmark Date: Fri, 2 Dec 2016 14:00:08 -0800 Subject: ipv6 addrconf: Implemented enhanced DAD (RFC7527) Implemented RFC7527 Enhanced DAD. IPv6 duplicate address detection can fail if there is some temporary loopback of Ethernet frames. RFC7527 solves this by including a random nonce in the NS messages used for DAD, and if an NS is received with the same nonce it is assumed to be a looped back DAD probe and is ignored. RFC7527 is enabled by default. Can be disabled by setting both of conf/{all,interface}/enhanced_dad to zero. Signed-off-by: Erik Nordmark Signed-off-by: Bob Gilligan Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 3f95233b2733..671d014e6429 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -68,6 +68,7 @@ struct ipv6_devconf { #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif + __u32 enhanced_dad; struct ctl_table_header *sysctl_header; }; -- cgit From c51d39010a1bccc9c1294e2d7c00005aefeb2b5c Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 15 Nov 2016 15:08:25 +0100 Subject: netfilter: conntrack: built-in support for DCCP CONFIG_NF_CT_PROTO_DCCP is no more a tristate. When set to y, connection tracking support for DCCP protocol is built-in into nf_conntrack.ko. footprint test: $ ls -l net/netfilter/nf_conntrack{_proto_dccp,}.ko \ net/ipv4/netfilter/nf_conntrack_ipv4.ko \ net/ipv6/netfilter/nf_conntrack_ipv6.ko (builtin)|| dccp | ipv4 | ipv6 | nf_conntrack ---------++--------+--------+--------+-------------- none || 469140 | 828755 | 828676 | 6141434 DCCP || - | 830566 | 829935 | 6533526 Signed-off-by: Davide Caratti Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_dccp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_dccp.h b/include/linux/netfilter/nf_conntrack_dccp.h index 40dcc82058d1..ff721d7325cf 100644 --- a/include/linux/netfilter/nf_conntrack_dccp.h +++ b/include/linux/netfilter/nf_conntrack_dccp.h @@ -25,7 +25,7 @@ enum ct_dccp_roles { #define CT_DCCP_ROLE_MAX (__CT_DCCP_ROLE_MAX - 1) #ifdef __KERNEL__ -#include +#include struct nf_ct_dccp { u_int8_t role[IP_CT_DIR_MAX]; -- cgit From 1cd9cb05f96e526f41bb4704caa95dc40ed08c5d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 4 Dec 2016 18:34:34 -0500 Subject: NFS: Only look at the change attribute cache state in nfs_check_verifier When looking at whether or not our dcache is valid, we really don't care about the general state of the directory attribute cache. Instead, we we only care about the state of the change attribute. This fixes a performance issue when the client is responsible for changing the directory contents; a number of NFSv4 operations will atomically update the directory change attribute, but may not return all the other attributes. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index db1002abc95e..cb631973839a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -345,6 +345,7 @@ extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct dentry *, struct iattr *); -- cgit From e0097cf5f2f1b7b8a594beaa32a604776d3ca6ce Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 29 Nov 2016 12:09:10 +0200 Subject: mmc: queue: Fix queue thread wake-up The only time the driver sleeps expecting to be woken upon the arrival of a new request, is when the dispatch queue is empty. The only time that it is known whether the dispatch queue is empty is after NULL is returned from blk_fetch_request() while under the queue lock. Recognizing those facts, simplify the synchronization between the queue thread and the request function. A couple of flags tell the request function what to do, and the queue lock and barriers associated with wake-ups ensure synchronization. The result is simpler and allows the removal of the context_info lock. Signed-off-by: Adrian Hunter Reviewed-by: Linus Walleij Reviewed-by: Harjani Ritesh Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 2ce32fefb41c..8bc884121465 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -197,14 +197,12 @@ struct mmc_slot { * @is_new_req wake up reason was new request * @is_waiting_last_req mmc context waiting for single running request * @wait wait queue - * @lock lock to protect data fields */ struct mmc_context_info { bool is_done_rcv; bool is_new_req; bool is_waiting_last_req; wait_queue_head_t wait; - spinlock_t lock; }; struct regulator; -- cgit From 925ff3a7a334b3fe968ae15f07d22df21addad26 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 29 Nov 2016 12:09:16 +0200 Subject: mmc: mmc: Add Command Queue definitions Add definitions relating to Command Queuing. Signed-off-by: Adrian Hunter Reviewed-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 2 ++ include/linux/mmc/mmc.h | 17 +++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index e49a3ff9d0e0..95d69d498296 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -89,6 +89,8 @@ struct mmc_ext_csd { unsigned int boot_ro_lock; /* ro lock support */ bool boot_ro_lockable; bool ffu_capable; /* Firmware upgrade support */ + bool cmdq_support; /* Command Queue supported */ + unsigned int cmdq_depth; /* Command Queue depth */ #define MMC_FIRMWARE_LEN 8 u8 fwrev[MMC_FIRMWARE_LEN]; /* FW version */ u8 raw_exception_status; /* 54 */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index c376209c70ef..672730acc705 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -84,6 +84,13 @@ #define MMC_APP_CMD 55 /* ac [31:16] RCA R1 */ #define MMC_GEN_CMD 56 /* adtc [0] RD/WR R1 */ + /* class 11 */ +#define MMC_QUE_TASK_PARAMS 44 /* ac [20:16] task id R1 */ +#define MMC_QUE_TASK_ADDR 45 /* ac [31:0] data addr R1 */ +#define MMC_EXECUTE_READ_TASK 46 /* adtc [20:16] task id R1 */ +#define MMC_EXECUTE_WRITE_TASK 47 /* adtc [20:16] task id R1 */ +#define MMC_CMDQ_TASK_MGMT 48 /* ac [20:16] task id R1b */ + static inline bool mmc_op_multi(u32 opcode) { return opcode == MMC_WRITE_MULTIPLE_BLOCK || @@ -272,6 +279,7 @@ struct _mmc_csd { * EXT_CSD fields */ +#define EXT_CSD_CMDQ_MODE_EN 15 /* R/W */ #define EXT_CSD_FLUSH_CACHE 32 /* W */ #define EXT_CSD_CACHE_CTRL 33 /* R/W */ #define EXT_CSD_POWER_OFF_NOTIFICATION 34 /* R/W */ @@ -331,6 +339,8 @@ struct _mmc_csd { #define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */ #define EXT_CSD_PWR_CL_DDR_200_360 253 /* RO */ #define EXT_CSD_FIRMWARE_VERSION 254 /* RO, 8 bytes */ +#define EXT_CSD_CMDQ_DEPTH 307 /* RO */ +#define EXT_CSD_CMDQ_SUPPORT 308 /* RO */ #define EXT_CSD_SUPPORTED_MODE 493 /* RO */ #define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */ #define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */ @@ -437,6 +447,13 @@ struct _mmc_csd { */ #define EXT_CSD_MANUAL_BKOPS_MASK 0x01 +/* + * Command Queue + */ +#define EXT_CSD_CMDQ_MODE_ENABLED BIT(0) +#define EXT_CSD_CMDQ_DEPTH_MASK GENMASK(4, 0) +#define EXT_CSD_CMDQ_SUPPORTED BIT(0) + /* * MMC_SWITCH access modes */ -- cgit From 30103b5b6432a51c3822a26dc340e35d91237f39 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Sun, 4 Dec 2016 16:52:31 -0600 Subject: regulator: Fix regulator_get_error_flags() signature mismatch The function signature of does not match regulator_get_error_flags() when CONFIG_REGULATOR is not defined vs. when it is not defined. This makes both declarations match to prevent compiler errors. Signed-off-by: David Lechner Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 528eb1f5273e..ea0fffa5faeb 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -498,7 +498,8 @@ static inline unsigned int regulator_get_mode(struct regulator *regulator) return REGULATOR_MODE_NORMAL; } -static inline int regulator_get_error_flags(struct regulator *regulator) +static inline int regulator_get_error_flags(struct regulator *regulator, + unsigned int *flags) { return -EINVAL; } -- cgit From e711f0309109701cb422aab44ace4ea0dccb89ea Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 2 Dec 2016 15:14:23 +0200 Subject: mmc: mmc: Introduce mmc_abort_tuning() If a tuning command times out, the card could still be processing it, which will cause problems for recovery. The eMMC specification says that CMD12 can be used to stop CMD21, so add a function that does that. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 0ce928b3ce90..e33cc748dcfe 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -176,6 +176,7 @@ extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *, extern void mmc_start_bkops(struct mmc_card *card, bool from_exception); extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int); extern int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); +extern int mmc_abort_tuning(struct mmc_host *host, u32 opcode); extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); #define MMC_ERASE_ARG 0x00000000 -- cgit From 64df1148876e35e81e91195e01c8197edc66fcc5 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 4 Dec 2016 13:10:04 +0100 Subject: driver core: Silence device links sphinx warning Silence this warning emitted by sphinx: include/linux/device.h:938: warning: No description found for parameter 'links' While at it, fix typos in comments of device links code. Cc: Rafael J. Wysocki Cc: Jonathan Corbet Cc: Silvio Fricke Signed-off-by: Lukas Wunner Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4cd8e52033b0..67bbbee8fe02 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -817,6 +817,7 @@ struct dev_links_info { * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. + * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/power/devices.txt for details. * @pm_domain: Provide callbacks that are executed during system suspend, -- cgit From 9d4b82706357f2eb23f45309227fc94d11eea255 Mon Sep 17 00:00:00 2001 From: Changming Huang Date: Tue, 29 Nov 2016 13:45:38 +0800 Subject: fsl/usb: Workarourd for USB erratum-A005697 The EHCI specification states the following in the SUSP bit description: In the Suspend state, the port is sensitive to resume detection. Note that the bit status does not change until the port is suspended and that there may be a delay in suspending a port if there is a transaction currently in progress on the USB. However, in NXP USBDR controller, the PORTSCx[SUSP] bit changes immediately when the application sets it and not when the port is actually suspended. So the application must wait for at least 10 milliseconds after a port indicates that it is suspended, to make sure this port has entered suspended state before initiating this port resume using the Force Port Resume bit. This bit is for NXP controller, not EHCI compatible. Signed-off-by: Changming Huang Signed-off-by: Ramneek Mehresh Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl_devices.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index f2912914141a..60cef8227534 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -100,6 +100,7 @@ struct fsl_usb2_platform_data { unsigned already_suspended:1; unsigned has_fsl_erratum_a007792:1; unsigned has_fsl_erratum_a005275:1; + unsigned has_fsl_erratum_a005697:1; unsigned check_phy_clk_valid:1; /* register save area for suspend/resume */ -- cgit From b9c2a2a39898d55b9fe13aa1fe15891e37bc9087 Mon Sep 17 00:00:00 2001 From: Tal Shorer Date: Fri, 18 Nov 2016 14:17:26 +0200 Subject: usb: hcd.h: construct hub class request constants from simpler constants Currently, each hub class request constant is defined by a line like: #define ClearHubFeature (0x2000 | USB_REQ_CLEAR_FEATURE) The "magic" number for the high byte is one of 0x20, 0xa0, 0x23, 0xa3. The 0x80 bit that changes inditace USB_DIR_IN, and the 0x03 that pops up is the difference between USB_RECIP_DEVICE (0x00) and USB_RECIP_OTHER (0x03). The constant 0x20 bit is USB_TYPE_CLASS. This patch eliminates those magic numbers by defining a macro to help construct these hub class request from simpler constants. Note that USB_RT_HUB is defined as (USB_TYPE_CLASS | USB_RECIP_DEVICE) and that USB_RT_PORT is defined as (USB_TYPE_CLASS | USB_RECIP_OTHER). Signed-off-by: Tal Shorer Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 66fc13705ab7..40edf6a8533e 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -566,21 +566,22 @@ extern void usb_ep0_reinit(struct usb_device *); ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) /* class requests from the USB 2.0 hub spec, table 11-15 */ +#define HUB_CLASS_REQ(dir, type, request) ((((dir) | (type)) << 8) | (request)) /* GetBusState and SetHubDescriptor are optional, omitted */ -#define ClearHubFeature (0x2000 | USB_REQ_CLEAR_FEATURE) -#define ClearPortFeature (0x2300 | USB_REQ_CLEAR_FEATURE) -#define GetHubDescriptor (0xa000 | USB_REQ_GET_DESCRIPTOR) -#define GetHubStatus (0xa000 | USB_REQ_GET_STATUS) -#define GetPortStatus (0xa300 | USB_REQ_GET_STATUS) -#define SetHubFeature (0x2000 | USB_REQ_SET_FEATURE) -#define SetPortFeature (0x2300 | USB_REQ_SET_FEATURE) +#define ClearHubFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, USB_REQ_CLEAR_FEATURE) +#define ClearPortFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, USB_REQ_CLEAR_FEATURE) +#define GetHubDescriptor HUB_CLASS_REQ(USB_DIR_IN, USB_RT_HUB, USB_REQ_GET_DESCRIPTOR) +#define GetHubStatus HUB_CLASS_REQ(USB_DIR_IN, USB_RT_HUB, USB_REQ_GET_STATUS) +#define GetPortStatus HUB_CLASS_REQ(USB_DIR_IN, USB_RT_PORT, USB_REQ_GET_STATUS) +#define SetHubFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, USB_REQ_SET_FEATURE) +#define SetPortFeature HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_PORT, USB_REQ_SET_FEATURE) /*-------------------------------------------------------------------------*/ /* class requests from USB 3.1 hub spec, table 10-7 */ -#define SetHubDepth (0x2000 | HUB_SET_DEPTH) -#define GetPortErrorCount (0xa300 | HUB_GET_PORT_ERR_COUNT) +#define SetHubDepth HUB_CLASS_REQ(USB_DIR_OUT, USB_RT_HUB, HUB_SET_DEPTH) +#define GetPortErrorCount HUB_CLASS_REQ(USB_DIR_IN, USB_RT_PORT, HUB_GET_PORT_ERR_COUNT) /* * Generic bandwidth allocation constants/support -- cgit From 40fc3423b983b864bf70b03199191260ae9b2ea6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Dec 2016 11:14:50 -0800 Subject: tcp: tsq: add tsq_flags / tsq_enum This is a cleanup, to ease code review of following patches. Old 'enum tsq_flags' is renamed, and a new enumeration is added with the flags used in cmpxchg() operations as opposed to single bit operations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 734bab4c3bef..d8be083ab0b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -364,7 +364,7 @@ struct tcp_sock { u32 *saved_syn; }; -enum tsq_flags { +enum tsq_enum { TSQ_THROTTLED, TSQ_QUEUED, TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */ @@ -375,6 +375,15 @@ enum tsq_flags { */ }; +enum tsq_flags { + TSQF_THROTTLED = (1UL << TSQ_THROTTLED), + TSQF_QUEUED = (1UL << TSQ_QUEUED), + TCPF_TSQ_DEFERRED = (1UL << TCP_TSQ_DEFERRED), + TCPF_WRITE_TIMER_DEFERRED = (1UL << TCP_WRITE_TIMER_DEFERRED), + TCPF_DELACK_TIMER_DEFERRED = (1UL << TCP_DELACK_TIMER_DEFERRED), + TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED), +}; + static inline struct tcp_sock *tcp_sk(const struct sock *sk) { return (struct tcp_sock *)sk; -- cgit From 7aa5470c2c09265902b5e4289afa82e4e7c2987e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Dec 2016 11:14:57 -0800 Subject: tcp: tsq: move tsq_flags close to sk_wmem_alloc tsq_flags being in the same cache line than sk_wmem_alloc makes a lot of sense. Both fields are changed from tcp_wfree() and more generally by various TSQ related functions. Prior patch made room in struct sock and added sk_tsq_flags, this patch deletes tsq_flags from struct tcp_sock. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d8be083ab0b0..fc5848dad7a4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -186,7 +186,6 @@ struct tcp_sock { u32 tsoffset; /* timestamp offset */ struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - unsigned long tsq_flags; /* Data for direct copy to user */ struct { -- cgit From a2e7eefd5618e0f75bae2eb5c9387ea2f627b6ca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 2 Dec 2016 19:31:01 +0100 Subject: nvme: move NVMe class code to pci_ids.h We'll need to check for it in the AHCI drivers (yes, really) soon. Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c58752fe16c4..a5e6c7bca610 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -23,8 +23,10 @@ #define PCI_CLASS_STORAGE_SATA 0x0106 #define PCI_CLASS_STORAGE_SATA_AHCI 0x010601 #define PCI_CLASS_STORAGE_SAS 0x0107 +#define PCI_CLASS_STORAGE_EXPRESS 0x010802 #define PCI_CLASS_STORAGE_OTHER 0x0180 + #define PCI_BASE_CLASS_NETWORK 0x02 #define PCI_CLASS_NETWORK_ETHERNET 0x0200 #define PCI_CLASS_NETWORK_TOKEN_RING 0x0201 -- cgit From bfa9cb3e110cc02f2120e021bc853773bfd61b74 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 2 Dec 2016 19:31:02 +0100 Subject: ahci-remap.h: add ahci remapping definitions Signed-off-by: Dan Williams [hch: split into a separate header and commit] Signed-off-by: Christoph Hellwig [tj: dropped duplicate definition of AHCI_VSCAP spotted by Sergei] Cc: Sergei Shtylyov Signed-off-by: Tejun Heo --- include/linux/ahci-remap.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 include/linux/ahci-remap.h (limited to 'include/linux') diff --git a/include/linux/ahci-remap.h b/include/linux/ahci-remap.h new file mode 100644 index 000000000000..62be3a40239d --- /dev/null +++ b/include/linux/ahci-remap.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_AHCI_REMAP_H +#define _LINUX_AHCI_REMAP_H + +#include + +#define AHCI_VSCAP 0xa4 +#define AHCI_REMAP_CAP 0x800 + +/* device class code */ +#define AHCI_REMAP_N_DCC 0x880 + +/* remap-device base relative to ahci-bar */ +#define AHCI_REMAP_N_OFFSET SZ_16K +#define AHCI_REMAP_N_SIZE SZ_16K + +#define AHCI_MAX_REMAP 3 + +static inline unsigned int ahci_remap_dcc(int i) +{ + return AHCI_REMAP_N_DCC + i * 0x80; +} + +static inline unsigned int ahci_remap_base(int i) +{ + return AHCI_REMAP_N_OFFSET + i * AHCI_REMAP_N_SIZE; +} + +#endif /* _LINUX_AHCI_REMAP_H */ -- cgit From cbbd26b8b1a6af9c02e2b6523e12bd50cc765059 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 1 Nov 2016 22:09:04 -0400 Subject: [iov_iter] new primitives - copy_from_iter_full() and friends copy_from_iter_full(), copy_from_iter_full_nocache() and csum_and_copy_from_iter_full() - counterparts of copy_from_iter() et.al., advancing iterator only in case of successful full copy and returning whether it had been successful or not. Convert some obvious users. *NOTE* - do not blindly assume that something is a good candidate for those unless you are sure that not advancing iov_iter in failure case is the right thing in this case. Anything that does short read/short write kind of stuff (or is in a loop, etc.) is unlikely to be a good one. Signed-off-by: Al Viro --- include/linux/uio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 6e22b544d039..e57c0ccd61c6 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -89,7 +89,9 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); +bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); @@ -155,6 +157,7 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) } size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); int import_iovec(int type, const struct iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, -- cgit From 15e6cb46c9b09711d1224ae5418b53140e1ba444 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 1 Nov 2016 22:42:45 -0400 Subject: make skb_add_data,{_nocache}() and skb_copy_to_page_nocache() advance only on success Signed-off-by: Al Viro --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 32810f279f8e..9cfae2e73b3c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2809,12 +2809,12 @@ static inline int skb_add_data(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; - if (csum_and_copy_from_iter(skb_put(skb, copy), copy, - &csum, from) == copy) { + if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, + &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } - } else if (copy_from_iter(skb_put(skb, copy), copy, from) == copy) + } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); -- cgit From 7bd509e311f408f7a5132fcdde2069af65fa05ae Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 4 Dec 2016 23:19:41 +0100 Subject: bpf: add prog_digest and expose it via fdinfo/netlink When loading a BPF program via bpf(2), calculate the digest over the program's instruction stream and store it in struct bpf_prog's digest member. This is done at a point in time before any instructions are rewritten by the verifier. Any unstable map file descriptor number part of the imm field will be zeroed for the hash. fdinfo example output for progs: # cat /proc/1590/fdinfo/5 pos: 0 flags: 02000002 mnt_id: 11 prog_type: 1 prog_jited: 1 prog_digest: b27e8b06da22707513aa97363dfb11c7c3675d28 memlock: 4096 When programs are pinned and retrieved by an ELF loader, the loader can check the program's digest through fdinfo and compare it against one that was generated over the ELF file's program section to see if the program needs to be reloaded. Furthermore, this can also be exposed through other means such as netlink in case of a tc cls/act dump (or xdp in future), but also through tracepoints or other facilities to identify the program. Other than that, the digest can also serve as a base name for the work in progress kallsyms support of programs. The digest doesn't depend/select the crypto layer, since we need to keep dependencies to a minimum. iproute2 will get support for this facility. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/linux/filter.h | 7 ++++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 69d0a7f12a3b..8796ff03f472 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,6 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +void bpf_prog_calc_digest(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 97338134398f..f078d2b1cff6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -14,6 +14,7 @@ #include #include #include +#include #include @@ -56,6 +57,9 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +/* Maximum BPF program size in bytes. */ +#define MAX_BPF_SIZE (BPF_MAXINSNS * sizeof(struct bpf_insn)) + /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -404,8 +408,9 @@ struct bpf_prog { cb_access:1, /* Is control block accessed? */ dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); - u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ + u32 len; /* Number of filter blocks */ + u32 digest[SHA_DIGEST_WORDS]; /* Program digest */ struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, -- cgit From 640eb7e7b5242af53c456552a526d0080e6333f8 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Mon, 14 Nov 2016 22:14:35 +0100 Subject: fs: Constify path_is_under()'s arguments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function path_is_under() doesn't modify the paths pointed by its arguments but only browse them. Constifying this pointers make a cleaner interface to be used by (future) code which may only have access to const struct path pointers (e.g. LSM hooks). Signed-off-by: Mickaël Salaün Cc: Alexander Viro Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..f96501b51c49 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2709,7 +2709,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); -extern bool path_is_under(struct path *, struct path *); +extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); -- cgit From 3cd5eca8d7a2fe43098df4c33a1272fe6945cac9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:19:09 -0500 Subject: fsnotify: constify 'data' passed to ->handle_event() Signed-off-by: Al Viro --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 79467b239fcf..d357041bbec8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -96,7 +96,7 @@ struct fsnotify_ops { struct inode *inode, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, - u32 mask, void *data, int data_type, + u32 mask, const void *data, int data_type, const unsigned char *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); -- cgit From e637835eccc8b93f39ca869628f9a0437bba744e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:21:17 -0500 Subject: fsnotify(): constify 'data' Signed-off-by: Al Viro --- include/linux/fsnotify_backend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d357041bbec8..e6ea6757a275 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -245,7 +245,7 @@ struct fsnotify_mark { /* called from the vfs helpers */ /* main fsnotify call to send events */ -extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, +extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, const unsigned char *name, u32 cookie); extern int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); @@ -357,7 +357,7 @@ extern void fsnotify_init_event(struct fsnotify_event *event, #else -static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, +static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, const unsigned char *name, u32 cookie) { return 0; -- cgit From 12c7f9dc0fd154632457f3474351bcfcf4e61512 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:23:04 -0500 Subject: constify fsnotify_parent() Signed-off-by: Al Viro --- include/linux/fsnotify.h | 2 +- include/linux/fsnotify_backend.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index b8bcc058e031..e19eb1f5e958 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,7 +17,7 @@ #include /* Notify this dentry's parent about a child's events. */ -static inline int fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) +static inline int fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask) { if (!dentry) dentry = path->dentry; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index e6ea6757a275..0cf34d6cc253 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -247,7 +247,7 @@ struct fsnotify_mark { /* main fsnotify call to send events */ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, const unsigned char *name, u32 cookie); -extern int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); +extern int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern u32 fsnotify_get_cookie(void); @@ -363,7 +363,7 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data, return 0; } -static inline int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) +static inline int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask) { return 0; } -- cgit From 40212d531d4bfac48dca8cd3d794639766745cda Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:24:41 -0500 Subject: fsnotify: constify the places working with ->f_path Signed-off-by: Al Viro --- include/linux/fsnotify.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index e19eb1f5e958..b43d3f5bd9ea 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -28,7 +28,7 @@ static inline int fsnotify_parent(const struct path *path, struct dentry *dentry /* simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { - struct path *path = &file->f_path; + const struct path *path = &file->f_path; /* * Do not use file_inode() here or anywhere in this file to get the * inode. That would break *notity on overlayfs. @@ -176,7 +176,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_access(struct file *file) { - struct path *path = &file->f_path; + const struct path *path = &file->f_path; struct inode *inode = path->dentry->d_inode; __u32 mask = FS_ACCESS; @@ -194,7 +194,7 @@ static inline void fsnotify_access(struct file *file) */ static inline void fsnotify_modify(struct file *file) { - struct path *path = &file->f_path; + const struct path *path = &file->f_path; struct inode *inode = path->dentry->d_inode; __u32 mask = FS_MODIFY; @@ -212,7 +212,7 @@ static inline void fsnotify_modify(struct file *file) */ static inline void fsnotify_open(struct file *file) { - struct path *path = &file->f_path; + const struct path *path = &file->f_path; struct inode *inode = path->dentry->d_inode; __u32 mask = FS_OPEN; @@ -228,7 +228,7 @@ static inline void fsnotify_open(struct file *file) */ static inline void fsnotify_close(struct file *file) { - struct path *path = &file->f_path; + const struct path *path = &file->f_path; struct inode *inode = path->dentry->d_inode; fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; -- cgit From 8bd107633b64195a0748b05236c3d14db0a8bed4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:36:51 -0500 Subject: audit_log_{name,link_denied}: constify struct path Signed-off-by: Al Viro --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 9d4443f93db6..f51fca8d0b6f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -147,7 +147,7 @@ extern void audit_log_d_path(struct audit_buffer *ab, extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_link_denied(const char *operation, - struct path *link); + const struct path *link); extern void audit_log_lost(const char *message); #ifdef CONFIG_SECURITY extern void audit_log_secctx(struct audit_buffer *ab, u32 secid); -- cgit From 71215a75ceddf38ba9d4563481da8dd943de10fc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 19:30:18 -0500 Subject: constify get_dcookie() and friends Signed-off-by: Al Viro --- include/linux/dcookies.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcookies.h b/include/linux/dcookies.h index 5ac3bdd5cee6..699b6c499c4f 100644 --- a/include/linux/dcookies.h +++ b/include/linux/dcookies.h @@ -44,7 +44,7 @@ void dcookie_unregister(struct dcookie_user * user); * * Returns 0 on success, with *cookie filled in */ -int get_dcookie(struct path *path, unsigned long *cookie); +int get_dcookie(const struct path *path, unsigned long *cookie); #else @@ -58,7 +58,7 @@ static inline void dcookie_unregister(struct dcookie_user * user) return; } -static inline int get_dcookie(struct path *path, unsigned long *cookie) +static inline int get_dcookie(const struct path *path, unsigned long *cookie) { return -ENOSYS; } -- cgit From a4141d7cf80fee99ace8d8a95dd358c98ad6ad69 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:28:12 -0500 Subject: constify alloc_file() Signed-off-by: Al Viro --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 7444f5feda12..61eb82cbafba 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -17,7 +17,7 @@ struct file_operations; struct vfsmount; struct dentry; struct path; -extern struct file *alloc_file(struct path *, fmode_t mode, +extern struct file *alloc_file(const struct path *, fmode_t mode, const struct file_operations *fop); static inline void fput_light(struct file *file, int fput_needed) -- cgit From 8c54ca9c6882f5a68d19a82fd063b74f91d4c22b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 19:49:34 -0500 Subject: quota: constify struct path in quota_on Signed-off-by: Al Viro --- include/linux/quota.h | 2 +- include/linux/quotaops.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 55107a8ff887..78a98821f9d0 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -431,7 +431,7 @@ struct qc_info { /* Operations handling requests from userspace */ struct quotactl_ops { - int (*quota_on)(struct super_block *, int, int, struct path *); + int (*quota_on)(struct super_block *, int, int, const struct path *); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index f00fa86ac966..799a63d0e1a8 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -90,7 +90,7 @@ int dquot_file_open(struct inode *inode, struct file *file); int dquot_enable(struct inode *inode, int type, int format_id, unsigned int flags); int dquot_quota_on(struct super_block *sb, int type, int format_id, - struct path *path); + const struct path *path); int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); int dquot_quota_off(struct super_block *sb, int type); -- cgit From ca71cf71eeda04dc9ad18271504e499013af5415 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 19:45:28 -0500 Subject: namespace.c: constify struct path passed to a bunch of primitives Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/mount.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f96501b51c49..3056fe46f336 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2123,7 +2123,7 @@ extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern long do_mount(const char *, const char __user *, const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(struct path *); +extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); diff --git a/include/linux/mount.h b/include/linux/mount.h index 1172cce949a4..cf2b5784b649 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -79,12 +79,12 @@ extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); -extern struct vfsmount *mnt_clone_internal(struct path *path); +extern struct vfsmount *mnt_clone_internal(const struct path *path); extern int __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); struct path; -extern struct vfsmount *clone_private_mount(struct path *path); +extern struct vfsmount *clone_private_mount(const struct path *path); struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, -- cgit From f0bb5aaf2c51267c49ed5e2c6103df22acfe30f5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 20 Nov 2016 20:27:12 -0500 Subject: vfs: misc struct path constification Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3056fe46f336..0e177d395efb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2127,7 +2127,7 @@ extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); -extern int vfs_statfs(struct path *, struct kstatfs *); +extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int vfs_ustat(dev_t, struct kstatfs *); -- cgit From 0f0fe7e01327b3d524787a2e8b7e78f010db2bb8 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 1 Dec 2016 16:28:17 +0530 Subject: PM / OPP: Manage supply's voltage/current in a separate structure This is a preparatory step for multiple regulator per device support. Move the voltage/current variables to a new structure. Signed-off-by: Viresh Kumar Tested-by: Dave Gerlach Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index f6bc76501912..824f7268f687 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -25,6 +25,22 @@ enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, }; +/** + * struct dev_pm_opp_supply - Power supply voltage/current values + * @u_volt: Target voltage in microvolts corresponding to this OPP + * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP + * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP + * @u_amp: Maximum current drawn by the device in microamperes + * + * This structure stores the voltage/current values for a single power supply. + */ +struct dev_pm_opp_supply { + unsigned long u_volt; + unsigned long u_volt_min; + unsigned long u_volt_max; + unsigned long u_amp; +}; + #if defined(CONFIG_PM_OPP) unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); -- cgit From dfbe4678d709e25e0f36e6b6333e2a7a67aefb7e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 1 Dec 2016 16:28:19 +0530 Subject: PM / OPP: Add infrastructure to manage multiple regulators This patch adds infrastructure to manage multiple regulators and updates the only user (cpufreq-dt) of dev_pm_opp_set{put}_regulator(). This is preparatory work for adding full support for devices with multiple regulators. Signed-off-by: Viresh Kumar Tested-by: Dave Gerlach Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 824f7268f687..9a825ae78653 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -79,8 +79,8 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); -struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name); -void dev_pm_opp_put_regulator(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); +void dev_pm_opp_put_regulators(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -187,12 +187,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} -static inline struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name) +static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_put_regulator(struct opp_table *opp_table) {} +static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { -- cgit From 947355850fcb3bb6549294316667d0f53bc03082 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 1 Dec 2016 16:28:20 +0530 Subject: PM / OPP: Separate out _generic_set_opp() Later patches would add support for custom set_opp() callbacks. This patch separates out the code for _generic_set_opp() handler in order to prepare for that. Signed-off-by: Viresh Kumar Tested-by: Dave Gerlach Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 9a825ae78653..779b40a9287d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -17,6 +17,8 @@ #include #include +struct clk; +struct regulator; struct dev_pm_opp; struct device; struct opp_table; @@ -41,6 +43,39 @@ struct dev_pm_opp_supply { unsigned long u_amp; }; +/** + * struct dev_pm_opp_info - OPP freq/voltage/current values + * @rate: Target clk rate in hz + * @supplies: Array of voltage/current values for all power supplies + * + * This structure stores the freq/voltage/current values for a single OPP. + */ +struct dev_pm_opp_info { + unsigned long rate; + struct dev_pm_opp_supply *supplies; +}; + +/** + * struct dev_pm_set_opp_data - Set OPP data + * @old_opp: Old OPP info + * @new_opp: New OPP info + * @regulators: Array of regulator pointers + * @regulator_count: Number of regulators + * @clk: Pointer to clk + * @dev: Pointer to the struct device + * + * This structure contains all information required for setting an OPP. + */ +struct dev_pm_set_opp_data { + struct dev_pm_opp_info old_opp; + struct dev_pm_opp_info new_opp; + + struct regulator **regulators; + unsigned int regulator_count; + struct clk *clk; + struct device *dev; +}; + #if defined(CONFIG_PM_OPP) unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); -- cgit From 4dab160eb1586f67e8ba7c55ffdd2373f7a5553e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 1 Dec 2016 16:28:21 +0530 Subject: PM / OPP: Allow platform specific custom set_opp() callbacks The generic set_opp() handler isn't sufficient for platforms with complex DVFS. For example, some TI platforms have multiple regulators for a CPU device. The order in which various supplies need to be programmed is only known to the platform code and its best to leave it to it. This patch implements APIs to register platform specific set_opp() callback. Signed-off-by: Viresh Kumar Tested-by: Dave Gerlach Reviewed-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 779b40a9287d..0edd88f93904 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -116,6 +116,8 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); void dev_pm_opp_put_regulators(struct opp_table *opp_table); +int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); +void dev_pm_opp_register_put_opp_helper(struct device *dev); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -215,6 +217,14 @@ static inline int dev_pm_opp_set_supported_hw(struct device *dev, static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} +static inline int dev_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + return -ENOTSUPP; +} + +static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {} + static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return -ENOTSUPP; -- cgit From a317178e36b52f5f24ad226a77403eeea5ac05c4 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 21 Oct 2016 23:51:54 +0300 Subject: parser: add u64 number parser Will be used by the nvme-fabrics FC transport in parsing options Signed-off-by: James Smart Signed-off-by: Sagi Grimberg --- include/linux/parser.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index 39d5b7955b23..884c1e6eb3fe 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -27,6 +27,7 @@ typedef struct { int match_token(char *, const match_table_t table, substring_t args[]); int match_int(substring_t *, int *result); +int match_u64(substring_t *, u64 *result); int match_octal(substring_t *, int *result); int match_hex(substring_t *, int *result); bool match_wildcard(const char *pattern, const char *str); -- cgit From cba3bdfd2e89edd706e2c40dfad914aca663b6ac Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 2 Dec 2016 00:28:39 -0800 Subject: nvme-fabrics: Add FC transport error codes to nvme.h Signed-off-by: James Smart Reviewed-by: Christoph Hellwig Reviewed-by: Jay Freyensee Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 0df9466a7c38..5ac1f57226f4 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -963,6 +963,19 @@ enum { NVME_SC_ACCESS_DENIED = 0x286, NVME_SC_DNR = 0x4000, + + + /* + * FC Transport-specific error status values for NVME commands + * + * Transport-specific status code values must be in the range 0xB0..0xBF + */ + + /* Generic FC failure - catchall */ + NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, + + /* I/O failure due to FC ABTS'd */ + NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { -- cgit From b1ad1475b447a7668ac8bfad77277c4405941883 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 2 Dec 2016 00:28:40 -0800 Subject: nvme-fabrics: Add FC transport FC-NVME definitions - Formats for Cmd, Data, Rsp IUs - Formats FC-4 LS definitions - Add to MAINTAINERS file Signed-off-by: James Smart Reviewed-by: Christoph Hellwig Reviewed-by: Jay Freyensee Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc.h | 268 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 268 insertions(+) create mode 100644 include/linux/nvme-fc.h (limited to 'include/linux') diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h new file mode 100644 index 000000000000..4b45226bd604 --- /dev/null +++ b/include/linux/nvme-fc.h @@ -0,0 +1,268 @@ +/* + * Copyright (c) 2016 Avago Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful. + * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, + * INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A + * PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO + * THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. + * See the GNU General Public License for more details, a copy of which + * can be found in the file COPYING included with this package + * + */ + +/* + * This file contains definitions relative to FC-NVME r1.11 and a few + * newer items + */ + +#ifndef _NVME_FC_H +#define _NVME_FC_H 1 + + +#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FC_ID FC_TYPE_NVME + +/* FC-NVME Cmd IU Flags */ +#define FCNVME_CMD_FLAGS_DIRMASK 0x03 +#define FCNVME_CMD_FLAGS_WRITE 0x01 +#define FCNVME_CMD_FLAGS_READ 0x02 + +struct nvme_fc_cmd_iu { + __u8 scsi_id; + __u8 fc_id; + __be16 iu_len; + __u8 rsvd4[3]; + __u8 flags; + __be64 connection_id; + __be32 csn; + __be32 data_len; + struct nvme_command sqe; + __be32 rsvd88[2]; +}; + +#define NVME_FC_SIZEOF_ZEROS_RSP 12 + +struct nvme_fc_ersp_iu { + __u8 rsvd0[2]; + __be16 iu_len; + __be32 rsn; + __be32 xfrd_len; + __be32 rsvd12; + struct nvme_completion cqe; + /* for now - no additional payload */ +}; + + +/* FC-NVME r1.03/16-119v0 NVME Link Services */ +enum { + FCNVME_LS_RSVD = 0, + FCNVME_LS_RJT = 1, + FCNVME_LS_ACC = 2, + FCNVME_LS_CREATE_ASSOCIATION = 3, + FCNVME_LS_CREATE_CONNECTION = 4, + FCNVME_LS_DISCONNECT = 5, +}; + +/* FC-NVME r1.03/16-119v0 NVME Link Service Descriptors */ +enum { + FCNVME_LSDESC_RSVD = 0x0, + FCNVME_LSDESC_RQST = 0x1, + FCNVME_LSDESC_RJT = 0x2, + FCNVME_LSDESC_CREATE_ASSOC_CMD = 0x3, + FCNVME_LSDESC_CREATE_CONN_CMD = 0x4, + FCNVME_LSDESC_DISCONN_CMD = 0x5, + FCNVME_LSDESC_CONN_ID = 0x6, + FCNVME_LSDESC_ASSOC_ID = 0x7, +}; + + +/* ********** start of Link Service Descriptors ********** */ + + +/* + * fills in length of a descriptor. Struture minus descriptor header + */ +static inline __be32 fcnvme_lsdesc_len(size_t sz) +{ + return cpu_to_be32(sz - (2 * sizeof(u32))); +} + + +struct fcnvme_ls_rqst_w0 { + u8 ls_cmd; /* FCNVME_LS_xxx */ + u8 zeros[3]; +}; + +/* FCNVME_LSDESC_RQST */ +struct fcnvme_lsdesc_rqst { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + struct fcnvme_ls_rqst_w0 w0; + __be32 rsvd12; +}; + + + + +/* FCNVME_LSDESC_RJT */ +struct fcnvme_lsdesc_rjt { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + u8 rsvd8; + + /* + * Reject reason and explanaction codes are generic + * to ELs's from LS-3. + */ + u8 reason_code; + u8 reason_explanation; + + u8 vendor; + __be32 rsvd12; +}; + + +#define FCNVME_ASSOC_HOSTID_LEN 64 +#define FCNVME_ASSOC_HOSTNQN_LEN 256 +#define FCNVME_ASSOC_SUBNQN_LEN 256 + +/* FCNVME_LSDESC_CREATE_ASSOC_CMD */ +struct fcnvme_lsdesc_cr_assoc_cmd { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + __be16 ersp_ratio; + __be16 rsvd10; + __be32 rsvd12[9]; + __be16 cntlid; + __be16 sqsize; + __be32 rsvd52; + u8 hostid[FCNVME_ASSOC_HOSTID_LEN]; + u8 hostnqn[FCNVME_ASSOC_HOSTNQN_LEN]; + u8 subnqn[FCNVME_ASSOC_SUBNQN_LEN]; + u8 rsvd632[384]; +}; + +/* FCNVME_LSDESC_CREATE_CONN_CMD */ +struct fcnvme_lsdesc_cr_conn_cmd { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + __be16 ersp_ratio; + __be16 rsvd10; + __be32 rsvd12[9]; + __be16 qid; + __be16 sqsize; + __be32 rsvd52; +}; + +/* Disconnect Scope Values */ +enum { + FCNVME_DISCONN_ASSOCIATION = 0, + FCNVME_DISCONN_CONNECTION = 1, +}; + +/* FCNVME_LSDESC_DISCONN_CMD */ +struct fcnvme_lsdesc_disconn_cmd { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + u8 rsvd8[3]; + /* note: scope is really a 1 bit field */ + u8 scope; /* FCNVME_DISCONN_xxx */ + __be32 rsvd12; + __be64 id; +}; + +/* FCNVME_LSDESC_CONN_ID */ +struct fcnvme_lsdesc_conn_id { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + __be64 connection_id; +}; + +/* FCNVME_LSDESC_ASSOC_ID */ +struct fcnvme_lsdesc_assoc_id { + __be32 desc_tag; /* FCNVME_LSDESC_xxx */ + __be32 desc_len; + __be64 association_id; +}; + +/* r_ctl values */ +enum { + FCNVME_RS_RCTL_DATA = 1, + FCNVME_RS_RCTL_XFER_RDY = 5, + FCNVME_RS_RCTL_RSP = 8, +}; + + +/* ********** start of Link Services ********** */ + + +/* FCNVME_LS_RJT */ +struct fcnvme_ls_rjt { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_rqst rqst; + struct fcnvme_lsdesc_rjt rjt; +}; + +/* FCNVME_LS_ACC */ +struct fcnvme_ls_acc_hdr { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_rqst rqst; + /* Followed by cmd-specific ACC descriptors, see next definitions */ +}; + +/* FCNVME_LS_CREATE_ASSOCIATION */ +struct fcnvme_ls_cr_assoc_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_cr_assoc_cmd assoc_cmd; +}; + +struct fcnvme_ls_cr_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_conn_id connectid; +}; + + +/* FCNVME_LS_CREATE_CONNECTION */ +struct fcnvme_ls_cr_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_cr_conn_cmd connect_cmd; +}; + +struct fcnvme_ls_cr_conn_acc { + struct fcnvme_ls_acc_hdr hdr; + struct fcnvme_lsdesc_conn_id connectid; +}; + +/* FCNVME_LS_DISCONNECT */ +struct fcnvme_ls_disconnect_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd discon_cmd; +}; + +struct fcnvme_ls_disconnect_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* + * Yet to be defined in FC-NVME: + */ +#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ +#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ +#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ + + +#endif /* _NVME_FC_H */ -- cgit From d6d20012e116904065d192be6146040c99c03c3c Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 2 Dec 2016 00:28:41 -0800 Subject: nvme-fabrics: Add FC transport LLDD api definitions Host: - LLDD registration with the host transport - registering host ports (local ports) and target ports seen on fabric (remote ports) - Data structures and call points for FC-4 LS's and FCP IO requests Target: - LLDD registration with the target transport - registering nvme subsystem ports (target ports) - Data structures and call points for reception of FC-4 LS's and FCP IO requests, and callbacks to perform data and rsp transfers for the io. Add to MAINTAINERS file Signed-off-by: James Smart Reviewed-by: Christoph Hellwig Reviewed-by: Jay Freyensee Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc-driver.h | 851 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 851 insertions(+) create mode 100644 include/linux/nvme-fc-driver.h (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h new file mode 100644 index 000000000000..f21471f7ee40 --- /dev/null +++ b/include/linux/nvme-fc-driver.h @@ -0,0 +1,851 @@ +/* + * Copyright (c) 2016, Avago Technologies + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _NVME_FC_DRIVER_H +#define _NVME_FC_DRIVER_H 1 + + +/* + * ********************** LLDD FC-NVME Host API ******************** + * + * For FC LLDD's that are the NVME Host role. + * + * ****************************************************************** + */ + + + +/* FC Port role bitmask - can merge with FC Port Roles in fc transport */ +#define FC_PORT_ROLE_NVME_INITIATOR 0x10 +#define FC_PORT_ROLE_NVME_TARGET 0x11 +#define FC_PORT_ROLE_NVME_DISCOVERY 0x12 + + +/** + * struct nvme_fc_port_info - port-specific ids and FC connection-specific + * data element used during NVME Host role + * registrations + * + * Static fields describing the port being registered: + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) + * + * Initialization values for dynamic port fields: + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + */ +struct nvme_fc_port_info { + u64 node_name; + u64 port_name; + u32 port_role; + u32 port_id; +}; + + +/** + * struct nvmefc_ls_req - Request structure passed from NVME-FC transport + * to LLDD in order to perform a NVME FC-4 LS + * request and obtain a response. + * + * Values set by the NVME-FC layer prior to calling the LLDD ls_req + * entrypoint. + * @rqstaddr: pointer to request buffer + * @rqstdma: PCI DMA address of request buffer + * @rqstlen: Length, in bytes, of request buffer + * @rspaddr: pointer to response buffer + * @rspdma: PCI DMA address of response buffer + * @rsplen: Length, in bytes, of response buffer + * @timeout: Maximum amount of time, in seconds, to wait for the LS response. + * If timeout exceeded, LLDD to abort LS exchange and complete + * LS request with error status. + * @private: pointer to memory allocated alongside the ls request structure + * that is specifically for the LLDD to use while processing the + * request. The length of the buffer corresponds to the + * lsrqst_priv_sz value specified in the nvme_fc_port_template + * supplied by the LLDD. + * @done: The callback routine the LLDD is to invoke upon completion of + * the LS request. req argument is the pointer to the original LS + * request structure. Status argument must be 0 upon success, a + * negative errno on failure (example: -ENXIO). + */ +struct nvmefc_ls_req { + void *rqstaddr; + dma_addr_t rqstdma; + u32 rqstlen; + void *rspaddr; + dma_addr_t rspdma; + u32 rsplen; + u32 timeout; + + void *private; + + void (*done)(struct nvmefc_ls_req *req, int status); + +} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ + + +enum nvmefc_fcp_datadir { + NVMEFC_FCP_NODATA, /* payload_length and sg_cnt will be zero */ + NVMEFC_FCP_WRITE, + NVMEFC_FCP_READ, +}; + + +#define NVME_FC_MAX_SEGMENTS 256 + +/** + * struct nvmefc_fcp_req - Request structure passed from NVME-FC transport + * to LLDD in order to perform a NVME FCP IO operation. + * + * Values set by the NVME-FC layer prior to calling the LLDD fcp_io + * entrypoint. + * @cmdaddr: pointer to the FCP CMD IU buffer + * @rspaddr: pointer to the FCP RSP IU buffer + * @cmddma: PCI DMA address of the FCP CMD IU buffer + * @rspdma: PCI DMA address of the FCP RSP IU buffer + * @cmdlen: Length, in bytes, of the FCP CMD IU buffer + * @rsplen: Length, in bytes, of the FCP RSP IU buffer + * @payload_length: Length of DATA_IN or DATA_OUT payload data to transfer + * @sg_table: scatter/gather structure for payload data + * @first_sgl: memory for 1st scatter/gather list segment for payload data + * @sg_cnt: number of elements in the scatter/gather list + * @io_dir: direction of the FCP request (see NVMEFC_FCP_xxx) + * @sqid: The nvme SQID the command is being issued on + * @done: The callback routine the LLDD is to invoke upon completion of + * the FCP operation. req argument is the pointer to the original + * FCP IO operation. + * @private: pointer to memory allocated alongside the FCP operation + * request structure that is specifically for the LLDD to use + * while processing the operation. The length of the buffer + * corresponds to the fcprqst_priv_sz value specified in the + * nvme_fc_port_template supplied by the LLDD. + * + * Values set by the LLDD indicating completion status of the FCP operation. + * Must be set prior to calling the done() callback. + * @transferred_length: amount of payload data, in bytes, that were + * transferred. Should equal payload_length on success. + * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. + * @status: Completion status of the FCP operation. must be 0 upon success, + * NVME_SC_FC_xxx value upon failure. Note: this is NOT a + * reflection of the NVME CQE completion status. Only the status + * of the FCP operation at the NVME-FC level. + */ +struct nvmefc_fcp_req { + void *cmdaddr; + void *rspaddr; + dma_addr_t cmddma; + dma_addr_t rspdma; + u16 cmdlen; + u16 rsplen; + + u32 payload_length; + struct sg_table sg_table; + struct scatterlist *first_sgl; + int sg_cnt; + enum nvmefc_fcp_datadir io_dir; + + __le16 sqid; + + void (*done)(struct nvmefc_fcp_req *req); + + void *private; + + u32 transferred_length; + u16 rcv_rsplen; + u32 status; +} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ + + +/* + * Direct copy of fc_port_state enum. For later merging + */ +enum nvme_fc_obj_state { + FC_OBJSTATE_UNKNOWN, + FC_OBJSTATE_NOTPRESENT, + FC_OBJSTATE_ONLINE, + FC_OBJSTATE_OFFLINE, /* User has taken Port Offline */ + FC_OBJSTATE_BLOCKED, + FC_OBJSTATE_BYPASSED, + FC_OBJSTATE_DIAGNOSTICS, + FC_OBJSTATE_LINKDOWN, + FC_OBJSTATE_ERROR, + FC_OBJSTATE_LOOPBACK, + FC_OBJSTATE_DELETED, +}; + + +/** + * struct nvme_fc_local_port - structure used between NVME-FC transport and + * a LLDD to reference a local NVME host port. + * Allocated/created by the nvme_fc_register_localport() + * transport interface. + * + * Fields with static values for the port. Initialized by the + * port_info struct supplied to the registration call. + * @port_num: NVME-FC transport host port number + * @port_role: NVME roles are supported on the port (see FC_PORT_ROLE_xxx) + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @private: pointer to memory allocated alongside the local port + * structure that is specifically for the LLDD to use. + * The length of the buffer corresponds to the local_priv_sz + * value specified in the nvme_fc_port_template supplied by + * the LLDD. + * + * Fields with dynamic values. Values may change base on link state. LLDD + * may reference fields directly to change them. Initialized by the + * port_info struct supplied to the registration call. + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + * @port_state: Operational state of the port. + */ +struct nvme_fc_local_port { + /* static/read-only fields */ + u32 port_num; + u32 port_role; + u64 node_name; + u64 port_name; + + void *private; + + /* dynamic fields */ + u32 port_id; + enum nvme_fc_obj_state port_state; +} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ + + +/** + * struct nvme_fc_remote_port - structure used between NVME-FC transport and + * a LLDD to reference a remote NVME subsystem port. + * Allocated/created by the nvme_fc_register_remoteport() + * transport interface. + * + * Fields with static values for the port. Initialized by the + * port_info struct supplied to the registration call. + * @port_num: NVME-FC transport remote subsystem port number + * @port_role: NVME roles are supported on the port (see FC_PORT_ROLE_xxx) + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @localport: pointer to the NVME-FC local host port the subsystem is + * connected to. + * @private: pointer to memory allocated alongside the remote port + * structure that is specifically for the LLDD to use. + * The length of the buffer corresponds to the remote_priv_sz + * value specified in the nvme_fc_port_template supplied by + * the LLDD. + * + * Fields with dynamic values. Values may change base on link or login + * state. LLDD may reference fields directly to change them. Initialized by + * the port_info struct supplied to the registration call. + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + * @port_state: Operational state of the remote port. Valid values are + * ONLINE or UNKNOWN. + */ +struct nvme_fc_remote_port { + /* static fields */ + u32 port_num; + u32 port_role; + u64 node_name; + u64 port_name; + + struct nvme_fc_local_port *localport; + + void *private; + + /* dynamic fields */ + u32 port_id; + enum nvme_fc_obj_state port_state; +} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ + + +/** + * struct nvme_fc_port_template - structure containing static entrypoints and + * operational parameters for an LLDD that supports NVME host + * behavior. Passed by reference in port registrations. + * NVME-FC transport remembers template reference and may + * access it during runtime operation. + * + * Host/Initiator Transport Entrypoints/Parameters: + * + * @localport_delete: The LLDD initiates deletion of a localport via + * nvme_fc_deregister_localport(). However, the teardown is + * asynchronous. This routine is called upon the completion of the + * teardown to inform the LLDD that the localport has been deleted. + * Entrypoint is Mandatory. + * + * @remoteport_delete: The LLDD initiates deletion of a remoteport via + * nvme_fc_deregister_remoteport(). However, the teardown is + * asynchronous. This routine is called upon the completion of the + * teardown to inform the LLDD that the remoteport has been deleted. + * Entrypoint is Mandatory. + * + * @create_queue: Upon creating a host<->controller association, queues are + * created such that they can be affinitized to cpus/cores. This + * callback into the LLDD to notify that a controller queue is being + * created. The LLDD may choose to allocate an associated hw queue + * or map it onto a shared hw queue. Upon return from the call, the + * LLDD specifies a handle that will be given back to it for any + * command that is posted to the controller queue. The handle can + * be used by the LLDD to map quickly to the proper hw queue for + * command execution. The mask of cpu's that will map to this queue + * at the block-level is also passed in. The LLDD should use the + * queue id and/or cpu masks to ensure proper affinitization of the + * controller queue to the hw queue. + * Entrypoint is Optional. + * + * @delete_queue: This is the inverse of the crete_queue. During + * host<->controller association teardown, this routine is called + * when a controller queue is being terminated. Any association with + * a hw queue should be termined. If there is a unique hw queue, the + * hw queue should be torn down. + * Entrypoint is Optional. + * + * @poll_queue: Called to poll for the completion of an io on a blk queue. + * Entrypoint is Optional. + * + * @ls_req: Called to issue a FC-NVME FC-4 LS service request. + * The nvme_fc_ls_req structure will fully describe the buffers for + * the request payload and where to place the response payload. The + * LLDD is to allocate an exchange, issue the LS request, obtain the + * LS response, and call the "done" routine specified in the request + * structure (argument to done is the ls request structure itself). + * Entrypoint is Mandatory. + * + * @fcp_io: called to issue a FC-NVME I/O request. The I/O may be for + * an admin queue or an i/o queue. The nvmefc_fcp_req structure will + * fully describe the io: the buffer containing the FC-NVME CMD IU + * (which contains the SQE), the sg list for the payload if applicable, + * and the buffer to place the FC-NVME RSP IU into. The LLDD will + * complete the i/o, indicating the amount of data transferred or + * any transport error, and call the "done" routine specified in the + * request structure (argument to done is the fcp request structure + * itself). + * Entrypoint is Mandatory. + * + * @ls_abort: called to request the LLDD to abort the indicated ls request. + * The call may return before the abort has completed. After aborting + * the request, the LLDD must still call the ls request done routine + * indicating an FC transport Aborted status. + * Entrypoint is Mandatory. + * + * @fcp_abort: called to request the LLDD to abort the indicated fcp request. + * The call may return before the abort has completed. After aborting + * the request, the LLDD must still call the fcp request done routine + * indicating an FC transport Aborted status. + * Entrypoint is Mandatory. + * + * @max_hw_queues: indicates the maximum number of hw queues the LLDD + * supports for cpu affinitization. + * Value is Mandatory. Must be at least 1. + * + * @max_sgl_segments: indicates the maximum number of sgl segments supported + * by the LLDD + * Value is Mandatory. Must be at least 1. Recommend at least 256. + * + * @max_dif_sgl_segments: indicates the maximum number of sgl segments + * supported by the LLDD for DIF operations. + * Value is Mandatory. Must be at least 1. Recommend at least 256. + * + * @dma_boundary: indicates the dma address boundary where dma mappings + * will be split across. + * Value is Mandatory. Typical value is 0xFFFFFFFF to split across + * 4Gig address boundarys + * + * @local_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like fc nvme layer to allocate on the LLDD's + * behalf whenever a localport is allocated. The additional memory + * area solely for the of the LLDD and its location is specified by + * the localport->private pointer. + * Value is Mandatory. Allowed to be zero. + * + * @remote_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like fc nvme layer to allocate on the LLDD's + * behalf whenever a remoteport is allocated. The additional memory + * area solely for the of the LLDD and its location is specified by + * the remoteport->private pointer. + * Value is Mandatory. Allowed to be zero. + * + * @lsrqst_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like fc nvme layer to allocate on the LLDD's + * behalf whenever a ls request structure is allocated. The additional + * memory area solely for the of the LLDD and its location is + * specified by the ls_request->private pointer. + * Value is Mandatory. Allowed to be zero. + * + * @fcprqst_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like fc nvme layer to allocate on the LLDD's + * behalf whenever a fcp request structure is allocated. The additional + * memory area solely for the of the LLDD and its location is + * specified by the fcp_request->private pointer. + * Value is Mandatory. Allowed to be zero. + */ +struct nvme_fc_port_template { + /* initiator-based functions */ + void (*localport_delete)(struct nvme_fc_local_port *); + void (*remoteport_delete)(struct nvme_fc_remote_port *); + int (*create_queue)(struct nvme_fc_local_port *, + unsigned int qidx, u16 qsize, + void **handle); + void (*delete_queue)(struct nvme_fc_local_port *, + unsigned int qidx, void *handle); + void (*poll_queue)(struct nvme_fc_local_port *, void *handle); + int (*ls_req)(struct nvme_fc_local_port *, + struct nvme_fc_remote_port *, + struct nvmefc_ls_req *); + int (*fcp_io)(struct nvme_fc_local_port *, + struct nvme_fc_remote_port *, + void *hw_queue_handle, + struct nvmefc_fcp_req *); + void (*ls_abort)(struct nvme_fc_local_port *, + struct nvme_fc_remote_port *, + struct nvmefc_ls_req *); + void (*fcp_abort)(struct nvme_fc_local_port *, + struct nvme_fc_remote_port *, + void *hw_queue_handle, + struct nvmefc_fcp_req *); + + u32 max_hw_queues; + u16 max_sgl_segments; + u16 max_dif_sgl_segments; + u64 dma_boundary; + + /* sizes of additional private data for data structures */ + u32 local_priv_sz; + u32 remote_priv_sz; + u32 lsrqst_priv_sz; + u32 fcprqst_priv_sz; +}; + + +/* + * Initiator/Host functions + */ + +int nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, + struct nvme_fc_port_template *template, + struct device *dev, + struct nvme_fc_local_port **lport_p); + +int nvme_fc_unregister_localport(struct nvme_fc_local_port *localport); + +int nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, + struct nvme_fc_port_info *pinfo, + struct nvme_fc_remote_port **rport_p); + +int nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *remoteport); + + + +/* + * *************** LLDD FC-NVME Target/Subsystem API *************** + * + * For FC LLDD's that are the NVME Subsystem role + * + * ****************************************************************** + */ + +/** + * struct nvmet_fc_port_info - port-specific ids and FC connection-specific + * data element used during NVME Subsystem role + * registrations + * + * Static fields describing the port being registered: + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * + * Initialization values for dynamic port fields: + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + */ +struct nvmet_fc_port_info { + u64 node_name; + u64 port_name; + u32 port_id; +}; + + +/** + * struct nvmefc_tgt_ls_req - Structure used between LLDD and NVMET-FC + * layer to represent the exchange context for + * a FC-NVME Link Service (LS). + * + * The structure is allocated by the LLDD whenever a LS Request is received + * from the FC link. The address of the structure is passed to the nvmet-fc + * layer via the nvmet_fc_rcv_ls_req() call. The address of the structure + * will be passed back to the LLDD when the response is to be transmit. + * The LLDD is to use the address to map back to the LLDD exchange structure + * which maintains information such as the targetport the LS was received + * on, the remote FC NVME initiator that sent the LS, and any FC exchange + * context. Upon completion of the LS response transmit, the address of the + * structure will be passed back to the LS rsp done() routine, allowing the + * nvmet-fc layer to release dma resources. Upon completion of the done() + * routine, no further access will be made by the nvmet-fc layer and the + * LLDD can de-allocate the structure. + * + * Field initialization: + * At the time of the nvmet_fc_rcv_ls_req() call, there is no content that + * is valid in the structure. + * + * When the structure is used for the LLDD->xmt_ls_rsp() call, the nvmet-fc + * layer will fully set the fields in order to specify the response + * payload buffer and its length as well as the done routine to be called + * upon compeletion of the transmit. The nvmet-fc layer will also set a + * private pointer for its own use in the done routine. + * + * Values set by the NVMET-FC layer prior to calling the LLDD xmt_ls_rsp + * entrypoint. + * @rspbuf: pointer to the LS response buffer + * @rspdma: PCI DMA address of the LS response buffer + * @rsplen: Length, in bytes, of the LS response buffer + * @done: The callback routine the LLDD is to invoke upon completion of + * transmitting the LS response. req argument is the pointer to + * the original ls request. + * @nvmet_fc_private: pointer to an internal NVMET-FC layer structure used + * as part of the NVMET-FC processing. The LLDD is not to access + * this pointer. + */ +struct nvmefc_tgt_ls_req { + void *rspbuf; + dma_addr_t rspdma; + u16 rsplen; + + void (*done)(struct nvmefc_tgt_ls_req *req); + void *nvmet_fc_private; /* LLDD is not to access !! */ +}; + +/* Operations that NVME-FC layer may request the LLDD to perform for FCP */ +enum { + NVMET_FCOP_READDATA = 1, /* xmt data to initiator */ + NVMET_FCOP_WRITEDATA = 2, /* xmt data from initiator */ + NVMET_FCOP_READDATA_RSP = 3, /* xmt data to initiator and send + * rsp as well + */ + NVMET_FCOP_RSP = 4, /* send rsp frame */ + NVMET_FCOP_ABORT = 5, /* abort exchange via ABTS */ + NVMET_FCOP_BA_ACC = 6, /* send BA_ACC */ + NVMET_FCOP_BA_RJT = 7, /* send BA_RJT */ +}; + +/** + * struct nvmefc_tgt_fcp_req - Structure used between LLDD and NVMET-FC + * layer to represent the exchange context and + * the specific FC-NVME IU operation(s) to perform + * for a FC-NVME FCP IO. + * + * Structure used between LLDD and nvmet-fc layer to represent the exchange + * context for a FC-NVME FCP I/O operation (e.g. a nvme sqe, the sqe-related + * memory transfers, and its assocated cqe transfer). + * + * The structure is allocated by the LLDD whenever a FCP CMD IU is received + * from the FC link. The address of the structure is passed to the nvmet-fc + * layer via the nvmet_fc_rcv_fcp_req() call. The address of the structure + * will be passed back to the LLDD for the data operations and transmit of + * the response. The LLDD is to use the address to map back to the LLDD + * exchange structure which maintains information such as the targetport + * the FCP I/O was received on, the remote FC NVME initiator that sent the + * FCP I/O, and any FC exchange context. Upon completion of the FCP target + * operation, the address of the structure will be passed back to the FCP + * op done() routine, allowing the nvmet-fc layer to release dma resources. + * Upon completion of the done() routine for either RSP or ABORT ops, no + * further access will be made by the nvmet-fc layer and the LLDD can + * de-allocate the structure. + * + * Field initialization: + * At the time of the nvmet_fc_rcv_fcp_req() call, there is no content that + * is valid in the structure. + * + * When the structure is used for an FCP target operation, the nvmet-fc + * layer will fully set the fields in order to specify the scattergather + * list, the transfer length, as well as the done routine to be called + * upon compeletion of the operation. The nvmet-fc layer will also set a + * private pointer for its own use in the done routine. + * + * Note: the LLDD must never fail a NVMET_FCOP_ABORT request !! + * + * Values set by the NVMET-FC layer prior to calling the LLDD fcp_op + * entrypoint. + * @op: Indicates the FCP IU operation to perform (see NVMET_FCOP_xxx) + * @hwqid: Specifies the hw queue index (0..N-1, where N is the + * max_hw_queues value from the LLD's nvmet_fc_target_template) + * that the operation is to use. + * @offset: Indicates the DATA_OUT/DATA_IN payload offset to be tranferred. + * Field is only valid on WRITEDATA, READDATA, or READDATA_RSP ops. + * @timeout: amount of time, in seconds, to wait for a response from the NVME + * host. A value of 0 is an infinite wait. + * Valid only for the following ops: + * WRITEDATA: caps the wait for data reception + * READDATA_RSP & RSP: caps wait for FCP_CONF reception (if used) + * @transfer_length: the length, in bytes, of the DATA_OUT or DATA_IN payload + * that is to be transferred. + * Valid only for the WRITEDATA, READDATA, or READDATA_RSP ops. + * @ba_rjt: Contains the BA_RJT payload that is to be transferred. + * Valid only for the NVMET_FCOP_BA_RJT op. + * @sg: Scatter/gather list for the DATA_OUT/DATA_IN payload data. + * Valid only for the WRITEDATA, READDATA, or READDATA_RSP ops. + * @sg_cnt: Number of valid entries in the scatter/gather list. + * Valid only for the WRITEDATA, READDATA, or READDATA_RSP ops. + * @rspaddr: pointer to the FCP RSP IU buffer to be transmit + * Used by RSP and READDATA_RSP ops + * @rspdma: PCI DMA address of the FCP RSP IU buffer + * Used by RSP and READDATA_RSP ops + * @rsplen: Length, in bytes, of the FCP RSP IU buffer + * Used by RSP and READDATA_RSP ops + * @done: The callback routine the LLDD is to invoke upon completion of + * the operation. req argument is the pointer to the original + * FCP subsystem op request. + * @nvmet_fc_private: pointer to an internal NVMET-FC layer structure used + * as part of the NVMET-FC processing. The LLDD is not to + * reference this field. + * + * Values set by the LLDD indicating completion status of the FCP operation. + * Must be set prior to calling the done() callback. + * @transferred_length: amount of DATA_OUT payload data received by a + * a WRITEDATA operation. If not a WRITEDATA operation, value must + * be set to 0. Should equal transfer_length on success. + * @fcp_error: status of the FCP operation. Must be 0 on success; on failure + * must be a NVME_SC_FC_xxxx value. + */ +struct nvmefc_tgt_fcp_req { + u8 op; + u16 hwqid; + u32 offset; + u32 timeout; + u32 transfer_length; + struct fc_ba_rjt ba_rjt; + struct scatterlist sg[NVME_FC_MAX_SEGMENTS]; + int sg_cnt; + void *rspaddr; + dma_addr_t rspdma; + u16 rsplen; + + void (*done)(struct nvmefc_tgt_fcp_req *); + + void *nvmet_fc_private; /* LLDD is not to access !! */ + + u32 transferred_length; + int fcp_error; +}; + + +/* Target Features (Bit fields) LLDD supports */ +enum { + NVMET_FCTGTFEAT_READDATA_RSP = (1 << 0), + /* Bit 0: supports the NVMET_FCPOP_READDATA_RSP op, which + * sends (the last) Read Data sequence followed by the RSP + * sequence in one LLDD operation. Errors during Data + * sequence transmit must not allow RSP sequence to be sent. + */ + NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED = (1 << 1), + /* Bit 1: When 0, the LLDD will deliver FCP CMD + * on the CPU it should be affinitized to. Thus work will + * be scheduled on the cpu received on. When 1, the LLDD + * may not deliver the CMD on the CPU it should be worked + * on. The transport should pick a cpu to schedule the work + * on. + */ +}; + + +/** + * struct nvmet_fc_target_port - structure used between NVME-FC transport and + * a LLDD to reference a local NVME subsystem port. + * Allocated/created by the nvme_fc_register_targetport() + * transport interface. + * + * Fields with static values for the port. Initialized by the + * port_info struct supplied to the registration call. + * @port_num: NVME-FC transport subsytem port number + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @private: pointer to memory allocated alongside the local port + * structure that is specifically for the LLDD to use. + * The length of the buffer corresponds to the target_priv_sz + * value specified in the nvme_fc_target_template supplied by + * the LLDD. + * + * Fields with dynamic values. Values may change base on link state. LLDD + * may reference fields directly to change them. Initialized by the + * port_info struct supplied to the registration call. + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + * @port_state: Operational state of the port. + */ +struct nvmet_fc_target_port { + /* static/read-only fields */ + u32 port_num; + u64 node_name; + u64 port_name; + + void *private; + + /* dynamic fields */ + u32 port_id; + enum nvme_fc_obj_state port_state; +} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ + + +/** + * struct nvmet_fc_target_template - structure containing static entrypoints + * and operational parameters for an LLDD that supports NVME + * subsystem behavior. Passed by reference in port + * registrations. NVME-FC transport remembers template + * reference and may access it during runtime operation. + * + * Subsystem/Target Transport Entrypoints/Parameters: + * + * @targetport_delete: The LLDD initiates deletion of a targetport via + * nvmet_fc_unregister_targetport(). However, the teardown is + * asynchronous. This routine is called upon the completion of the + * teardown to inform the LLDD that the targetport has been deleted. + * Entrypoint is Mandatory. + * + * @xmt_ls_rsp: Called to transmit the response to a FC-NVME FC-4 LS service. + * The nvmefc_tgt_ls_req structure is the same LLDD-supplied exchange + * structure specified in the nvmet_fc_rcv_ls_req() call made when + * the LS request was received. The structure will fully describe + * the buffers for the response payload and the dma address of the + * payload. The LLDD is to transmit the response (or return a non-zero + * errno status), and upon completion of the transmit, call the + * "done" routine specified in the nvmefc_tgt_ls_req structure + * (argument to done is the ls reqwuest structure itself). + * After calling the done routine, the LLDD shall consider the + * LS handling complete and the nvmefc_tgt_ls_req structure may + * be freed/released. + * Entrypoint is Mandatory. + * + * @fcp_op: Called to perform a data transfer, transmit a response, or + * abort an FCP opertion. The nvmefc_tgt_fcp_req structure is the same + * LLDD-supplied exchange structure specified in the + * nvmet_fc_rcv_fcp_req() call made when the FCP CMD IU was received. + * The op field in the structure shall indicate the operation for + * the LLDD to perform relative to the io. + * NVMET_FCOP_READDATA operation: the LLDD is to send the + * payload data (described by sglist) to the host in 1 or + * more FC sequences (preferrably 1). Note: the fc-nvme layer + * may call the READDATA operation multiple times for longer + * payloads. + * NVMET_FCOP_WRITEDATA operation: the LLDD is to receive the + * payload data (described by sglist) from the host via 1 or + * more FC sequences (preferrably 1). The LLDD is to generate + * the XFER_RDY IU(s) corresponding to the data being requested. + * Note: the FC-NVME layer may call the WRITEDATA operation + * multiple times for longer payloads. + * NVMET_FCOP_READDATA_RSP operation: the LLDD is to send the + * payload data (described by sglist) to the host in 1 or + * more FC sequences (preferrably 1). If an error occurs during + * payload data transmission, the LLDD is to set the + * nvmefc_tgt_fcp_req fcp_error and transferred_length field, then + * consider the operation complete. On error, the LLDD is to not + * transmit the FCP_RSP iu. If all payload data is transferred + * successfully, the LLDD is to update the nvmefc_tgt_fcp_req + * transferred_length field and may subsequently transmit the + * FCP_RSP iu payload (described by rspbuf, rspdma, rsplen). + * The LLDD is to await FCP_CONF reception to confirm the RSP + * reception by the host. The LLDD may retramsit the FCP_RSP iu + * if necessary per FC-NVME. Upon reception of FCP_CONF, or upon + * FCP_CONF failure, the LLDD is to set the nvmefc_tgt_fcp_req + * fcp_error field and consider the operation complete.. + * NVMET_FCOP_RSP: the LLDD is to transmit the FCP_RSP iu payload + * (described by rspbuf, rspdma, rsplen). The LLDD is to await + * FCP_CONF reception to confirm the RSP reception by the host. + * The LLDD may retramsit the FCP_RSP iu if necessary per FC-NVME. + * Upon reception of FCP_CONF, or upon FCP_CONF failure, the + * LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and + * consider the operation complete.. + * NVMET_FCOP_ABORT: the LLDD is to terminate the exchange + * corresponding to the fcp operation. The LLDD shall send + * ABTS and follow FC exchange abort-multi rules, including + * ABTS retries and possible logout. + * Upon completing the indicated operation, the LLDD is to set the + * status fields for the operation (tranferred_length and fcp_error + * status) in the request, then all the "done" routine + * indicated in the fcp request. Upon return from the "done" + * routine for either a NVMET_FCOP_RSP or NVMET_FCOP_ABORT operation + * the fc-nvme layer will not longer reference the fcp request, + * allowing the LLDD to free/release the fcp request. + * Note: when calling the done routine for READDATA or WRITEDATA + * operations, the fc-nvme layer may immediate convert, in the same + * thread and before returning to the LLDD, the fcp operation to + * the next operation for the fcp io and call the LLDDs fcp_op + * call again. If fields in the fcp request are to be accessed post + * the done call, the LLDD should save their values prior to calling + * the done routine, and inspect the save values after the done + * routine. + * Returns 0 on success, - on failure (Ex: -EIO) + * Entrypoint is Mandatory. + * + * @max_hw_queues: indicates the maximum number of hw queues the LLDD + * supports for cpu affinitization. + * Value is Mandatory. Must be at least 1. + * + * @max_sgl_segments: indicates the maximum number of sgl segments supported + * by the LLDD + * Value is Mandatory. Must be at least 1. Recommend at least 256. + * + * @max_dif_sgl_segments: indicates the maximum number of sgl segments + * supported by the LLDD for DIF operations. + * Value is Mandatory. Must be at least 1. Recommend at least 256. + * + * @dma_boundary: indicates the dma address boundary where dma mappings + * will be split across. + * Value is Mandatory. Typical value is 0xFFFFFFFF to split across + * 4Gig address boundarys + * + * @target_features: The LLDD sets bits in this field to correspond to + * optional features that are supported by the LLDD. + * Refer to the NVMET_FCTGTFEAT_xxx values. + * Value is Mandatory. Allowed to be zero. + * + * @target_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like fc nvme layer to allocate on the LLDD's + * behalf whenever a targetport is allocated. The additional memory + * area solely for the of the LLDD and its location is specified by + * the targetport->private pointer. + * Value is Mandatory. Allowed to be zero. + */ +struct nvmet_fc_target_template { + void (*targetport_delete)(struct nvmet_fc_target_port *tgtport); + int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_ls_req *tls_req); + int (*fcp_op)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *); + + u32 max_hw_queues; + u16 max_sgl_segments; + u16 max_dif_sgl_segments; + u64 dma_boundary; + + u32 target_features; + + u32 target_priv_sz; +}; + + +int nvmet_fc_register_targetport(struct nvmet_fc_port_info *portinfo, + struct nvmet_fc_target_template *template, + struct device *dev, + struct nvmet_fc_target_port **tgtport_p); + +int nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *tgtport); + +int nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_ls_req *lsreq, + void *lsreqbuf, u32 lsreqbuf_len); + +int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq, + void *cmdiubuf, u32 cmdiubuf_len); + +#endif /* _NVME_FC_DRIVER_H */ -- cgit From 7c4788950ba5922fde976d80b72baf46f14dee8d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Nov 2016 10:57:15 +0100 Subject: x86/uaccess, sched/preempt: Verify access_ok() context I recently encountered wreckage because access_ok() was used where it should not be, add an explicit WARN when access_ok() is used wrongly. Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/preempt.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 75e4e30677f1..7eeceac52dea 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -65,19 +65,24 @@ /* * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? + * + * in_irq() - We're in (hard) IRQ context + * in_softirq() - We have BH disabled, or are processing softirqs + * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled + * in_serving_softirq() - We're in softirq context + * in_nmi() - We're in NMI context + * in_task() - We're in task context + * + * Note: due to the BH disabled confusion: in_softirq(),in_interrupt() really + * should not be used in new code. */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) +#define in_nmi() (preempt_count() & NMI_MASK) +#define in_task() (!(preempt_count() & \ + (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) /* * The preempt_count offset after preempt_disable(); -- cgit From f4ec57b632fe15ed7a355099cb96ed4b647416de Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 24 Nov 2016 12:46:26 +0100 Subject: locking/ww_mutex: Use relaxed atomics The stamp is a sequence number, we don't care about memory ordering. Signed-off-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/ww_mutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 2bb5deb0012e..7b0066814fa0 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -120,7 +120,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, struct ww_class *ww_class) { ctx->task = current; - ctx->stamp = atomic_long_inc_return(&ww_class->stamp); + ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; -- cgit From 8d7cc7adcec55bfeb28cc2dc58b996c95f180337 Mon Sep 17 00:00:00 2001 From: Martyn Welch Date: Sat, 3 Dec 2016 23:45:01 +0000 Subject: VME: Remove shutdown entry from vme_driver The vme_driver structure currently has a "shutdown" entry. This entry is never used, it lacks the correct parameter (it should be providing a pointer to the relevant vme_dev struct to even *look* usable), the VME subsystem currently doesn't provide support for shutdown functions and no in-tree drivers use it (hardly surprising, given it'd never be called). Remove the entry from vme_driver to avoid confusion. Signed-off-by: Martyn Welch Signed-off-by: Greg Kroah-Hartman --- include/linux/vme.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vme.h b/include/linux/vme.h index ea6095deba20..8c589176c2f8 100644 --- a/include/linux/vme.h +++ b/include/linux/vme.h @@ -113,7 +113,6 @@ struct vme_driver { int (*match)(struct vme_dev *); int (*probe)(struct vme_dev *); int (*remove)(struct vme_dev *); - void (*shutdown)(void); struct device_driver driver; struct list_head devices; }; -- cgit From 076802d0061520bc646ee121fe0f34fce6c55a93 Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Sat, 3 Dec 2016 00:15:25 +0200 Subject: mei: bus: enable non-blocking RX Enable non-blocking receive for drivers on mei bus, this allows checking for data availability by mei client drivers. This is most effective for fixed address clients, that lacks flow control. This function adds new API function mei_cldev_recv_nonblock(), it retuns -EGAIN if function will block. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 017f5232b3de..a0d274fe08f1 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -75,7 +75,7 @@ void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); /** * module_mei_cl_driver - Helper macro for registering mei cl driver * - * @__mei_cldrv mei_cl_driver structure + * @__mei_cldrv: mei_cl_driver structure * * Helper macro for mei cl drivers which do not do anything special in module * init/exit, for eliminating a boilerplate code. @@ -86,7 +86,9 @@ void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); mei_cldev_driver_unregister) ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length); -ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); +ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); +ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf, + size_t length); int mei_cldev_register_rx_cb(struct mei_cl_device *cldev, mei_cldev_cb_t rx_cb); int mei_cldev_register_notif_cb(struct mei_cl_device *cldev, -- cgit From f45be72c8ec0b85263d1fe1e6c681d8c87e198e6 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Sat, 3 Dec 2016 12:34:29 -0800 Subject: hyperv: Fix spelling of HV_UNKOWN Changed it to HV_UNKNOWN Signed-off-by: Haiyang Zhang Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2a52d9abb305..35053f99522b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -696,7 +696,7 @@ enum vmbus_device_type { HV_FCOPY, HV_BACKUP, HV_DM, - HV_UNKOWN, + HV_UNKNOWN, }; struct vmbus_device { -- cgit From fc76936d3ea5720a6e0948a08381b803a68deb28 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 3 Dec 2016 12:34:39 -0800 Subject: vmbus: add support for dynamic device id's This patch adds sysfs interface to dynamically bind new UUID values to existing VMBus device. This is useful for generic UIO driver to act similar to uio_pci_generic. Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 35053f99522b..42fe43fb0c80 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1119,6 +1119,12 @@ struct hv_driver { struct device_driver driver; + /* dynamic device GUID's */ + struct { + spinlock_t lock; + struct list_head list; + } dynids; + int (*probe)(struct hv_device *, const struct hv_vmbus_device_id *); int (*remove)(struct hv_device *); void (*shutdown)(struct hv_device *); -- cgit From 18b709beb503bfc9a96a2e4b93d3cae4f5b17df0 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 6 Dec 2016 14:20:11 +0000 Subject: ACPI/IORT: Make dma masks set-up IORT specific The introduction of acpi_dma_configure() allows to configure DMA and related IOMMU for any device that is DMA capable. To achieve that goal it ensures DMA masks are set-up to sane default values before proceeding with IOMMU and DMA ops configuration. On x86/ia64 systems, through acpi_bind_one(), acpi_dma_configure() is called for every device that has an ACPI companion, in that every device is considered DMA capable on x86/ia64 systems (ie acpi_get_dma_attr() API), which has the side effect of initializing dma masks also for pseudo-devices (eg CPUs and memory nodes) and potentially for devices whose dma masks were not set-up before the acpi_dma_configure() API was introduced, which may have noxious side effects. Therefore, in preparation for IORT firmware specific DMA masks set-up, wrap the default DMA masks set-up in acpi_dma_configure() inside an IORT specific wrapper that reverts to a NOP on x86/ia64 systems, restoring the default expected behaviour on x86/ia64 systems and keeping DMA default masks set-up on IORT based (ie ARM) arch configurations. Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Acked-by: Rafael J. Wysocki Reviewed-by: Hanjun Guo Tested-by: Hanjun Guo Cc: Will Deacon Cc: Hanjun Guo Cc: Bjorn Helgaas Cc: Robin Murphy Cc: Tomasz Nowicki Cc: Joerg Roedel Cc: "Rafael J. Wysocki" Cc: Sricharan R Signed-off-by: Joerg Roedel --- include/linux/acpi_iort.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index dcb2b601e152..77e08099e554 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -35,6 +35,7 @@ bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); /* IOMMU interface */ +void iort_set_dma_mask(struct device *dev); const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } @@ -45,6 +46,7 @@ static inline struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id) { return NULL; } /* IOMMU interface */ +static inline void iort_set_dma_mask(struct device *dev) { } static inline const struct iommu_ops *iort_iommu_configure(struct device *dev) { return NULL; } -- cgit From 13983eb89d5afaa65acd4479fad151cbd4de5509 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Fri, 9 Sep 2016 21:24:03 +0200 Subject: PCI/ACPI: Extend pci_mcfg_lookup() to return ECAM config accessors pci_mcfg_lookup() is the external interface to the generic MCFG code. Previously it merely looked up the ECAM base address for a given domain and bus range. We want a way to add MCFG quirks, some of which may require special config accessors and adjustments to the ECAM address range. Extend pci_mcfg_lookup() so it can return a pointer to a pci_ecam_ops structure and a struct resource for the ECAM address space. For now, it always returns &pci_generic_ecam_ops (the standard accessor) and the resource described by the MCFG. No functional changes intended. [bhelgaas: changelog] Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas --- include/linux/pci-acpi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 7d63a66e8ed4..7a4e83a8c89c 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -24,7 +24,9 @@ static inline acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev) } extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle); -extern phys_addr_t pci_mcfg_lookup(u16 domain, struct resource *bus_res); +struct pci_ecam_ops; +extern int pci_mcfg_lookup(struct acpi_pci_root *root, struct resource *cfgres, + struct pci_ecam_ops **ecam_ops); static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { -- cgit From 2ca5b8ddc6f70d77a51851ba5e5cd0d39c27dd88 Mon Sep 17 00:00:00 2001 From: Christopher Covington Date: Wed, 2 Nov 2016 11:11:27 -0500 Subject: PCI: Add MCFG quirks for Qualcomm QDF2432 host controller The Qualcomm Technologies QDF2432 SoC does not support accesses smaller than 32 bits to the PCI configuration space. Register the appropriate quirk. [bhelgaas: add QCOM_ECAM32 macro, ifdef for ACPI and PCI_QUIRKS] Signed-off-by: Christopher Covington Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 7adad206b1f4..739d2330fd9e 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -59,6 +59,10 @@ void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn, /* default ECAM ops */ extern struct pci_ecam_ops pci_generic_ecam_ops; +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) +extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ +#endif + #ifdef CONFIG_PCI_HOST_GENERIC /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, -- cgit From 5f00f1a0178cf52928366a5e1f376a65f1f3f389 Mon Sep 17 00:00:00 2001 From: Dongdong Liu Date: Thu, 1 Dec 2016 00:45:35 -0600 Subject: PCI: Add MCFG quirks for HiSilicon Hip05/06/07 host controllers The PCIe controller in Hip05/Hip06/Hip07 SoCs is not completely ECAM-compliant. It is non-ECAM only for the RC bus config space; for any other bus underneath the root bus it does support ECAM access. Add specific quirks for PCI config space accessors. This involves: 1. New initialization call hisi_pcie_init() to obtain RC base addresses from PNP0C02 at the root of the ACPI namespace (under \_SB). 2. New entry in common quirk array. [bhelgaas: move to pcie-hisi.c and change Makefile/ifdefs so quirk doesn't depend on CONFIG_PCI_HISI] Signed-off-by: Dongdong Liu Signed-off-by: Gabriele Paoloni Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 739d2330fd9e..bdacbc883a22 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -61,6 +61,7 @@ extern struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ +extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ #endif #ifdef CONFIG_PCI_HOST_GENERIC -- cgit From 44f22bd91e88f9a1203a6e564a237e593f5f2f74 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Thu, 1 Dec 2016 00:07:56 -0600 Subject: PCI: Add MCFG quirks for Cavium ThunderX pass2.x host controller ThunderX PCIe controller to off-chip devices (so-called PEM) is not fully compliant with ECAM standard. It uses non-standard configuration space accessors (see thunder_pem_ecam_ops) and custom configuration space granulation (see bus_shift = 24). In order to access configuration space and probe PEM as ACPI-based PCI host controller we need to add MCFG quirk infrastructure. This involves: 1. A new thunder_pem_acpi_init() init function to locate PEM-specific register ranges using ACPI. 2. Export PEM thunder_pem_ecam_ops structure so it is visible to MCFG quirk code. 3. New quirk entries for each PEM segment. Each contains platform IDs, mentioned thunder_pem_ecam_ops and CFG resources. Quirk is considered for ThunderX silicon pass2.x only which is identified via MCFG revision 1. ThunderX pass 2.x requires the following accessors: NUMA Node 0 PCI segments 0- 3: pci_generic_ecam_ops (ECAM-compliant) NUMA Node 0 PCI segments 4- 9: thunder_pem_ecam_ops (MCFG quirk) NUMA Node 1 PCI segments 10-13: pci_generic_ecam_ops (ECAM-compliant) NUMA Node 1 PCI segments 14-19: thunder_pem_ecam_ops (MCFG quirk) [bhelgaas: adapt to use acpi_get_rc_resources(), update Makefile/ifdefs so quirk doesn't depend on CONFIG_PCI_HOST_THUNDER_PEM] Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index bdacbc883a22..e88d7db74200 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -62,6 +62,7 @@ extern struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ +extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 2.x */ #endif #ifdef CONFIG_PCI_HOST_GENERIC -- cgit From 648d93fc77da4f655cf13108417f33c91d745e2c Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Wed, 30 Nov 2016 23:16:34 -0600 Subject: PCI: Add MCFG quirks for Cavium ThunderX pass1.x host controller ThunderX pass1.x requires to emulate the EA headers for on-chip devices hence it has to use custom pci_thunder_ecam_ops for accessing PCI config space (pci-thunder-ecam.c). Add new entries to MCFG quirk array where it can be applied while probing ACPI based PCI host controller. ThunderX pass1.x is using the same way for accessing off-chip devices (so-called PEM) as silicon pass-2.x so we need to add PEM quirk entries too. Quirk is considered for ThunderX silicon pass1.x only which is identified via MCFG revision 2. ThunderX pass 1.x requires the following accessors: NUMA node 0 PCI segments 0- 3: pci_thunder_ecam_ops (MCFG quirk) NUMA node 0 PCI segments 4- 9: thunder_pem_ecam_ops (MCFG quirk) NUMA node 1 PCI segments 10-13: pci_thunder_ecam_ops (MCFG quirk) NUMA node 1 PCI segments 14-19: thunder_pem_ecam_ops (MCFG quirk) [bhelgaas: change Makefile/ifdefs so quirk doesn't depend on CONFIG_PCI_HOST_THUNDER_ECAM] Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index e88d7db74200..00eb8eb774e2 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -62,7 +62,8 @@ extern struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ -extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 2.x */ +extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ +extern struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ #endif #ifdef CONFIG_PCI_HOST_GENERIC -- cgit From c5d4603961009c39de94725213d8b5420f110f9e Mon Sep 17 00:00:00 2001 From: Duc Dang Date: Thu, 1 Dec 2016 18:27:07 -0800 Subject: PCI: Add MCFG quirks for X-Gene host controller PCIe controllers in X-Gene SoCs are not ECAM compliant: software needs to configure additional controller's register to address device at bus:dev:function. Add a quirk to discover controller MMIO register space and configure controller registers to select and address the target secondary device. The quirk will only be applied for X-Gene PCIe MCFG table with OEM revison 1, 2, 3 or 4 (PCIe controller v1 and v2 on X-Gene SoCs). Tested-by: Jon Masters Signed-off-by: Duc Dang Signed-off-by: Bjorn Helgaas --- include/linux/pci-ecam.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 00eb8eb774e2..f0d2b9451270 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -64,6 +64,8 @@ extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ extern struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ +extern struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ +extern struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ #endif #ifdef CONFIG_PCI_HOST_GENERIC -- cgit From 0aa8c57a04907a5d02068ff9f917629be97ea78d Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Tue, 15 Nov 2016 17:48:44 -0500 Subject: netfilter: introduce accessor functions for hook entries This allows easier future refactoring. Signed-off-by: Aaron Conole Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 69230140215b..575aa198097e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -79,6 +79,33 @@ struct nf_hook_entry { const struct nf_hook_ops *orig_ops; }; +static inline void +nf_hook_entry_init(struct nf_hook_entry *entry, const struct nf_hook_ops *ops) +{ + entry->next = NULL; + entry->ops = *ops; + entry->orig_ops = ops; +} + +static inline int +nf_hook_entry_priority(const struct nf_hook_entry *entry) +{ + return entry->ops.priority; +} + +static inline int +nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, + struct nf_hook_state *state) +{ + return entry->ops.hook(entry->ops.priv, skb, state); +} + +static inline const struct nf_hook_ops * +nf_hook_entry_ops(const struct nf_hook_entry *entry) +{ + return entry->orig_ops; +} + static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, -- cgit From d415b9eb76fc55c03ef5451691170aa5771dcea3 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Tue, 15 Nov 2016 17:48:45 -0500 Subject: netfilter: decouple nf_hook_entry and nf_hook_ops During nfhook traversal we only need a very small subset of nf_hook_ops members. We need: - next element - hook function to call - hook function priv argument Bridge netfilter also needs 'thresh'; can be obtained via ->orig_ops. nf_hook_entry struct is now 32 bytes on x86_64. A followup patch will turn the run-time list into an array that only stores hook functions plus their priv arguments, eliminating the ->next element. Suggested-by: Florian Westphal Signed-off-by: Aaron Conole Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 575aa198097e..a4b97be30b28 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -75,7 +75,8 @@ struct nf_hook_ops { struct nf_hook_entry { struct nf_hook_entry __rcu *next; - struct nf_hook_ops ops; + nf_hookfn *hook; + void *priv; const struct nf_hook_ops *orig_ops; }; @@ -83,21 +84,22 @@ static inline void nf_hook_entry_init(struct nf_hook_entry *entry, const struct nf_hook_ops *ops) { entry->next = NULL; - entry->ops = *ops; + entry->hook = ops->hook; + entry->priv = ops->priv; entry->orig_ops = ops; } static inline int nf_hook_entry_priority(const struct nf_hook_entry *entry) { - return entry->ops.priority; + return entry->orig_ops->priority; } static inline int nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, struct nf_hook_state *state) { - return entry->ops.hook(entry->ops.priv, skb, state); + return entry->hook(entry->priv, skb, state); } static inline const struct nf_hook_ops * -- cgit From 4d31eef5176df06f218201bc9c0ce40babb41660 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Nov 2016 14:44:17 +0100 Subject: netfilter: x_tables: pass xt_counters struct instead of packet counter On SMP we overload the packet counter (unsigned long) to contain percpu offset. Hide this from callers and pass xt_counters address instead. Preparation patch to allocate the percpu counters in page-sized batch chunks. Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index cd4eaf8df445..6e61edeb68e3 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -430,11 +430,7 @@ static inline unsigned long xt_percpu_counter_alloc(void) return 0; } -static inline void xt_percpu_counter_free(u64 pcnt) -{ - if (nr_cpu_ids > 1) - free_percpu((void __percpu *) (unsigned long) pcnt); -} +void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) -- cgit From f28e15bacedd444608e25421c72eb2cf4527c9ca Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Nov 2016 14:44:18 +0100 Subject: netfilter: x_tables: pass xt_counters struct to counter allocator Keeps some noise away from a followup patch. Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6e61edeb68e3..05a94bd32c55 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -404,32 +404,7 @@ static inline unsigned long ifname_compare_aligned(const char *_a, } -/* On SMP, ip(6)t_entry->counters.pcnt holds address of the - * real (percpu) counter. On !SMP, its just the packet count, - * so nothing needs to be done there. - * - * xt_percpu_counter_alloc returns the address of the percpu - * counter, or 0 on !SMP. We force an alignment of 16 bytes - * so that bytes/packets share a common cache line. - * - * Hence caller must use IS_ERR_VALUE to check for error, this - * allows us to return 0 for single core systems without forcing - * callers to deal with SMP vs. NONSMP issues. - */ -static inline unsigned long xt_percpu_counter_alloc(void) -{ - if (nr_cpu_ids > 1) { - void __percpu *res = __alloc_percpu(sizeof(struct xt_counters), - sizeof(struct xt_counters)); - - if (res == NULL) - return -ENOMEM; - - return (__force unsigned long) res; - } - - return 0; -} +bool xt_percpu_counter_alloc(struct xt_counters *counters); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * -- cgit From ae0ac0ed6fcf5af3be0f63eb935f483f44a402d2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Nov 2016 14:44:19 +0100 Subject: netfilter: x_tables: pack percpu counter allocations instead of allocating each xt_counter individually, allocate 4k chunks and then use these for counter allocation requests. This should speed up rule evaluation by increasing data locality, also speeds up ruleset loading because we reduce calls to the percpu allocator. As Eric points out we can't use PAGE_SIZE, page_allocator would fail on arches with 64k page size. Suggested-by: Eric Dumazet Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 05a94bd32c55..5117e4d2ddfa 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -403,8 +403,13 @@ static inline unsigned long ifname_compare_aligned(const char *_a, return ret; } +struct xt_percpu_counter_alloc_state { + unsigned int off; + const char __percpu *mem; +}; -bool xt_percpu_counter_alloc(struct xt_counters *counters); +bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, + struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * -- cgit From df122f58b834b24c27d7e2ac02a4910d3e56f6ae Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 28 Nov 2016 11:40:05 +0100 Subject: netfilter: ingress: translate 0 nf_hook_slow retval to -1 The caller assumes that < 0 means that skb was stolen (or free'd). All other return values continue skb processing. nf_hook_slow returns 3 different return value types: A) a (negative) errno value: the skb was dropped (NF_DROP, e.g. by iptables '-j DROP' rule). B) 0. The skb was stolen by the hook or queued to userspace. C) 1. all hooks returned NF_ACCEPT so the caller should invoke the okfn so packet processing can continue. nft ingress facility currently doesn't have the 'okfn' that the NF_HOOK() macros use; there is no nfqueue support either. So 1 means that nf_hook_ingress() caller should go on processing the skb. In order to allow use of NF_STOLEN from ingress we need to translate this to an errno number, else we'd crash because we continue with already-free'd (or about to be free-d) skb. The errno value isn't checked, its just important that its less than 0, so return -1. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ingress.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 2dc3b49b804a..59476061de86 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -19,6 +19,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entry *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; + int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. @@ -29,7 +30,11 @@ static inline int nf_hook_ingress(struct sk_buff *skb) nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); - return nf_hook_slow(skb, &state, e); + ret = nf_hook_slow(skb, &state, e); + if (ret == 0) + return -1; + + return ret; } static inline void nf_hook_ingress_init(struct net_device *dev) -- cgit From 562b488443f658151abc9732e1a9762e27c694a0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 25 Nov 2016 10:53:39 +0100 Subject: gpio: pl061: move platform data into driver No boardfile defines any PL061 platform data anymore: the Integrator IM/PD-1 includes the file but is not making use of the struct. Let's delete the include and all references, then move the platform data into the driver for later consolidation into the driver state container. The only resource defined by the IM/PD-1 is the IRQ which is passed through the AMBA PrimeCell bus abstraction struct amba_device. Cc: arm@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: Russell King Signed-off-by: Linus Walleij --- include/linux/amba/pl061.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/amba/pl061.h (limited to 'include/linux') diff --git a/include/linux/amba/pl061.h b/include/linux/amba/pl061.h deleted file mode 100644 index fb83c0453489..000000000000 --- a/include/linux/amba/pl061.h +++ /dev/null @@ -1,16 +0,0 @@ -#include - -/* platform data for the PL061 GPIO driver */ - -struct pl061_platform_data { - /* number of the first GPIO */ - unsigned gpio_base; - - /* number of the first IRQ. - * If the IRQ functionality in not desired this must be set to 0. - */ - unsigned irq_base; - - u8 directions; /* startup directions, 1: out, 0: in */ - u8 values; /* startup values */ -}; -- cgit From 37d6a0a6f4700ad3ae7bbf8db38b4557e97b3fe4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Nov 2016 11:57:09 +0100 Subject: PCI: Add pci_register_host_bridge() interface Make the existing pci_host_bridge structure a proper device that is usable by PCI host drivers in a more standard way. In addition to the existing pci_scan_bus(), pci_scan_root_bus(), pci_scan_root_bus_msi(), and pci_create_root_bus() interfaces, this unfortunately means having to add yet another interface doing basically the same thing, and add some extra code in the initial step. However, this time it's more likely to be extensible enough that we won't have to do another one again in the future, and we should be able to reduce code much more as a result. The main idea is to pull the allocation of 'struct pci_host_bridge' out of the registration, and let individual host drivers and architecture code fill the members before calling the registration function. There are a number of things we can do based on this: * Use a single memory allocation for the driver-specific structure and the generic PCI host bridge * consolidate the contents of driver-specific structures by moving them into pci_host_bridge * Add a consistent interface for removing a PCI host bridge again when unloading a host driver module * Replace the architecture specific __weak pcibios_*() functions with callbacks in a pci_host_bridge device * Move common boilerplate code from host drivers into the generic function, based on contents of the structure * Extend pci_host_bridge with additional members when needed without having to add arguments to pci_scan_*(). * Move members of struct pci_bus into pci_host_bridge to avoid having lots of identical copies. Signed-off-by: Arnd Bergmann Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e49f70dbd9b..f79634612fbf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -420,9 +420,13 @@ static inline int pci_channel_offline(struct pci_dev *pdev) struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* root bus */ + struct pci_ops *ops; + void *sysdata; + int busnr; struct list_head windows; /* resource_entry */ void (*release_fn)(struct pci_host_bridge *); void *release_data; + struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* for entire hierarchy */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, -- cgit From 5909406598d9fab58be860b72dff9409bff11653 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 25 Nov 2016 11:57:10 +0100 Subject: PCI: Allow driver-specific data in host bridge Provide a way to allocate driver-specific data along with a PCI host bridge structure. The bridge's ->private field points to this data. Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index f79634612fbf..beacb17e81fb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -434,10 +434,21 @@ struct pci_host_bridge { resource_size_t start, resource_size_t size, resource_size_t align); + unsigned long private[0] ____cacheline_aligned; }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) +static inline void *pci_host_bridge_priv(struct pci_host_bridge *bridge) +{ + return (void *)bridge->private; +} + +static inline struct pci_host_bridge *pci_host_bridge_from_priv(void *priv) +{ + return container_of(priv, struct pci_host_bridge, private); +} + struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); void pci_set_host_bridge_release(struct pci_host_bridge *bridge, -- cgit From a52d1443bba1db98907521414727eee22ae8c380 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 25 Nov 2016 11:57:11 +0100 Subject: PCI: Export host bridge registration interface Allow PCI host bridge drivers to use the new host bridge interfaces to register their host bridge. Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index beacb17e81fb..aa5e8af16cfc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -449,6 +449,8 @@ static inline struct pci_host_bridge *pci_host_bridge_from_priv(void *priv) return container_of(priv, struct pci_host_bridge, private); } +struct pci_host_bridge *pci_alloc_host_bridge(size_t priv); +int pci_register_host_bridge(struct pci_host_bridge *bridge); struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); void pci_set_host_bridge_release(struct pci_host_bridge *bridge, -- cgit From 777c6e0daebb3fcefbbd6f620410a946b07ef6d0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 7 Dec 2016 14:54:38 +0100 Subject: hotplug: Make register and unregister notifier API symmetric Yu Zhao has noticed that __unregister_cpu_notifier only unregisters its notifiers when HOTPLUG_CPU=y while the registration might succeed even when HOTPLUG_CPU=n if MODULE is enabled. This means that e.g. zswap might keep a stale notifier on the list on the manual clean up during the pool tear down and thus corrupt the list. Resulting in the following [ 144.964346] BUG: unable to handle kernel paging request at ffff880658a2be78 [ 144.971337] IP: [] raw_notifier_chain_register+0x1b/0x40 [ 145.122628] Call Trace: [ 145.125086] [] __register_cpu_notifier+0x18/0x20 [ 145.131350] [] zswap_pool_create+0x273/0x400 [ 145.137268] [] __zswap_param_set+0x1fc/0x300 [ 145.143188] [] ? trace_hardirqs_on+0xd/0x10 [ 145.149018] [] ? kernel_param_lock+0x28/0x30 [ 145.154940] [] ? __might_fault+0x4f/0xa0 [ 145.160511] [] zswap_compressor_param_set+0x17/0x20 [ 145.167035] [] param_attr_store+0x5c/0xb0 [ 145.172694] [] module_attr_store+0x1d/0x30 [ 145.178443] [] sysfs_kf_write+0x4f/0x70 [ 145.183925] [] kernfs_fop_write+0x149/0x180 [ 145.189761] [] __vfs_write+0x18/0x40 [ 145.194982] [] vfs_write+0xb2/0x1a0 [ 145.200122] [] SyS_write+0x52/0xa0 [ 145.205177] [] entry_SYSCALL_64_fastpath+0x12/0x17 This can be even triggered manually by changing /sys/module/zswap/parameters/compressor multiple times. Fix this issue by making unregister APIs symmetric to the register so there are no surprises. Fixes: 47e627bc8c9a ("[PATCH] hotplug: Allow modules to use the cpu hotplug notifiers even if !CONFIG_HOTPLUG_CPU") Reported-and-tested-by: Yu Zhao Signed-off-by: Michal Hocko Cc: linux-mm@kvack.org Cc: Andrew Morton Cc: Dan Streetman Link: http://lkml.kernel.org/r/20161207135438.4310-1-mhocko@kernel.org Signed-off-by: Thomas Gleixner --- include/linux/cpu.h | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b886dc17f2f3..e571128ad99a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -93,22 +93,16 @@ extern bool cpuhp_tasks_frozen; { .notifier_call = fn, .priority = pri }; \ __register_cpu_notifier(&fn##_nb); \ } -#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */ -#define cpu_notifier(fn, pri) do { (void)(fn); } while (0) -#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) -#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */ -#ifdef CONFIG_HOTPLUG_CPU extern int register_cpu_notifier(struct notifier_block *nb); extern int __register_cpu_notifier(struct notifier_block *nb); extern void unregister_cpu_notifier(struct notifier_block *nb); extern void __unregister_cpu_notifier(struct notifier_block *nb); -#else -#ifndef MODULE -extern int register_cpu_notifier(struct notifier_block *nb); -extern int __register_cpu_notifier(struct notifier_block *nb); -#else +#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */ +#define cpu_notifier(fn, pri) do { (void)(fn); } while (0) +#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) + static inline int register_cpu_notifier(struct notifier_block *nb) { return 0; @@ -118,7 +112,6 @@ static inline int __register_cpu_notifier(struct notifier_block *nb) { return 0; } -#endif static inline void unregister_cpu_notifier(struct notifier_block *nb) { -- cgit From 1da5c46fa965ff90f5ffc080b6ab3fae5e227bc3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 Nov 2016 18:50:57 +0100 Subject: kthread: Make struct kthread kmalloc'ed commit 23196f2e5f5d "kthread: Pin the stack via try_get_task_stack() / put_task_stack() in to_live_kthread() function" is a workaround for the fragile design of struct kthread being allocated on the task stack. struct kthread in its current form should be removed, but this needs cleanups outside of kthread.c. As a first step move struct kthread away from the task stack by making it kmalloc'ed. This allows to access kthread.exited without the magic of trying to pin task stack and the try logic in to_live_kthread(). Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Chunming Zhou Cc: Roman Pen Cc: Petr Mladek Cc: Andy Lutomirski Cc: Tejun Heo Cc: Andy Lutomirski Cc: Alex Deucher Cc: Andrew Morton Link: http://lkml.kernel.org/r/20161129175057.GA5330@redhat.com Signed-off-by: Thomas Gleixner --- include/linux/kthread.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index a6e82a69c363..c1c3e63d52c1 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -48,6 +48,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), __k; \ }) +void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); int kthread_stop(struct task_struct *k); -- cgit From 89caaa2d80b7bf9bd8632cd3137254f8c685e5db Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Wed, 7 Dec 2016 15:20:07 +0100 Subject: net: stmmac: add support for independent DMA pbl for tx/rx GMAC and newer supports independent programmable burst lengths for DMA tx/rx. Add new optional devicetree properties representing this. To be backwards compatible, snps,pbl will still be valid, but snps,txpbl/snps,rxpbl will override the value in snps,pbl if set. If the IP is synthesized to use the AXI interface, there is a register and a matching DT property inside the optional stmmac-axi-config DT node for controlling burst lengths, named snps,blen. However, using this register, it is not possible to control tx and rx independently. Also, this register is not available if the IP was synthesized with, e.g., the AHB interface. Signed-off-by: Niklas Cassel Acked-by: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3537fb33cc90..e6d7a5940819 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -88,6 +88,8 @@ struct stmmac_mdio_bus_data { struct stmmac_dma_cfg { int pbl; + int txpbl; + int rxpbl; int fixed_burst; int mixed_burst; bool aal; -- cgit From 4022d039a315951e59d95d22e79198d861ce4490 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Wed, 7 Dec 2016 15:20:08 +0100 Subject: net: smmac: allow configuring lower pbl values The driver currently always sets the PBLx8/PBLx4 bit, which means that the pbl values configured via the pbl/txpbl/rxpbl DT properties are always multiplied by 8/4 in the hardware. In order to allow the DT to configure lower pbl values, while at the same time not changing behavior of any existing device trees using the pbl/txpbl/rxpbl settings, add a property to disable the multiplication of the pbl by 8/4 in the hardware. Suggested-by: Rabin Vincent Signed-off-by: Niklas Cassel Acked-by: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index e6d7a5940819..266dab9ad782 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -90,6 +90,7 @@ struct stmmac_dma_cfg { int pbl; int txpbl; int rxpbl; + bool pblx8; int fixed_burst; int mixed_burst; bool aal; -- cgit From 13bfff25c081f4e060af761c4082b5a96f756810 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Dec 2016 08:29:10 -0800 Subject: net: rfs: add a jump label RFS is not commonly used, so add a jump label to avoid some conditionals in fast path. Signed-off-by: Eric Dumazet Cc: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1ff5ea6e1221..994f7423a74b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -192,6 +192,7 @@ struct net_device_stats { #ifdef CONFIG_RPS #include extern struct static_key rps_needed; +extern struct static_key rfs_needed; #endif struct neighbour; -- cgit From c8c8b127091b758f5768f906bcdeeb88bc9951ca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Dec 2016 09:19:33 -0800 Subject: udp: under rx pressure, try to condense skbs Under UDP flood, many softirq producers try to add packets to UDP receive queue, and one user thread is burning one cpu trying to dequeue packets as fast as possible. Two parts of the per packet cost are : - copying payload from kernel space to user space, - freeing memory pieces associated with skb. If socket is under pressure, softirq handler(s) can try to pull in skb->head the payload of the packet if it fits. Meaning the softirq handler(s) can free/reuse the page fragment immediately, instead of letting udp_recvmsg() do this hundreds of usec later, possibly from another node. Additional gains : - We reduce skb->truesize and thus can store more packets per SO_RCVBUF - We avoid cache line misses at copyout() time and consume_skb() time, and avoid one put_page() with potential alien freeing on NUMA hosts. This comes at the cost of a copy, bounded to available tail room, which is usually small. (We might have to fix GRO_MAX_HEAD which looks bigger than necessary) This patch gave me about 5 % increase in throughput in my tests. skb_condense() helper could probably used in other contexts. Signed-off-by: Eric Dumazet Cc: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9c535fbccf2c..0cd92b0f2af5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1966,6 +1966,8 @@ static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } +void skb_condense(struct sk_buff *skb); + /** * skb_headroom - bytes at buffer head * @skb: buffer to check -- cgit From d2a4dd37f6b41fbcad76efbf63124eb3126c66fe Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Dec 2016 10:57:59 -0800 Subject: bpf: fix state equivalence Commmits 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") and 484611357c19 ("bpf: allow access into map value arrays") by themselves are correct, but in combination they make state equivalence ignore 'id' field of the register state which can lead to accepting invalid program. Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") Fixes: 484611357c19 ("bpf: allow access into map value arrays") Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7453c1281531..a13b031dc6b8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,13 +18,6 @@ struct bpf_reg_state { enum bpf_reg_type type; - /* - * Used to determine if any memory access using this register will - * result in a bad access. - */ - s64 min_value; - u64 max_value; - u32 id; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; @@ -40,6 +33,13 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; }; + u32 id; + /* Used to determine if any memory access using this register will + * result in a bad access. These two fields must be last. + * See states_equal() + */ + s64 min_value; + u64 max_value; }; enum bpf_stack_slot_type { -- cgit From f38e7a32ee4fc9c8aeeac59e6e0462cd281586e3 Mon Sep 17 00:00:00 2001 From: "Woojung.Huh@microchip.com" Date: Wed, 7 Dec 2016 20:26:07 +0000 Subject: phy: add phy fixup unregister functions >From : Woojung Huh Add functions to unregister phy fixup for modules. int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask) Unregister phy fixup from phy_fixup_list per bus_id, phy_uid & phy_uid_mask int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask) Unregister phy fixup from phy_fixup_list. Use it for fixup registered by phy_register_fixup_for_uid() int phy_unregister_fixup_for_id(const char *bus_id) Unregister phy fixup from phy_fixup_list. Use it for fixup registered by phy_register_fixup_for_id() Signed-off-by: Woojung Huh Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index feb8a98e8dd3..f7d95f644eed 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -860,6 +860,10 @@ int phy_register_fixup_for_id(const char *bus_id, int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); +int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); +int phy_unregister_fixup_for_id(const char *bus_id); +int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); + int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); -- cgit From 17bedab2723145d17b14084430743549e6943d03 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 7 Dec 2016 15:53:11 -0800 Subject: bpf: xdp: Allow head adjustment in XDP prog This patch allows XDP prog to extend/remove the packet data at the head (like adding or removing header). It is done by adding a new XDP helper bpf_xdp_adjust_head(). It also renames bpf_helper_changes_skb_data() to bpf_helper_changes_pkt_data() to better reflect that XDP prog does not work on skb. This patch adds one "xdp_adjust_head" bit to bpf_prog for the XDP-capable driver to check if the XDP prog requires bpf_xdp_adjust_head() support. The driver can then decide to error out during XDP_SETUP_PROG. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/filter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index f078d2b1cff6..6a1658308612 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -406,7 +406,8 @@ struct bpf_prog { u16 jited:1, /* Is our filter JIT'ed? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1; /* Do we need dst entry? */ + dst_needed:1, /* Do we need dst entry? */ + xdp_adjust_head:1; /* Adjusting pkt head? */ kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ @@ -440,6 +441,7 @@ struct bpf_skb_data_end { struct xdp_buff { void *data; void *data_end; + void *data_hard_start; }; /* compute the linear packet data range [data, data_end) which @@ -595,7 +597,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); -bool bpf_helper_changes_skb_data(void *func); +bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -- cgit From 71a2f11511b4d1dc8b8e326e10ec6533b534ddf1 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 5 Dec 2016 05:23:20 +0000 Subject: clk: add devm_get_clk_from_child() API Some driver is using this type of DT bindings for clock (more detail, see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.txt). sound_soc { ... cpu { clocks = <&xxx>; ... }; codec { clocks = <&xxx>; ... }; }; Current driver in this case uses of_clk_get() for each node, but there is no devm_of_clk_get() today. OTOH, the problem of having devm_of_clk_get() is that it encourages the use of of_clk_get() when clk_get() is more desirable. Thus, this patch adds new devm_get_clk_from_chile() which explicitly reads as get a clock from a child node of this device. By this function, we can also use this type of DT bindings sound_soc { clocks = <&xxx>, <&xxx>; clock-names = "cpu", "codec"; clock-ranges; ... cpu { ... }; codec { ... }; }; Signed-off-by: Kuninori Morimoto [sboyd@codeurora.org: Rename subject to clk + add API] Signed-off-by: Stephen Boyd --- include/linux/clk.h | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 123c02788807..e9d36b3e49de 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -17,8 +17,9 @@ #include struct device; - struct clk; +struct device_node; +struct of_phandle_args; /** * DOC: clk notifier callback types @@ -248,6 +249,23 @@ struct clk *clk_get(struct device *dev, const char *id); */ struct clk *devm_clk_get(struct device *dev, const char *id); +/** + * devm_get_clk_from_child - lookup and obtain a managed reference to a + * clock producer from child node. + * @dev: device for clock "consumer" + * @np: pointer to clock consumer node + * @con_id: clock consumer ID + * + * This function parses the clocks, and uses them to look up the + * struct clk from the registered list of clock providers by using + * @np and @con_id + * + * The clock will automatically be freed when the device is unbound + * from the bus. + */ +struct clk *devm_get_clk_from_child(struct device *dev, + struct device_node *np, const char *con_id); + /** * clk_enable - inform the system when the clock source should be running. * @clk: clock source @@ -432,6 +450,12 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; } +static inline struct clk *devm_get_clk_from_child(struct device *dev, + struct device_node *np, const char *con_id) +{ + return NULL; +} + static inline void clk_put(struct clk *clk) {} static inline void devm_clk_put(struct device *dev, struct clk *clk) {} @@ -501,9 +525,6 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } -struct device_node; -struct of_phandle_args; - #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); -- cgit From 8cf868affdc459beee1a941df0cfaba1673740e3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 28 Nov 2016 13:03:21 -0500 Subject: tracing: Have the reg function allow to fail Some tracepoints have a registration function that gets enabled when the tracepoint is enabled. There may be cases that the registraction function must fail (for example, can't allocate enough memory). In this case, the tracepoint should also fail to register, otherwise the user would not know why the tracepoint is not working. Cc: David Howells Cc: Seiji Aguchi Cc: Anton Blanchard Cc: Mathieu Desnoyers Signed-off-by: Steven Rostedt --- include/linux/tracepoint-defs.h | 2 +- include/linux/tracepoint.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 4ac89acb6136..a03192052066 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -29,7 +29,7 @@ struct tracepoint_func { struct tracepoint { const char *name; /* Tracepoint name */ struct static_key key; - void (*regfunc)(void); + int (*regfunc)(void); void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; }; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index be586c632a0c..f72fcfe0e66a 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -81,7 +81,7 @@ static inline void tracepoint_synchronize_unregister(void) } #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS -extern void syscall_regfunc(void); +extern int syscall_regfunc(void); extern void syscall_unregfunc(void); #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */ -- cgit From f9d03f96b988002027d4b28ea1b7a24729a4c9b5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 8 Dec 2016 15:20:32 -0700 Subject: block: improve handling of the magic discard payload Instead of allocating a single unused biovec for discard requests, send them down without any payload. Instead we allow the driver to add a "special" payload using a biovec embedded into struct request (unioned over other fields never used while in the driver), and overloading the number of segments for this case. This has a couple of advantages: - we don't have to allocate the bio_vec - the amount of special casing for discard requests in the block layer is significantly reduced - using this same scheme for other request types is trivial, which will be important for implementing the new WRITE_ZEROES op on devices where it actually requires a payload (e.g. SCSI) - we can get rid of playing games with the request length, as we'll never touch it and completions will work just fine - it will allow us to support ranged discard operations in the future by merging non-contiguous discard bios into a single request - last but not least it removes a lot of code This patch is the common base for my WIP series for ranges discards and to remove discard_zeroes_data in favor of always using REQ_OP_WRITE_ZEROES, so it would be good to get it in quickly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 ++- include/linux/blkdev.h | 15 ++++++++++++--- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b15323934a29..7cf8a6c70a3f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -197,8 +197,9 @@ static inline unsigned bio_segments(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE_ZEROES: + return 0; + case REQ_OP_WRITE_SAME: return 1; default: break; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ebeef2b79c5a..c5393766909d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -120,10 +120,13 @@ typedef __u32 __bitwise req_flags_t; #define RQF_HASHED ((__force req_flags_t)(1 << 16)) /* IO stats tracking on */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) +/* Look at ->special_vec for the actual data payload instead of the + bio chain. */ +#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ) + (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) #define BLK_MAX_CDB 16 @@ -175,6 +178,7 @@ struct request { */ union { struct rb_node rb_node; /* sort/lookup */ + struct bio_vec special_vec; void *completion_data; }; @@ -909,8 +913,6 @@ extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); -extern void blk_add_request_payload(struct request *rq, struct page *page, - int offset, unsigned int len); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, @@ -1153,6 +1155,13 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); +static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return 1; + return rq->nr_phys_segments; +} + extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -- cgit From fd4a0edf2a3d781c6ae07d2810776ce22302ee1c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Dec 2016 16:45:04 +0100 Subject: vfs: replace calling i_op->readlink with vfs_readlink() Also check d_is_symlink() in callers instead of inode->i_op->readlink because following patches will allow NULL ->readlink for symlinks. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..eba20d1c068d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2935,6 +2935,7 @@ extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_fstatat(int , const char __user *, struct kstat *, int); extern const char *vfs_get_link(struct dentry *, struct delayed_call *); +extern int vfs_readlink(struct dentry *, char __user *, int); extern int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, -- cgit From 76fca90e9f3abc82114d9d02d8e14e0324a18ca2 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Dec 2016 16:45:04 +0100 Subject: vfs: default to generic_readlink() If i_op->readlink is NULL, but i_op->get_link is set then vfs_readlink() defaults to calling generic_readlink(). The IOP_DEFAULT_READLINK flag indicates that the above conditions are met and the default action can be taken. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index eba20d1c068d..f6c206eae6ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -595,6 +595,7 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 +#define IOP_DEFAULT_READLINK 0x0010 /* * Keep mostly read-only and often accessed (especially for -- cgit From d16744ec8ad011793144bb932ce822cc0c1733cb Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 9 Dec 2016 16:45:04 +0100 Subject: vfs: make generic_readlink() static Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f6c206eae6ac..e343d784651a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2915,7 +2915,6 @@ extern int __page_symlink(struct inode *inode, const char *symname, int len, extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); extern int vfs_getattr(struct path *, struct kstat *); -- cgit From ae911c5e796d51cb2d1ed3a55e73b9cc88d176cf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Dec 2016 13:19:30 -0700 Subject: blk-mq: add blk_mq_start_stopped_hw_queue() We have a variant for all hardware queues, but not one for a single hardware queue. Signed-off-by: Jens Axboe Reviewed-by: Hannes Reinecke --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 35a0af5ede6d..87e404aae267 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -231,6 +231,7 @@ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); +void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -- cgit From 70b3ea056f3074be6d9256c312b64c0d90a4a683 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Dec 2016 08:43:31 -0700 Subject: elevator: make the rqhash helpers exported Signed-off-by: Jens Axboe Reviewed-by: Hannes Reinecke --- include/linux/elevator.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index f219c9aed360..b276e9ef0e0b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -108,6 +108,11 @@ struct elevator_type #define ELV_HASH_BITS 6 +void elv_rqhash_del(struct request_queue *q, struct request *rq); +void elv_rqhash_add(struct request_queue *q, struct request *rq); +void elv_rqhash_reposition(struct request_queue *q, struct request *rq); +struct request *elv_rqhash_find(struct request_queue *q, sector_t offset); + /* * each queue has an elevator_queue associated with it */ -- cgit From a6ab53742a52786ca594438eff2c80c3a242aaf3 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 14 Nov 2016 15:53:05 -0800 Subject: configfs: Minimize #include directives Only include the header files that are needed by configfs.h itself. Add #include . Signed-off-by: Bart Van Assche Cc: Christoph Hellwig --- include/linux/configfs.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index d9d6a9d77489..9fc9843c0300 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -35,14 +35,11 @@ #ifndef _CONFIGFS_H_ #define _CONFIGFS_H_ -#include -#include -#include -#include -#include -#include - -#include +#include /* S_IRUGO */ +#include /* ssize_t */ +#include /* struct list_head */ +#include /* struct kref */ +#include /* struct mutex */ #define CONFIGFS_ITEM_NAME_LEN 20 -- cgit From 876bec6f9bbfcb394916d17e35226b086c04dc45 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 9 Dec 2016 16:18:30 -0800 Subject: vfs: refactor clone/dedupe_file_range common functions Hoist both the XFS reflink inode state and preparation code and the XFS file blocks compare functions into the VFS so that ocfs2 can take advantage of it for reflink and dedupe. Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..caea736fa09c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1778,8 +1778,14 @@ extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *, int); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, + struct inode *inode_out, loff_t pos_out, + u64 *len, bool is_dedupe); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); +extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -- cgit From c84d949057cab262b4d3110ead9a42a58c2958f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Dec 2016 11:41:55 -0800 Subject: udp: copy skb->truesize in the first cache line In UDP RX handler, we currently clear skb->dev before skb is added to receive queue, because device pointer is no longer available once we exit from RCU section. Since this first cache line is always hot, lets reuse this space to store skb->truesize and thus avoid a cache line miss at udp_recvmsg()/udp_skb_destructor time while receive queue spinlock is held. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0cd92b0f2af5..332e76756f54 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -645,8 +645,15 @@ struct sk_buff { struct rb_node rbnode; /* used in netem & tcp stack */ }; struct sock *sk; - struct net_device *dev; + union { + struct net_device *dev; + /* Some protocols might use this space to store information, + * while device pointer would be NULL. + * UDP receive path is one user. + */ + unsigned long dev_scratch; + }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you -- cgit From 6b229cf77d683f634f0edd876c6d1015402303ad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Dec 2016 11:41:56 -0800 Subject: udp: add batching to udp_rmem_release() If udp_recvmsg() constantly releases sk_rmem_alloc for every read packet, it gives opportunity for producers to immediately grab spinlocks and desperatly try adding another packet, causing false sharing. We can add a simple heuristic to give the signal by batches of ~25 % of the queue capacity. This patch considerably increases performance under flood by about 50 %, since the thread draining the queue is no longer slowed by false sharing. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/udp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index d1fd8cd39478..c0f530809d1f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -79,6 +79,9 @@ struct udp_sock { int (*gro_complete)(struct sock *sk, struct sk_buff *skb, int nhoff); + + /* This field is dirtied by udp_recvmsg() */ + int forward_deficit; }; static inline struct udp_sock *udp_sk(const struct sock *sk) -- cgit From dff25ddb48086afcb434770caa3d6849a4489b85 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 2 Dec 2016 22:53:30 -0500 Subject: nfs: add support for the umask attribute Clients can set the umask attribute when creating files to cause the server to apply it always except when inheriting permissions from the parent directory. That way, the new files will end up with the same permissions as files created locally. See https://tools.ietf.org/html/draft-ietf-nfsv4-umask-02 for more details. Signed-off-by: Andreas Gruenbacher Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 9094faf0699d..bca536341d1a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -440,6 +440,7 @@ enum lock_type4 { #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) +#define FATTR4_WORD2_MODE_UMASK (1UL << 17) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 617cfaa20ffc..348f7c158084 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -433,6 +433,7 @@ struct nfs_openargs { enum open_claim_type4 claim; enum createmode4 createmode; const struct nfs4_label *label; + umode_t umask; }; struct nfs_openres { @@ -958,6 +959,7 @@ struct nfs4_create_arg { const struct nfs_fh * dir_fh; const u32 * bitmask; const struct nfs4_label *label; + umode_t umask; }; struct nfs4_create_res { -- cgit From f680b2845694a197e7bfc9f56b241f9a3f17296e Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 20 Nov 2016 02:55:45 -0800 Subject: hwmon: (core) Clarify when read and write callbacks are mandatory The callback descrption in hwmon.h was misleading and stated that read and write callbacks would be optional. More accurate is is that the callbacks are mandatory if readable / writeable attributes are present. Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 9d2f8bde7d12..b6a86aa4a9e2 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -298,8 +298,7 @@ enum hwmon_pwm_attributes { * Channel number * The function returns the file permissions. * If the return value is 0, no attribute will be created. - * @read: Read callback. Optional. If not provided, attributes - * will not be readable. + * @read: Read callback. Mandatory if readable attributes are present. * Parameters are: * @dev: Pointer to hardware monitoring device * @type: Sensor type @@ -308,8 +307,7 @@ enum hwmon_pwm_attributes { * Channel number * @val: Pointer to returned value * The function returns 0 on success or a negative error number. - * @write: Write callback. Optional. If not provided, attributes - * will not be writable. + * @write: Write callback. Mandatory if writeable attributes are present. * Parameters are: * @dev: Pointer to hardware monitoring device * @type: Sensor type -- cgit From e159ab5cb1afb519601a961405933c61cdd5a56a Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 7 Aug 2016 20:51:25 -0700 Subject: hwmon: (core) Add support for string attributes to new API The new API is so far only suited for data attributes and does not work well for string attributes, specifically for the 'label' attributes. Provide a separate callback function for those. Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index b6a86aa4a9e2..e68334aede4c 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -298,7 +298,8 @@ enum hwmon_pwm_attributes { * Channel number * The function returns the file permissions. * If the return value is 0, no attribute will be created. - * @read: Read callback. Mandatory if readable attributes are present. + * @read: Read callback for data attributes. Mandatory if readable + * data attributes are present. * Parameters are: * @dev: Pointer to hardware monitoring device * @type: Sensor type @@ -307,7 +308,19 @@ enum hwmon_pwm_attributes { * Channel number * @val: Pointer to returned value * The function returns 0 on success or a negative error number. - * @write: Write callback. Mandatory if writeable attributes are present. + * @read_string: + * Read callback for string attributes. Mandatory if string + * attributes are present. + * Parameters are: + * @dev: Pointer to hardware monitoring device + * @type: Sensor type + * @attr: Sensor attribute + * @channel: + * Channel number + * @str: Pointer to returned string + * The function returns 0 on success or a negative error number. + * @write: Write callback for data attributes. Mandatory if writeable + * data attributes are present. * Parameters are: * @dev: Pointer to hardware monitoring device * @type: Sensor type @@ -322,6 +335,8 @@ struct hwmon_ops { u32 attr, int channel); int (*read)(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val); + int (*read_string)(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, char **str); int (*write)(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val); }; -- cgit From af1bd36c06b5fad33baa7ee16820226efbd96cd9 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 16 Oct 2016 11:31:08 -0700 Subject: hwmon: (core) Deprecate hwmon_device_register() Inform the user that hwmon_device_register() is deprecated, and suggest conversion to the newest API. Also remove hwmon_device_register() from the kernel API documentation. Note that hwmon_device_register() is not marked as __deprecated() since doing so might result in build errors. Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index e68334aede4c..2588e6ee7660 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -362,7 +362,9 @@ struct hwmon_chip_info { const struct hwmon_channel_info **info; }; +/* hwmon_device_register() is deprecated */ struct device *hwmon_device_register(struct device *dev); + struct device * hwmon_device_register_with_groups(struct device *dev, const char *name, void *drvdata, -- cgit From 848ba0a2f20dc121a3ef5272a24641d2bd963d8b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 16 Oct 2016 17:20:43 -0700 Subject: hwmon: (core) Rename groups parameter in API to extra_groups The 'groups' parameter of hwmon_device_register_with_info() and devm_hwmon_device_register_with_info() is only necessary if extra non-standard attributes need to be provided. Rename the parameter to extra_groups and clarify the documentation. Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 2588e6ee7660..78d59dba563e 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -377,12 +377,12 @@ struct device * hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *info, - const struct attribute_group **groups); + const struct attribute_group **extra_groups); struct device * devm_hwmon_device_register_with_info(struct device *dev, - const char *name, void *drvdata, - const struct hwmon_chip_info *info, - const struct attribute_group **groups); + const char *name, void *drvdata, + const struct hwmon_chip_info *info, + const struct attribute_group **extra_groups); void hwmon_device_unregister(struct device *dev); void devm_hwmon_device_unregister(struct device *dev); -- cgit From db717d8e26c2d1b0dba3e08668a1e6a7f665adde Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 26 Nov 2016 19:07:49 -0500 Subject: fscrypto: move ioctl processing more fully into common code Multiple bugs were recently fixed in the "set encryption policy" ioctl. To make it clear that fscrypt_process_policy() and fscrypt_get_policy() implement ioctls and therefore their implementations must take standard security and correctness precautions, rename them to fscrypt_ioctl_set_policy() and fscrypt_ioctl_get_policy(). Make the latter take in a struct file * to make it consistent with the former. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 98c71e973a96..be94684dc05f 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -259,8 +259,8 @@ extern void fscrypt_restore_control_page(struct page *); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); /* policy.c */ -extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); -extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); +extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); +extern int fscrypt_ioctl_get_policy(struct file *, void __user *); extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, void *, bool); @@ -334,14 +334,14 @@ static inline int fscrypt_notsupp_zeroout_range(const struct inode *i, pgoff_t p } /* policy.c */ -static inline int fscrypt_notsupp_process_policy(struct file *f, - const struct fscrypt_policy *p) +static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f, + const void __user *arg) { return -EOPNOTSUPP; } -static inline int fscrypt_notsupp_get_policy(struct inode *i, - struct fscrypt_policy *p) +static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f, + void __user *arg) { return -EOPNOTSUPP; } -- cgit From 3325bea5b26ac67e2521383f10e5ea0156c9a4b6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Nov 2016 20:32:46 -0500 Subject: fscrypt: rename get_crypt_info() to fscrypt_get_crypt_info() To avoid namespace collisions, rename get_crypt_info() to fscrypt_get_crypt_info(). The function is only used inside the fs/crypto directory, so declare it in the new header file, fscrypt_private.h. Signed-off-by: Theodore Ts'o Reviewed-by: Eric Biggers --- include/linux/fscrypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index be94684dc05f..2f8894f0696c 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -265,7 +265,6 @@ extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, void *, bool); /* keyinfo.c */ -extern int get_crypt_info(struct inode *); extern int fscrypt_get_encryption_info(struct inode *); extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); -- cgit From b98701df349b7003efd52d9330acbb7be5a255c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Nov 2016 20:43:09 -0500 Subject: fscrypt: unexport fscrypt_initialize() The fscrypt_initalize() function isn't used outside fs/crypto, so there's no point making it be an exported symbol. Signed-off-by: Theodore Ts'o Reviewed-by: Eric Biggers --- include/linux/fscrypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 2f8894f0696c..ce2ebdee6a89 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -244,7 +244,6 @@ static inline void fscrypt_set_d_op(struct dentry *dentry) #if IS_ENABLED(CONFIG_FS_ENCRYPTION) /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; -int fscrypt_initialize(void); extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); -- cgit From cc4e0df038ddb73510c01712abf302b3f0130147 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Nov 2016 22:05:18 -0500 Subject: fscrypt: move non-public structures and constants to fscrypt_private.h Signed-off-by: Theodore Ts'o Reviewed-by: Eric Biggers --- include/linux/fscrypto.h | 68 +++--------------------------------------------- 1 file changed, 3 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index ce2ebdee6a89..71e8a20711ec 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -18,9 +18,6 @@ #include #include -#define FS_KEY_DERIVATION_NONCE_SIZE 16 -#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 - #define FS_POLICY_FLAGS_PAD_4 0x00 #define FS_POLICY_FLAGS_PAD_8 0x01 #define FS_POLICY_FLAGS_PAD_16 0x02 @@ -35,56 +32,10 @@ #define FS_ENCRYPTION_MODE_AES_256_CBC 3 #define FS_ENCRYPTION_MODE_AES_256_CTS 4 -/** - * Encryption context for inode - * - * Protector format: - * 1 byte: Protector format (1 = this version) - * 1 byte: File contents encryption mode - * 1 byte: File names encryption mode - * 1 byte: Flags - * 8 bytes: Master Key descriptor - * 16 bytes: Encryption Key derivation nonce - */ -struct fscrypt_context { - u8 format; - u8 contents_encryption_mode; - u8 filenames_encryption_mode; - u8 flags; - u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; -} __packed; - -/* Encryption parameters */ -#define FS_XTS_TWEAK_SIZE 16 -#define FS_AES_128_ECB_KEY_SIZE 16 -#define FS_AES_256_GCM_KEY_SIZE 32 -#define FS_AES_256_CBC_KEY_SIZE 32 -#define FS_AES_256_CTS_KEY_SIZE 32 -#define FS_AES_256_XTS_KEY_SIZE 64 -#define FS_MAX_KEY_SIZE 64 - -#define FS_KEY_DESC_PREFIX "fscrypt:" -#define FS_KEY_DESC_PREFIX_SIZE 8 - -/* This is passed in from userspace into the kernel keyring */ -struct fscrypt_key { - u32 mode; - u8 raw[FS_MAX_KEY_SIZE]; - u32 size; -} __packed; - -struct fscrypt_info { - u8 ci_data_mode; - u8 ci_filename_mode; - u8 ci_flags; - struct crypto_skcipher *ci_ctfm; - struct key *ci_keyring_key; - u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; -}; +#define FS_CRYPTO_BLOCK_SIZE 16 -#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 -#define FS_WRITE_PATH_FL 0x00000002 +struct fscrypt_info; +struct fscrypt_ctx; struct fscrypt_ctx { union { @@ -102,19 +53,6 @@ struct fscrypt_ctx { u8 mode; /* Encryption mode for tfm */ }; -struct fscrypt_completion_result { - struct completion completion; - int res; -}; - -#define DECLARE_FS_COMPLETION_RESULT(ecr) \ - struct fscrypt_completion_result ecr = { \ - COMPLETION_INITIALIZER((ecr).completion), 0 } - -#define FS_FNAME_NUM_SCATTER_ENTRIES 4 -#define FS_CRYPTO_BLOCK_SIZE 16 -#define FS_FNAME_CRYPTO_DIGEST_SIZE 32 - /** * For encrypted symlinks, the ciphertext length is stored at the beginning * of the string in little-endian format. -- cgit From 41d5319af3368127b55f6587f1c747dd6a7b9b04 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Nov 2016 22:18:59 -0500 Subject: fscrypt: move the policy flags and encryption mode definitions to uapi header These constants are part of the UAPI, so they belong in include/uapi/linux/fs.h instead of include/linux/fscrypto.h Signed-off-by: Theodore Ts'o Reviewed-by: Eric Biggers --- include/linux/fscrypto.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 71e8a20711ec..42ef82d60790 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -18,20 +18,6 @@ #include #include -#define FS_POLICY_FLAGS_PAD_4 0x00 -#define FS_POLICY_FLAGS_PAD_8 0x01 -#define FS_POLICY_FLAGS_PAD_16 0x02 -#define FS_POLICY_FLAGS_PAD_32 0x03 -#define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 - -/* Encryption algorithms */ -#define FS_ENCRYPTION_MODE_INVALID 0 -#define FS_ENCRYPTION_MODE_AES_256_XTS 1 -#define FS_ENCRYPTION_MODE_AES_256_GCM 2 -#define FS_ENCRYPTION_MODE_AES_256_CBC 3 -#define FS_ENCRYPTION_MODE_AES_256_CTS 4 - #define FS_CRYPTO_BLOCK_SIZE 16 struct fscrypt_info; -- cgit From 1400451f04f2ff28b658b92557495e5090914aee Mon Sep 17 00:00:00 2001 From: David Gstir Date: Tue, 6 Dec 2016 23:53:55 +0100 Subject: fscrypt: Cleanup fscrypt_{decrypt,encrypt}_page() - Improve documentation - Add BUG_ON(len == 0) to avoid accidental switch of offs and len parameters - Improve variable names for readability Signed-off-by: David Gstir Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 42ef82d60790..2d9abfa22b94 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -173,9 +173,9 @@ extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, unsigned int, unsigned int, - pgoff_t, gfp_t); + u64, gfp_t); extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, - unsigned int, pgoff_t); + unsigned int, u64); extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); extern void fscrypt_pullback_bio_page(struct page **, bool); extern void fscrypt_restore_control_page(struct page *); @@ -221,14 +221,14 @@ static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i, struct page *p, unsigned int len, unsigned int offs, - pgoff_t index, gfp_t f) + u64 lblk_num, gfp_t f) { return ERR_PTR(-EOPNOTSUPP); } static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p, unsigned int len, unsigned int offs, - pgoff_t index) + u64 lblk_num) { return -EOPNOTSUPP; } -- cgit From bd7b8290388dd58a8c0a3710b171e58ef952ca4d Mon Sep 17 00:00:00 2001 From: David Gstir Date: Tue, 6 Dec 2016 23:53:56 +0100 Subject: fscrypt: Cleanup page locking requirements for fscrypt_{decrypt,encrypt}_page() Rename the FS_CFLG_INPLACE_ENCRYPTION flag to FS_CFLG_OWN_PAGES which, when set, indicates that the fs uses pages under its own control as opposed to writeback pages which require locking and a bounce buffer for encryption. Signed-off-by: David Gstir Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 2d9abfa22b94..188b4fa59cbf 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -80,7 +80,7 @@ struct fscrypt_name { /* * fscrypt superblock flags */ -#define FS_CFLG_INPLACE_ENCRYPTION (1U << 1) +#define FS_CFLG_OWN_PAGES (1U << 1) /* * crypto opertions for filesystems -- cgit From f32d7ac20a5864483c1f96e4970daa083e18bfd1 Mon Sep 17 00:00:00 2001 From: David Gstir Date: Tue, 6 Dec 2016 23:53:57 +0100 Subject: fscrypt: Delay bounce page pool allocation until needed Since fscrypt users can now indicated if fscrypt_encrypt_page() should use a bounce page, we can delay the bounce page pool initialization util it is really needed. That is until fscrypt_operations has no FS_CFLG_OWN_PAGES flag set. Signed-off-by: David Gstir Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 188b4fa59cbf..1adc1c758d31 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -168,7 +168,6 @@ static inline void fscrypt_set_d_op(struct dentry *dentry) #if IS_ENABLED(CONFIG_FS_ENCRYPTION) /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; - extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, -- cgit From 6a34e4d2be07255cc59e6ccaf820669cfd7f815c Mon Sep 17 00:00:00 2001 From: David Gstir Date: Tue, 6 Dec 2016 23:53:58 +0100 Subject: fscrypt: Rename FS_WRITE_PATH_FL to FS_CTX_HAS_BOUNCE_BUFFER_FL ... to better explain its purpose after introducing in-place encryption without bounce buffer. Signed-off-by: David Gstir Signed-off-by: Theodore Ts'o --- include/linux/fscrypto.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index 1adc1c758d31..c074b670aa99 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -21,7 +21,6 @@ #define FS_CRYPTO_BLOCK_SIZE 16 struct fscrypt_info; -struct fscrypt_ctx; struct fscrypt_ctx { union { -- cgit From e8f4aa6087fa80732382881ef7c0c96733bb1984 Mon Sep 17 00:00:00 2001 From: Allen Pais Date: Thu, 13 Oct 2016 10:06:13 +0530 Subject: sparc64:Support User Probes for sparc Signed-off-by: Eric Saint Etienne Signed-off-by: Allen Pais Signed-off-by: David S. Miller --- include/linux/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 4a29c75b146e..0a294e950df8 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -27,6 +27,7 @@ #include #include #include +#include struct vm_area_struct; struct mm_struct; -- cgit From 5191d88acc688743eef56f1c598a4e4cddf6c6cd Mon Sep 17 00:00:00 2001 From: Nick Dyer Date: Sat, 10 Dec 2016 23:27:32 -0800 Subject: Input: synaptics-rmi4 - add support for F34 V7 bootloader Port firmware update code from Samsung Galaxy S7 driver into mainline framework. This patch has been tested on Synaptics S7813. Signed-off-by: Nick Dyer Tested-by: Chris Healy Signed-off-by: Dmitry Torokhov --- include/linux/rmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmi.h b/include/linux/rmi.h index ac910f730688..64125443f8a6 100644 --- a/include/linux/rmi.h +++ b/include/linux/rmi.h @@ -342,7 +342,7 @@ struct rmi_driver_data { struct rmi_function *f01_container; struct rmi_function *f34_container; - bool f01_bootloader_mode; + bool bootloader_mode; int num_of_irq_regs; int irq_count; -- cgit From 0dde584882ade13dc9708d611fbf69b0ae8a9e48 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 2 Dec 2016 16:35:09 +0100 Subject: libceph: drop len argument of *verify_authorizer_reply() The length of the reply is protocol-dependent - for cephx it's ceph_x_authorize_reply. Nothing sensible can be passed from the messenger layer anyway. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/auth.h | 5 ++--- include/linux/ceph/messenger.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 374bb1c4ef52..a6747789fe5c 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -64,7 +64,7 @@ struct ceph_auth_client_ops { int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, - struct ceph_authorizer *a, size_t len); + struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, int peer_type); @@ -118,8 +118,7 @@ extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, - struct ceph_authorizer *a, - size_t len); + struct ceph_authorizer *a); extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, int peer_type); diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8dbd7879fdc6..531f2d882bd9 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -30,7 +30,7 @@ struct ceph_connection_operations { struct ceph_auth_handshake *(*get_authorizer) ( struct ceph_connection *con, int *proto, int force_new); - int (*verify_authorizer_reply) (struct ceph_connection *con, int len); + int (*verify_authorizer_reply) (struct ceph_connection *con); int (*invalidate_authorizer)(struct ceph_connection *con); /* there was some error on the socket (disconnect, whatever) */ -- cgit From 34888602eb99df174e76eafeb613ad857f534ebb Mon Sep 17 00:00:00 2001 From: Jingkui Wang Date: Sat, 10 Dec 2016 22:44:10 -0800 Subject: Input: drv260x - use generic device properties Update driver drv260x to use generic device properties so that it can be used on non-DT systems. We also remove platform data as generic device properties work on static board code as well. Signed-off-by: Jingkui Wang Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/drv260x-pdata.h | 28 ---------------------------- 1 file changed, 28 deletions(-) delete mode 100644 include/linux/platform_data/drv260x-pdata.h (limited to 'include/linux') diff --git a/include/linux/platform_data/drv260x-pdata.h b/include/linux/platform_data/drv260x-pdata.h deleted file mode 100644 index 0a03b0944411..000000000000 --- a/include/linux/platform_data/drv260x-pdata.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Platform data for DRV260X haptics driver family - * - * Author: Dan Murphy - * - * Copyright: (C) 2014 Texas Instruments, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -#ifndef _LINUX_DRV260X_PDATA_H -#define _LINUX_DRV260X_PDATA_H - -struct drv260x_platform_data { - u32 library_selection; - u32 mode; - u32 vib_rated_voltage; - u32 vib_overdrive_voltage; -}; - -#endif -- cgit From e9e427f0a14f7e4773896dd7af357819a56d097a Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 10 Nov 2016 16:02:06 +0800 Subject: ceph: check availability of mds cluster on mount Signed-off-by: Yan, Zheng --- include/linux/ceph/mdsmap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 87ed09f54800..8ed5dc505fbb 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -31,6 +31,10 @@ struct ceph_mdsmap { int m_num_data_pg_pools; u64 *m_data_pg_pools; u64 m_cas_pg_pool; + + bool m_enabled; + bool m_damaged; + int m_num_laggy; }; static inline struct ceph_entity_addr * @@ -59,5 +63,6 @@ static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m); extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end); extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m); +extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m); #endif -- cgit From 1e4ef0c6332bd90e6c70afc07b35dffaf1eab1a7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 10 Nov 2016 07:42:06 -0500 Subject: ceph: add flags parameter to send_cap_msg Add a flags parameter to send_cap_msg, so we can request expedited service from the MDS when we know we'll be waiting on the result. Set that flag in the case of try_flush_caps. The callers of that function generally wait synchronously on the result, so it's beneficial to ask the server to expedite it. Signed-off-by: Jeff Layton Reviewed-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index f96de8de4fa7..f4b2ee18f38c 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -653,6 +653,9 @@ enum { extern const char *ceph_cap_op_name(int op); +/* flags field in client cap messages (version >= 10) */ +#define CEPH_CLIENT_CAPS_SYNC (0x1) + /* * caps message, used for capability callbacks, acks, requests, etc. */ -- cgit From c0b942a76361e08fc9fb17989e0f266e64ff0688 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Mon, 12 Dec 2016 16:40:39 -0800 Subject: kthread: add __printf attributes When commit fbae2d44aa1d ("kthread: add kthread_create_worker*()") introduced some kthread_create_...() functions which were taking printf-like parametter, it introduced __printf attributes to some functions (e.g. kthread_create_worker()). Nevertheless some new functions were forgotten (they have been detected thanks to -Wmissing-format-attribute warning flag). Add the missing __printf attributes to the newly-introduced functions in order to detect formatting issues at build-time with -Wformat flag. Link: http://lkml.kernel.org/r/20161126193543.22672-1-nicolas.iooss_linux@m4x.org Signed-off-by: Nicolas Iooss Reviewed-by: Petr Mladek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c1c3e63d52c1..4fec8b775895 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -175,7 +175,7 @@ __printf(2, 3) struct kthread_worker * kthread_create_worker(unsigned int flags, const char namefmt[], ...); -struct kthread_worker * +__printf(3, 4) struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[], ...); -- cgit From 3fb4afd9a504c2386b8435028d43283216bf588e Mon Sep 17 00:00:00 2001 From: Stanislav Kinsburskiy Date: Mon, 12 Dec 2016 16:40:42 -0800 Subject: prctl: remove one-shot limitation for changing exe link This limitation came with the reason to remove "another way for malicious code to obscure a compromised program and masquerade as a benign process" by allowing "security-concious program can use this prctl once during its early initialization to ensure the prctl cannot later be abused for this purpose": http://marc.info/?l=linux-kernel&m=133160684517468&w=2 This explanation doesn't look sufficient. The only thing "exe" link is indicating is the file, used to execve, which is basically nothing and not reliable immediately after process has returned from execve system call. Moreover, to use this feture, all the mappings to previous exe file have to be unmapped and all the new exe file permissions must be satisfied. Which means, that changing exe link is very similar to calling execve on the binary. The need to remove this limitations comes from migration of NFS mount point, which is not accessible during restore and replaced by other file system. Because of this exe link has to be changed twice. [akpm@linux-foundation.org: fix up comment] Link: http://lkml.kernel.org/r/20160927153755.9337.69650.stgit@localhost.localdomain Signed-off-by: Stanislav Kinsburskiy Acked-by: Oleg Nesterov Acked-by: Cyrill Gorcunov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Michal Hocko Cc: Kees Cook Cc: Andy Lutomirski Cc: John Stultz Cc: Matt Helsley Cc: Pavel Emelyanov Cc: Vlastimil Babka Cc: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7551d3e2ab70..0e90f2973719 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -540,7 +540,11 @@ static inline int get_dumpable(struct mm_struct *mm) /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ #define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ -#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -- cgit From fd60775aea802beef444881ddfa111a4b73b1bbc Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 12 Dec 2016 16:42:20 -0800 Subject: mm, thp: avoid unlikely branches for split_huge_pmd While doing MADV_DONTNEED on a large area of thp memory, I noticed we encountered many unlikely() branches in profiles for each backing hugepage. This is because zap_pmd_range() would call split_huge_pmd(), which rechecked the conditions that were already validated, but as part of an unlikely() branch. Avoid the unlikely() branch when in a context where pmd is known to be good for __split_huge_pmd() directly. Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1610181600300.84525@chino.kir.corp.google.com Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e35e6de633b9..1f782aa1d8e6 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -189,6 +189,8 @@ static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) +static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address, bool freeze, struct page *page) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} -- cgit From 41a9ada3e6b4253f1a3ce42699c6aaeb8584306c Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Mon, 12 Dec 2016 16:43:02 -0800 Subject: of/fdt: mark hotpluggable memory When movable nodes are enabled, any node containing only hotpluggable memory is made movable at boot time. On x86, hotpluggable memory is discovered by parsing the ACPI SRAT, making corresponding calls to memblock_mark_hotplug(). If we introduce a dt property to describe memory as hotpluggable, configs supporting early fdt may then also do this marking and use movable nodes. Link: http://lkml.kernel.org/r/1479160961-25840-5-git-send-email-arbab@linux.vnet.ibm.com Signed-off-by: Reza Arbab Tested-by: Balbir Singh Acked-by: Balbir Singh Cc: "Aneesh Kumar K.V" Cc: "H. Peter Anvin" Cc: Alistair Popple Cc: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Bharata B Rao Cc: Frank Rowand Cc: Ingo Molnar Cc: Michael Ellerman Cc: Nathan Fontenot Cc: Paul Mackerras Cc: Rob Herring Cc: Stewart Smith Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/of_fdt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 4341f32516d8..271b3fdf0070 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -71,6 +71,7 @@ extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); extern void early_init_dt_add_memory_arch(u64 base, u64 size); +extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size); extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool no_map); extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); -- cgit From c1ef8e2c0235bffe4b0505c3325bb8a6af954021 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 12 Dec 2016 16:43:12 -0800 Subject: mm: disable numa migration faults for dax vmas Mark dax vmas as not migratable to exclude them from task_numa_work(). This is especially relevant for device-dax which wants to ensure predictable access latency and not incur periodic faults. [akpm@linux-foundation.org: add comment] Link: http://lkml.kernel.org/r/147892450132.22062.16875659431109209179.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Aneesh Kumar K.V Cc: Michal Hocko Cc: Vlastimil Babka Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5e5b2969d931..5f4d8281832b 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -7,6 +7,7 @@ #include +#include #include #include #include @@ -177,6 +178,13 @@ static inline bool vma_migratable(struct vm_area_struct *vma) if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; + /* + * DAX device mappings require predictable access latency, so avoid + * incurring periodic faults. + */ + if (vma_is_dax(vma)) + return false; + #ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION if (vma->vm_flags & VM_HUGETLB) return false; -- cgit From d5e6eff265fe7537fa494e6ab125747813be76a0 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 12 Dec 2016 16:43:15 -0800 Subject: mm: cma: make linux/cma.h standalone includible The header uses types and definitions from the linux/init.h as well as linux/types.h headers without explicitly including them. This causes a failure to compile if they are not implicitly pulled in by includers. Link: http://lkml.kernel.org/r/20161115133235.13387-1-thierry.reding@gmail.com Signed-off-by: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index 29f9e774ab76..6f0a91b37f68 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -1,6 +1,9 @@ #ifndef __CMA_H__ #define __CMA_H__ +#include +#include + /* * There is always at least global CMA area and a few optional * areas configured in kernel .config. -- cgit From 9491ae4aade6814afcfa67f4eb3e3342c2b39750 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 12 Dec 2016 16:43:26 -0800 Subject: mm: don't cap request size based on read-ahead setting We ran into a funky issue, where someone doing 256K buffered reads saw 128K requests at the device level. Turns out it is read-ahead capping the request size, since we use 128K as the default setting. This doesn't make a lot of sense - if someone is issuing 256K reads, they should see 256K reads, regardless of the read-ahead setting, if the underlying device can support a 256K read in a single command. This patch introduces a bdi hint, io_pages. This is the soft max IO size for the lower level, I've hooked it up to the bdev settings here. Read-ahead is modified to issue the maximum of the user request size, and the read-ahead max size, but capped to the max request size on the device side. The latter is done to avoid reading ahead too much, if the application asks for a huge read. With this patch, the kernel behaves like the application expects. Link: http://lkml.kernel.org/r/1479498073-8657-1-git-send-email-axboe@fb.com Signed-off-by: Jens Axboe Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c357f27d5483..b8144b2d59ce 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -136,6 +136,7 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ + unsigned long io_pages; /* max allowed IO size */ unsigned int capabilities; /* Device capabilities */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ -- cgit From 8db378a570330fa0aaa9d75299fe264e4a5b6348 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 12 Dec 2016 16:43:29 -0800 Subject: include/linux/backing-dev-defs.h: shrink struct backing_dev_info Move the 4-byte `capabilities' field next to other 4-byte things. Shrinks sizeof(backing_dev_info) by 8 bytes on x86_64. Reviewed-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index b8144b2d59ce..0b5b1af35e5e 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -137,12 +137,12 @@ struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ - unsigned int capabilities; /* Device capabilities */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ char *name; + unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; -- cgit From f7942430e40f14c6d2ca48a1875add509938c07d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 12 Dec 2016 16:43:41 -0800 Subject: lib: radix-tree: native accounting of exceptional entries The way the page cache is sneaking shadow entries of evicted pages into the radix tree past the node entry accounting and tracking them manually in the upper bits of node->count is fraught with problems. These shadow entries are marked in the tree as exceptional entries, which are a native concept to the radix tree. Maintain an explicit counter of exceptional entries in the radix tree node. Subsequent patches will switch shadow entry tracking over to that counter. DAX and shmem are the other users of exceptional entries. Since slot replacements that change the entry type from regular to exceptional must now be accounted, introduce a __radix_tree_replace() function that does replacement and accounting, and switch DAX and shmem over. The increase in radix tree node size is temporary. A followup patch switches the shadow tracking to this new scheme and we'll no longer need the upper bits in node->count and shrink that back to one byte. Link: http://lkml.kernel.org/r/20161117192945.GA23430@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Jan Kara Cc: Kirill A. Shutemov Cc: Hugh Dickins Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index af3581b8a451..7ced8a70cc8b 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -85,9 +85,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_COUNT_MASK ((1UL << RADIX_TREE_COUNT_SHIFT) - 1) struct radix_tree_node { - unsigned char shift; /* Bits remaining in each slot */ - unsigned char offset; /* Slot offset in parent */ - unsigned int count; + unsigned char shift; /* Bits remaining in each slot */ + unsigned char offset; /* Slot offset in parent */ + unsigned int count; /* Total entry count */ + unsigned char exceptional; /* Exceptional entry count */ union { struct { /* Used when ascending tree */ @@ -276,6 +277,9 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void ***slotp); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void __radix_tree_replace(struct radix_tree_root *root, + struct radix_tree_node *node, + void **slot, void *item); bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); -- cgit From 6d75f366b9242f9b17ed7d0b0604d7460f818f21 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 12 Dec 2016 16:43:43 -0800 Subject: lib: radix-tree: check accounting of existing slot replacement users The bug in khugepaged fixed earlier in this series shows that radix tree slot replacement is fragile; and it will become more so when not only NULL<->!NULL transitions need to be caught but transitions from and to exceptional entries as well. We need checks. Re-implement radix_tree_replace_slot() on top of the sanity-checked __radix_tree_replace(). This requires existing callers to also pass the radix tree root, but it'll warn us when somebody replaces slots with contents that need proper accounting (transitions between NULL entries, real entries, exceptional entries) and where a replacement through the slot pointer would corrupt the radix tree node counts. Link: http://lkml.kernel.org/r/20161117193021.GB23430@cmpxchg.org Signed-off-by: Johannes Weiner Suggested-by: Jan Kara Reviewed-by: Jan Kara Cc: Kirill A. Shutemov Cc: Hugh Dickins Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7ced8a70cc8b..2d1b9b8be983 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -249,20 +249,6 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -/** - * radix_tree_replace_slot - replace item in a slot - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * @item: new item to store in the slot. - * - * For use with radix_tree_lookup_slot(). Caller must hold tree write locked - * across slot lookup and replacement. - */ -static inline void radix_tree_replace_slot(void **pslot, void *item) -{ - BUG_ON(radix_tree_is_internal_node(item)); - rcu_assign_pointer(*pslot, item); -} - int __radix_tree_create(struct radix_tree_root *root, unsigned long index, unsigned order, struct radix_tree_node **nodep, void ***slotp); @@ -280,6 +266,8 @@ void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void **slot, void *item); +void radix_tree_replace_slot(struct radix_tree_root *root, + void **slot, void *item); bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); -- cgit From 4d693d08607ab319095ec8942909df4b4aebdf66 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 12 Dec 2016 16:43:49 -0800 Subject: lib: radix-tree: update callback for changing leaf nodes Support handing __radix_tree_replace() a callback that gets invoked for all leaf nodes that change or get freed as a result of the slot replacement, to assist users tracking nodes with node->private_list. This prepares for putting page cache shadow entries into the radix tree root again and drastically simplifying the shadow tracking. Link: http://lkml.kernel.org/r/20161117193134.GD23430@cmpxchg.org Signed-off-by: Johannes Weiner Suggested-by: Jan Kara Reviewed-by: Jan Kara Cc: Kirill A. Shutemov Cc: Hugh Dickins Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 2d1b9b8be983..15c972ea9510 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -263,9 +263,11 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void ***slotp); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *); void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, - void **slot, void *item); + void **slot, void *item, + radix_tree_update_node_t update_node, void *private); void radix_tree_replace_slot(struct radix_tree_root *root, void **slot, void *item); bool __radix_tree_delete_node(struct radix_tree_root *root, -- cgit From 14b468791fa955d442f962fdf5207dfd39a131c8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 12 Dec 2016 16:43:52 -0800 Subject: mm: workingset: move shadow entry tracking to radix tree exceptional tracking Currently, we track the shadow entries in the page cache in the upper bits of the radix_tree_node->count, behind the back of the radix tree implementation. Because the radix tree code has no awareness of them, we rely on random subtleties throughout the implementation (such as the node->count != 1 check in the shrinking code, which is meant to exclude multi-entry nodes but also happens to skip nodes with only one shadow entry, as that's accounted in the upper bits). This is error prone and has, in fact, caused the bug fixed in d3798ae8c6f3 ("mm: filemap: don't plant shadow entries without radix tree node"). To remove these subtleties, this patch moves shadow entry tracking from the upper bits of node->count to the existing counter for exceptional entries. node->count goes back to being a simple counter of valid entries in the tree node and can be shrunk to a single byte. This vastly simplifies the page cache code. All accounting happens natively inside the radix tree implementation, and maintaining the LRU linkage of shadow nodes is consolidated into a single function in the workingset code that is called for leaf nodes affected by a change in the page cache tree. This also removes the last user of the __radix_delete_node() return value. Eliminate it. Link: http://lkml.kernel.org/r/20161117193211.GE23430@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Jan Kara Cc: Kirill A. Shutemov Cc: Hugh Dickins Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 8 ++------ include/linux/swap.h | 34 +--------------------------------- 2 files changed, 3 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 15c972ea9510..744486057e9e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -80,14 +80,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) -/* Internally used bits of node->count */ -#define RADIX_TREE_COUNT_SHIFT (RADIX_TREE_MAP_SHIFT + 1) -#define RADIX_TREE_COUNT_MASK ((1UL << RADIX_TREE_COUNT_SHIFT) - 1) - struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ - unsigned int count; /* Total entry count */ + unsigned char count; /* Total entry count */ unsigned char exceptional; /* Exceptional entry count */ union { struct { @@ -270,7 +266,7 @@ void __radix_tree_replace(struct radix_tree_root *root, radix_tree_update_node_t update_node, void *private); void radix_tree_replace_slot(struct radix_tree_root *root, void **slot, void *item); -bool __radix_tree_delete_node(struct radix_tree_root *root, +void __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); diff --git a/include/linux/swap.h b/include/linux/swap.h index a56523cefb9b..09b212d37f1d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -246,39 +246,7 @@ struct swap_info_struct { void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -extern struct list_lru workingset_shadow_nodes; - -static inline unsigned int workingset_node_pages(struct radix_tree_node *node) -{ - return node->count & RADIX_TREE_COUNT_MASK; -} - -static inline void workingset_node_pages_inc(struct radix_tree_node *node) -{ - node->count++; -} - -static inline void workingset_node_pages_dec(struct radix_tree_node *node) -{ - VM_WARN_ON_ONCE(!workingset_node_pages(node)); - node->count--; -} - -static inline unsigned int workingset_node_shadows(struct radix_tree_node *node) -{ - return node->count >> RADIX_TREE_COUNT_SHIFT; -} - -static inline void workingset_node_shadows_inc(struct radix_tree_node *node) -{ - node->count += 1U << RADIX_TREE_COUNT_SHIFT; -} - -static inline void workingset_node_shadows_dec(struct radix_tree_node *node) -{ - VM_WARN_ON_ONCE(!workingset_node_shadows(node)); - node->count -= 1U << RADIX_TREE_COUNT_SHIFT; -} +void workingset_update_node(struct radix_tree_node *node, void *private); /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; -- cgit From bf22e37a641327e34681b7b6959d9646e3886770 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Mon, 12 Dec 2016 16:44:10 -0800 Subject: mm: add vfree_atomic() We are going to use sleeping lock for freeing vmap. However some vfree() users want to free memory from atomic (but not from interrupt) context. For this we add vfree_atomic() - deferred variation of vfree() which can be used in any atomic context (except NMIs). [akpm@linux-foundation.org: tweak comment grammar] [aryabinin@virtuozzo.com: use raw_cpu_ptr() instead of this_cpu_ptr()] Link: http://lkml.kernel.org/r/1481553981-3856-1-git-send-email-aryabinin@virtuozzo.com Link: http://lkml.kernel.org/r/1479474236-4139-5-git-send-email-hch@lst.de Signed-off-by: Andrey Ryabinin Signed-off-by: Christoph Hellwig Cc: Joel Fernandes Cc: Jisheng Zhang Cc: Chris Wilson Cc: John Dias Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3d9d786a943c..d68edffbf142 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -82,6 +82,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller); extern void vfree(const void *addr); +extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); -- cgit From d5a187daf5856df9b997f9d208e5a7b64006eb2e Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 12 Dec 2016 16:44:38 -0800 Subject: mm, rmap: handle anon_vma_prepare() common case inline anon_vma_prepare() is mostly a large "if (unlikely(...))" block, as the expected common case is that an anon_vma already exists. We could turn the condition around and return 0, but it also makes sense to do it inline and avoid a call for the common case. Bloat-o-meter naturally shows that inlining the check has some code size costs: add/remove: 1/1 grow/shrink: 4/0 up/down: 475/-373 (102) function old new delta __anon_vma_prepare - 359 +359 handle_mm_fault 2744 2796 +52 hugetlb_cow 1146 1170 +24 hugetlb_fault 2123 2145 +22 wp_page_copy 1469 1487 +18 anon_vma_prepare 373 - -373 Checking the asm however confirms that the hot paths now avoid a call, which is moved away. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20161116074005.22768-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Konstantin Khlebnikov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b46bb5620a76..15321fb1df6b 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -137,11 +137,19 @@ static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) * anon_vma helper functions. */ void anon_vma_init(void); /* create anon_vma_cachep */ -int anon_vma_prepare(struct vm_area_struct *); +int __anon_vma_prepare(struct vm_area_struct *); void unlink_anon_vmas(struct vm_area_struct *); int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); +static inline int anon_vma_prepare(struct vm_area_struct *vma) +{ + if (likely(vma->anon_vma)) + return 0; + + return __anon_vma_prepare(vma); +} + static inline void anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) { -- cgit From 8e8780a547d987b6465c9458402177fe706c5624 Mon Sep 17 00:00:00 2001 From: Benjamin Peterson Date: Mon, 12 Dec 2016 16:45:38 -0800 Subject: compiler-gcc.h: use "proved" instead of "proofed" Link: http://lkml.kernel.org/r/1477894241.1103202.772260161.1B0A5995@webmail.messagingengine.com Signed-off-by: Benjamin Peterson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 928e5ca0caee..0444b1336268 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -21,7 +21,7 @@ * clobbered. The issue is as follows: while the inline asm might * access any memory it wants, the compiler could have fit all of * @ptr into memory registers instead, and since @ptr never escaped - * from that, it proofed that the inline asm wasn't touching any of + * from that, it proved that the inline asm wasn't touching any of * it. This version works well with both compilers, i.e. we're telling * the compiler that the inline asm absolutely may see the contents * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 -- cgit From 497957576cf8a2150d723aedd74ea60b5d498bfe Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Mon, 12 Dec 2016 16:45:47 -0800 Subject: printk/kdb: handle more message headers Commit 4bcc595ccd80 ("printk: reinstate KERN_CONT for printing continuation lines") allows to define more message headers for a single message. The motivation is that continuous lines might get mixed. Therefore it make sense to define the right log level for every piece of a cont line. This patch introduces printk_skip_headers() that will skip all headers and uses it in the kdb code instead of printk_skip_level(). This approach helps to fix other printk_skip_level() users independently. Link: http://lkml.kernel.org/r/1478695291-12169-3-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek Cc: Joe Perches Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Jason Wessel Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index eac1af8502bb..a0859e169bc3 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -31,6 +31,14 @@ static inline const char *printk_skip_level(const char *buffer) return buffer; } +static inline const char *printk_skip_headers(const char *buffer) +{ + while (printk_get_level(buffer)) + buffer = printk_skip_level(buffer); + + return buffer; +} + #define CONSOLE_EXT_LOG_MAX 8192 /* printk's without a loglevel use this.. */ -- cgit From 262c5e86fec7cfd59754732001a9ff5b13eba501 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Mon, 12 Dec 2016 16:45:50 -0800 Subject: printk/btrfs: handle more message headers Commit 4bcc595ccd80 ("printk: reinstate KERN_CONT for printing continuation lines") allows to define more message headers for a single message. The motivation is that continuous lines might get mixed. Therefore it make sense to define the right log level for every piece of a cont line. The current btrfs_printk() macros do not support continuous lines at the moment. But better be prepared for a custom messages and avoid potential "lvl" buffer overflow. This patch iterates over the entire message header. It is interested only into the message level like the original code. This patch also introduces PRINTK_MAX_SINGLE_HEADER_LEN. Three bytes are enough for the message level header at the moment. But it used to be three, see the commit 04d2c8c83d0e ("printk: convert the format for KERN_ to a 2 byte pattern"). Also I fixed the default ratelimit level. It looked very strange when it was different from the default log level. [pmladek@suse.com: Fix a check of the valid message level] Link: http://lkml.kernel.org/r/20161111183236.GD2145@dhcp128.suse.cz Link: http://lkml.kernel.org/r/1478695291-12169-4-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek Acked-by: David Sterba Cc: Joe Perches Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Jason Wessel Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Chris Mason Cc: Josef Bacik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index a0859e169bc3..afe8ccec1672 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -10,6 +10,8 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; +#define PRINTK_MAX_SINGLE_HEADER_LEN 2 + static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { -- cgit From a8cfdc68f6cfc0c7ffc6d664406fe7f06f17eef4 Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Mon, 12 Dec 2016 16:45:56 -0800 Subject: printk: add Kconfig option to set default console loglevel Add a configuration option to set the default console loglevel. This is, as before, still possible to override at runtime through bootargs (loglevel=), sysrq and /proc/printk. There are cases where adding additional arguments on the commandline is impractical, and changing the default for the kernel when being built makes more sense. Provide such a method here, for those who choose to do so. Also, while touching this code, clarify the difference between MESSAGE_LOGLEVEL_DEFAULT and CONSOLE_LOGLEVEL_DEFAULT. Link: http://lkml.kernel.org/r/1479676829-30031-1-git-send-email-olof@lixom.net Signed-off-by: Olof Johansson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index afe8ccec1672..3472cc6b7a60 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -50,10 +50,15 @@ static inline const char *printk_skip_headers(const char *buffer) #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ #define CONSOLE_LOGLEVEL_QUIET 4 /* Shhh ..., when booted with "quiet" */ -#define CONSOLE_LOGLEVEL_DEFAULT 7 /* anything MORE serious than KERN_DEBUG */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ +/* + * Default used to be hard-coded at 7, we're now allowing it to be set from + * kernel config. + */ +#define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT + extern int console_printk[]; #define console_loglevel (console_printk[0]) -- cgit From c226dc22ec4904340e3e14a536983cda3dbe7914 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 31 Oct 2016 12:15:20 +0200 Subject: net/mlx5: Report multi packet WQE capabilities Multi packet WQE enables sending multiple fix sized packets using a single WQE. The exposed field reports such HW support. Signed-off-by: Bodong Wang Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2632cb2caf10..0779ad2e8f51 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -576,7 +576,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 self_lb_en_modifiable[0x1]; u8 reserved_at_9[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_at_10[0x2]; + u8 multi_pkt_send_wqe[0x2]; u8 wqe_inline_mode[0x2]; u8 rss_ind_tbl_cap[0x4]; u8 reg_umr_sq[0x1]; -- cgit From 0184cfe72d2f139c4feed7f3820ba2269f5de322 Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Fri, 21 Oct 2016 04:57:27 +0200 Subject: crypto: doc - fix source comments for Sphinx Update comments to avoid any complaints from Sphinx during compilation. Signed-off-by: Stephan Mueller Signed-off-by: Jonathan Corbet --- include/linux/crypto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 7cee5551625b..faf8127234e1 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -960,7 +960,7 @@ static inline void ablkcipher_request_free(struct ablkcipher_request *req) * ablkcipher_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags - * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and + * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle @@ -977,7 +977,7 @@ static inline void ablkcipher_request_free(struct ablkcipher_request *req) * cipher operation completes. * * The callback function is registered with the ablkcipher_request handle and - * must comply with the following template + * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ -- cgit From 74dcba3589fc184c7118905eda22b3a4aaef95ff Mon Sep 17 00:00:00 2001 From: Aaron Sierra Date: Tue, 6 Dec 2016 19:09:16 -0600 Subject: NTB: correct ntb_spad_count comment typo The comment for ntb_spad_count incorrectly referred to ntb_mw_count. Signed-off-by: Aaron Sierra Acked-by: Allen Hubbe Signed-off-by: Jiri Kosina --- include/linux/ntb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 6f47562d477b..50a7dbe88cf3 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -896,7 +896,7 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) } /** - * ntb_mw_count() - get the number of scratchpads + * ntb_spad_count() - get the number of scratchpads * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. -- cgit From e28d2af43614eb86f59812e7221735fc221bbc10 Mon Sep 17 00:00:00 2001 From: Ingo Tuchscherer Date: Thu, 25 Aug 2016 11:16:03 +0200 Subject: s390/zcrypt: add multi domain support Currently the ap infrastructure only supports one domain at a time. This feature extends the generic cryptographic device driver to support multiple cryptographic domains simultaneously. There are now card and queue devices on the AP bus with independent card and queue drivers. The new /sys layout is as follows: /sys/bus/ap devices . -> ../../../devices/ap/card/. ... card -> ../../../devices/ap/card ... drivers card card -> ../../../../devices/ap/card queue . -> ../../../../devices/ap/card/. ... /sys/devices/ap card . driver -> ../../../../bus/ap/drivers/queue ... driver -> ../../../bus/ap/drivers/card ... The two digit field is the card number, the four digit field is the queue number and is the name of the device driver, e.g. "cex4". For compatability /sys/bus/ap/card for the old layout has to exist, including the attributes that used to reside there. With additional contributions from Harald Freudenberger and Martin Schwidefsky. Signed-off-by: Ingo Tuchscherer Signed-off-by: Martin Schwidefsky --- include/linux/mod_devicetable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index ed84c07f6a51..8a57f0b1242d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -175,7 +175,8 @@ struct ap_device_id { kernel_ulong_t driver_info; }; -#define AP_DEVICE_ID_MATCH_DEVICE_TYPE 0x01 +#define AP_DEVICE_ID_MATCH_CARD_TYPE 0x01 +#define AP_DEVICE_ID_MATCH_QUEUE_TYPE 0x02 /* s390 css bus devices (subchannels) */ struct css_device_id { -- cgit From c297eb42690b904fb5b78dd9ad001bafe25f49ec Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 2 Dec 2016 14:01:55 +0100 Subject: libceph: always signal completion when done r_safe_completion is currently, and has always been, signaled only if on-disk ack was requested. It's there for fsync and syncfs, which wait for in-flight writes to flush - all data write requests set ONDISK. However, the pool perm check code introduced in 4.2 sends a write request with only ACK set. An unfortunately timed syncfs can then hang forever: r_safe_completion won't be signaled because only an unsafe reply was requested. We could patch ceph_osdc_sync() to skip !ONDISK write requests, but that is somewhat incomplete and yet another special case. Instead, rename this completion to r_done_completion and always signal it when the OSD client is done with the request, whether unsafe, safe, or error. This is a bit cleaner and helps with the cancellation code. Reported-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a8e66344bacc..03a6653d329a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -176,7 +176,7 @@ struct ceph_osd_request { struct kref r_kref; bool r_mempool; struct completion r_completion; - struct completion r_safe_completion; /* fsync waiter */ + struct completion r_done_completion; /* fsync waiter */ ceph_osdc_callback_t r_callback; ceph_osdc_unsafe_callback_t r_unsafe_callback; struct list_head r_unsafe_item; -- cgit From c7be96af89d4b53211862d8599b2430e8900ed92 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 14 Dec 2016 15:04:10 -0800 Subject: signals: avoid unnecessary taking of sighand->siglock When running certain database workload on a high-end system with many CPUs, it was found that spinlock contention in the sigprocmask syscalls became a significant portion of the overall CPU cycles as shown below. 9.30% 9.30% 905387 dataserver /proc/kcore 0x7fff8163f4d2 [k] _raw_spin_lock_irq | ---_raw_spin_lock_irq | |--99.34%-- __set_current_blocked | sigprocmask | sys_rt_sigprocmask | system_call_fastpath | | | |--50.63%-- __swapcontext | | | | | |--99.91%-- upsleepgeneric | | | |--49.36%-- __setcontext | | ktskRun Looking further into the swapcontext function in glibc, it was found that the function always call sigprocmask() without checking if there are changes in the signal mask. A check was added to the __set_current_blocked() function to avoid taking the sighand->siglock spinlock if there is no change in the signal mask. This will prevent unneeded spinlock contention when many threads are trying to call sigprocmask(). With this patch applied, the spinlock contention in sigprocmask() was gone. Link: http://lkml.kernel.org/r/1474979209-11867-1-git-send-email-Waiman.Long@hpe.com Signed-off-by: Waiman Long Acked-by: Oleg Nesterov Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Stas Sergeev Cc: Scott J Norton Cc: Douglas Hatch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index b63f63eaa39c..5308304993be 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -97,6 +97,23 @@ static inline int sigisemptyset(sigset_t *set) } } +static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) +{ + switch (_NSIG_WORDS) { + case 4: + return (set1->sig[3] == set2->sig[3]) && + (set1->sig[2] == set2->sig[2]) && + (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 2: + return (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 1: + return set1->sig[0] == set2->sig[0]; + } + return 0; +} + #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS -- cgit From 69f58384791ac6da4165ce8e6defd6f408f4afdf Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 14 Dec 2016 15:04:16 -0800 Subject: Revert "kdump, vmcoreinfo: report memory sections virtual addresses" This reverts commit 0549a3c02efb ("kdump, vmcoreinfo: report memory sections virtual addresses"). Commit 0549a3c02efb tells the userspace utility makedumpfile the randomized base address of these memmory sections when mm kaslr is enabled. However the following patch "kexec: export the value of phys_base instead of symbol address" makes makedumpfile not need these addresses any more. Besides we should use VMCOREINFO_NUMBER to export the value of the variable so that we can use the existing number_table mechanism of Makedumpfile to fetch it. So revert it now. If needed we can add it later. http://lists.infradead.org/pipermail/kexec/2016-October/017540.html Link: http://lkml.kernel.org/r/1478568596-30060-1-git-send-email-bhe@redhat.com Signed-off-by: Baoquan He Cc: Thomas Garnier Cc: Baoquan He Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Eric Biederman Cc: Xunlei Pang Cc: HATAYAMA Daisuke Cc: Kees Cook Cc: Eugene Surovegin Cc: Dave Young Cc: AKASHI Takahiro Cc: Atsushi Kumagai Cc: Dave Anderson Cc: Pratyush Anand Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 406c33dcae13..d7437777baaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -259,12 +259,6 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) -#define VMCOREINFO_PAGE_OFFSET(value) \ - vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value) -#define VMCOREINFO_VMALLOC_START(value) \ - vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value) -#define VMCOREINFO_VMEMMAP_START(value) \ - vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value) extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; -- cgit From 0495c3d367944e4af053983ff3cdf256b567b053 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:23 -0800 Subject: dma: add calls for dma_map_page_attrs and dma_unmap_page_attrs Add support for mapping and unmapping a page with attributes. The primary use for this is currently to allow for us to pass the DMA_ATTR_SKIP_CPU_SYNC attribute when mapping and unmapping a page. On some architectures such as ARM the synchronization has significant overhead and if we are already taking care of the sync_for_cpu and sync_for_device from the driver there isn't much need to handle this in the map/unmap calls as well. Link: http://lkml.kernel.org/r/20161110113601.76501.46095.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 08528afdf58b..10c5a17b1f51 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -243,29 +243,33 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg ops->unmap_sg(dev, sg, nents, dir, attrs); } -static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, - size_t offset, size_t size, - enum dma_data_direction dir) +static inline dma_addr_t dma_map_page_attrs(struct device *dev, + struct page *page, + size_t offset, size_t size, + enum dma_data_direction dir, + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; kmemcheck_mark_initialized(page_address(page) + offset, size); BUG_ON(!valid_dma_direction(dir)); - addr = ops->map_page(dev, page, offset, size, dir, 0); + addr = ops->map_page(dev, page, offset, size, dir, attrs); debug_dma_map_page(dev, page, offset, size, dir, addr, false); return addr; } -static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) +static inline void dma_unmap_page_attrs(struct device *dev, + dma_addr_t addr, size_t size, + enum dma_data_direction dir, + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) - ops->unmap_page(dev, addr, size, dir, 0); + ops->unmap_page(dev, addr, size, dir, attrs); debug_dma_unmap_page(dev, addr, size, dir, false); } @@ -385,6 +389,8 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0) +#define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0) +#define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0) extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size); -- cgit From 44fdffd70504c15b617686753dfdf9eb0ddf3729 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:26 -0800 Subject: mm: add support for releasing multiple instances of a page Add a function that allows us to batch free a page that has multiple references outstanding. Specifically this function can be used to drop a page being used in the page frag alloc cache. With this drivers can make use of functionality similar to the page frag alloc cache without having to do any workarounds for the fact that there is no function that frees multiple references. Link: http://lkml.kernel.org/r/20161110113606.76501.70752.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: "David S. Miller" Cc: "James E.J. Bottomley" Cc: Chris Metcalf Cc: David Howells Cc: Geert Uytterhoeven Cc: Hans-Christian Noren Egtvedt Cc: Helge Deller Cc: James Hogan Cc: Jeff Kirsher Cc: Jonas Bonn Cc: Keguang Zhang Cc: Ley Foon Tan Cc: Mark Salter Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Ralf Baechle Cc: Rich Felker Cc: Richard Kuo Cc: Russell King Cc: Steven Miao Cc: Tobias Klauser Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f8041f9de31e..4175dca4ac39 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -506,6 +506,8 @@ extern void free_hot_cold_page(struct page *page, bool cold); extern void free_hot_cold_page_list(struct list_head *list, bool cold); struct page_frag_cache; +extern void __page_frag_drain(struct page *page, unsigned int order, + unsigned int count); extern void *__alloc_page_frag(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void __free_page_frag(void *addr); -- cgit From d1bd8ead126668a2d6c42d97cc3664e95b3fa1dc Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 14 Dec 2016 15:05:52 -0800 Subject: kdb: remove unused kdb_event handling kdb_event state variable is only set but never checked in the kernel code. http://www.spinics.net/lists/kdb/msg01733.html suggests that this variable affected WARN_CONSOLE_UNLOCKED() in the original implementation. But this check never went upstream. The semantic is unclear and racy. The value is updated after the kdb_printf_lock is acquired and after it is released. It should be symmetric at minimum. The value should be manipulated either inside or outside the locked area. Fortunately, it seems that the original function is gone and we could simply remove the state variable. Link: http://lkml.kernel.org/r/1480412276-16690-2-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek Suggested-by: Daniel Thompson Cc: Jason Wessel Cc: Peter Zijlstra Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kdb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 410decacff8f..eb706188dc23 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -77,7 +77,6 @@ extern int kdb_poll_idx; * number whenever the kernel debugger is entered. */ extern int kdb_initial_cpu; -extern atomic_t kdb_event; /* Types and messages used for dynamically added kdb shell commands */ -- cgit From 34aaff40b42148b23dcde40152480e25c7d2d759 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 14 Dec 2016 15:05:58 -0800 Subject: kdb: call vkdb_printf() from vprintk_default() only when wanted kdb_trap_printk allows to pass normal printk() messages to kdb via vkdb_printk(). For example, it is used to get backtrace using the classic show_stack(), see kdb_show_stack(). vkdb_printf() tries to avoid a potential infinite loop by disabling the trap. But this approach is racy, for example: CPU1 CPU2 vkdb_printf() // assume that kdb_trap_printk == 0 saved_trap_printk = kdb_trap_printk; kdb_trap_printk = 0; kdb_show_stack() kdb_trap_printk++; Problem1: Now, a nested printk() on CPU0 calls vkdb_printf() even when it should have been disabled. It will not cause a deadlock but... // using the outdated saved value: 0 kdb_trap_printk = saved_trap_printk; kdb_trap_printk--; Problem2: Now, kdb_trap_printk == -1 and will stay like this. It means that all messages will get passed to kdb from now on. This patch removes the racy saved_trap_printk handling. Instead, the recursion is prevented by a check for the locked CPU. The solution is still kind of racy. A non-related printk(), from another process, might get trapped by vkdb_printf(). And the wanted printk() might not get trapped because kdb_printf_cpu is assigned. But this problem existed even with the original code. A proper solution would be to get_cpu() before setting kdb_trap_printk and trap messages only from this CPU. I am not sure if it is worth the effort, though. In fact, the race is very theoretical. When kdb is running any of the commands that use kdb_trap_printk there is a single active CPU and the other CPUs should be in a holding pen inside kgdb_cpu_enter(). The only time this is violated is when there is a timeout waiting for the other CPUs to report to the holding pen. Finally, note that the situation is a bit schizophrenic. vkdb_printf() explicitly allows recursion but only from KDB code that calls kdb_printf() directly. On the other hand, the generic printk() recursion is not allowed because it might cause an infinite loop. This is why we could not hide the decision inside vkdb_printf() easily. Link: http://lkml.kernel.org/r/1480412276-16690-4-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek Cc: Daniel Thompson Cc: Jason Wessel Cc: Peter Zijlstra Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index eb706188dc23..68bd88223417 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -161,6 +161,7 @@ enum kdb_msgsrc { }; extern int kdb_trap_printk; +extern int kdb_printf_cpu; extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list args); extern __printf(1, 2) int kdb_printf(const char *, ...); -- cgit From 249e52e35580fcfe5dad53a7dcd7c1252788749c Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 14 Dec 2016 15:06:21 -0800 Subject: kernel/watchdog.c: move shared definitions to nmi.h Patch series "Clean up watchdog handlers", v2. This is an attempt to cleanup watchdog handlers. Right now, kernel/watchdog.c implements both softlockup and hardlockup detectors. Softlockup code is generic. Hardlockup code is arch specific. Some architectures don't use hardlockup detectors. They use their own watchdog detectors. To make both these combination work, we have numerous #ifdefs in kernel/watchdog.c. We are trying here to make these handlers independent of each other. Also provide an interface for architectures to implement their own handlers. watchdog_nmi_enable and watchdog_nmi_disable will be defined as weak such that architectures can override its definitions. Thanks to Don Zickus for his suggestions. Here are our previous discussions http://www.spinics.net/lists/sparclinux/msg16543.html http://www.spinics.net/lists/sparclinux/msg16441.html This patch (of 3): Move shared macros and definitions to nmi.h so that watchdog.c, new file watchdog_hld.c or any other architecture specific handler can use those definitions. Link: http://lkml.kernel.org/r/1478034826-43888-2-git-send-email-babu.moger@oracle.com Signed-off-by: Babu Moger Acked-by: Don Zickus Cc: Ingo Molnar Cc: Jiri Kosina Cc: Andi Kleen Cc: Yaowei Bai Cc: Aaron Tomlin Cc: Ulrich Obergfell Cc: Tejun Heo Cc: Hidehiro Kawai Cc: Josh Hunt Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a78c35cff1ae..aacca824a6ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -7,6 +7,23 @@ #include #include +/* + * The run state of the lockup detectors is controlled by the content of the + * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - + * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. + * + * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' + * are variables that are only used as an 'interface' between the parameters + * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The + * 'watchdog_thresh' variable is handled differently because its value is not + * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' + * is equal zero. + */ +#define NMI_WATCHDOG_ENABLED_BIT 0 +#define SOFT_WATCHDOG_ENABLED_BIT 1 +#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) +#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -91,9 +108,16 @@ extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; +extern unsigned long watchdog_enabled; extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; +#else +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif +extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); -- cgit From 5b56d49fc31dbb0487e14ead790fc81ca9fb2c99 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 14 Dec 2016 15:06:52 -0800 Subject: mm: add locked parameter to get_user_pages_remote() Patch series "mm: unexport __get_user_pages_unlocked()". This patch series continues the cleanup of get_user_pages*() functions taking advantage of the fact we can now pass gup_flags as we please. It firstly adds an additional 'locked' parameter to get_user_pages_remote() to allow for its callers to utilise VM_FAULT_RETRY functionality. This is necessary as the invocation of __get_user_pages_unlocked() in process_vm_rw_single_vec() makes use of this and no other existing higher level function would allow it to do so. Secondly existing callers of __get_user_pages_unlocked() are replaced with the appropriate higher-level replacement - get_user_pages_unlocked() if the current task and memory descriptor are referenced, or get_user_pages_remote() if other task/memory descriptors are referenced (having acquiring mmap_sem.) This patch (of 2): Add a int *locked parameter to get_user_pages_remote() to allow VM_FAULT_RETRY faulting behaviour similar to get_user_pages_[un]locked(). Taking into account the previous adjustments to get_user_pages*() functions allowing for the passing of gup_flags, we are now in a position where __get_user_pages_unlocked() need only be exported for his ability to allow VM_FAULT_RETRY behaviour, this adjustment allows us to subsequently unexport __get_user_pages_unlocked() as well as allowing for future flexibility in the use of get_user_pages_remote(). [sfr@canb.auug.org.au: merge fix for get_user_pages_remote API change] Link: http://lkml.kernel.org/r/20161122210511.024ec341@canb.auug.org.au Link: http://lkml.kernel.org/r/20161027095141.2569-2-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Acked-by: Michal Hocko Cc: Jan Kara Cc: Hugh Dickins Cc: Dave Hansen Cc: Rik van Riel Cc: Mel Gorman Cc: Paolo Bonzini Cc: Radim Krcmar Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a92c8d73aeaf..cc154454675a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1274,7 +1274,7 @@ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); -- cgit From 8b7457ef9a9eb46cd1675d40d8e1fd3c47a38395 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 14 Dec 2016 15:06:55 -0800 Subject: mm: unexport __get_user_pages_unlocked() Unexport the low-level __get_user_pages_unlocked() function and replaces invocations with calls to more appropriate higher-level functions. In hva_to_pfn_slow() we are able to replace __get_user_pages_unlocked() with get_user_pages_unlocked() since we can now pass gup_flags. In async_pf_execute() and process_vm_rw_single_vec() we need to pass different tsk, mm arguments so get_user_pages_remote() is the sane replacement in these cases (having added manual acquisition and release of mmap_sem.) Additionally get_user_pages_remote() reintroduces use of the FOLL_TOUCH flag. However, this flag was originally silently dropped by commit 1e9877902dc7 ("mm/gup: Introduce get_user_pages_remote()"), so this appears to have been unintentional and reintroducing it is therefore not an issue. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20161027095141.2569-3-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Acked-by: Michal Hocko Cc: Jan Kara Cc: Hugh Dickins Cc: Dave Hansen Cc: Rik van Riel Cc: Mel Gorman Cc: Paolo Bonzini Cc: Radim Krcmar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cc154454675a..7b2d14ed3815 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1280,9 +1280,6 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); -long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, int write, -- cgit From 82b0f8c39a3869b6fd2a10e180a862248736ec6f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:06:58 -0800 Subject: mm: join struct fault_env and vm_fault Currently we have two different structures for passing fault information around - struct vm_fault and struct fault_env. DAX will need more information in struct vm_fault to handle its faults so the content of that structure would become event closer to fault_env. Furthermore it would need to generate struct fault_env to be able to call some of the generic functions. So at this point I don't think there's much use in keeping these two structures separate. Just embed into struct vm_fault all that is needed to use it for both purposes. Link: http://lkml.kernel.org/r/1479460644-25076-2-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Kirill A. Shutemov Cc: Ross Zwisler Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 10 +++++----- include/linux/mm.h | 28 +++++++++++----------------- include/linux/userfaultfd_k.h | 4 ++-- 3 files changed, 18 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1f782aa1d8e6..97e478d6b690 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,12 +1,12 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H -extern int do_huge_pmd_anonymous_page(struct fault_env *fe); +extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma); -extern void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd); -extern int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd); +extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); +extern int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -142,7 +142,7 @@ static inline int hpage_nr_pages(struct page *page) return 1; } -extern int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd); +extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; @@ -212,7 +212,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, return NULL; } -static inline int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd) +static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) { return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b2d14ed3815..de5bcead2511 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -292,10 +292,16 @@ extern pgprot_t protection_map[16]; * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { + struct vm_area_struct *vma; /* Target VMA */ unsigned int flags; /* FAULT_FLAG_xxx flags */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ - void __user *virtual_address; /* Faulting virtual address */ + unsigned long address; /* Faulting virtual address */ + void __user *virtual_address; /* Faulting virtual address masked by + * PAGE_MASK */ + pmd_t *pmd; /* Pointer to pmd entry matching + * the 'address' + */ struct page *cow_page; /* Handler may choose to COW */ struct page *page; /* ->fault handlers should return a @@ -309,19 +315,7 @@ struct vm_fault { * VM_FAULT_DAX_LOCKED and fill in * entry here. */ -}; - -/* - * Page fault context: passes though page fault handler instead of endless list - * of function arguments. - */ -struct fault_env { - struct vm_area_struct *vma; /* Target VMA */ - unsigned long address; /* Faulting virtual address */ - unsigned int flags; /* FAULT_FLAG_xxx flags */ - pmd_t *pmd; /* Pointer to pmd entry matching - * the 'address' - */ + /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. @@ -351,7 +345,7 @@ struct vm_operations_struct { int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); int (*pmd_fault)(struct vm_area_struct *, unsigned long address, pmd_t *, unsigned int flags); - void (*map_pages)(struct fault_env *fe, + void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); /* notification that a previously read-only page is about to become @@ -625,7 +619,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg, +int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); #endif @@ -2094,7 +2088,7 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); -extern void filemap_map_pages(struct fault_env *fe, +extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index dd66a952e8cd..11b92b047a1e 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -27,7 +27,7 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int handle_userfault(struct fault_env *fe, unsigned long reason); +extern int handle_userfault(struct vm_fault *vmf, unsigned long reason); extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len); @@ -55,7 +55,7 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) #else /* CONFIG_USERFAULTFD */ /* mm helpers */ -static inline int handle_userfault(struct fault_env *fe, unsigned long reason) +static inline int handle_userfault(struct vm_fault *vmf, unsigned long reason) { return VM_FAULT_SIGBUS; } -- cgit From 1a29d85eb0f19b7d8271923d8917d7b4f5540b3e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:01 -0800 Subject: mm: use vmf->address instead of of vmf->virtual_address Every single user of vmf->virtual_address typed that entry to unsigned long before doing anything with it so the type of virtual_address does not really provide us any additional safety. Just use masked vmf->address which already has the appropriate type. Link: http://lkml.kernel.org/r/1479460644-25076-3-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Kirill A. Shutemov Cc: Dan Williams Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index de5bcead2511..75fda0de64bf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -297,8 +297,6 @@ struct vm_fault { gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ - void __user *virtual_address; /* Faulting virtual address masked by - * PAGE_MASK */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ -- cgit From 2994302bc8a17180788fac66a47102d338d5d0ec Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:16 -0800 Subject: mm: add orig_pte field into vm_fault Add orig_pte field to vm_fault structure to allow ->page_mkwrite handlers to fully handle the fault. This also allows us to save some passing of extra arguments around. Link: http://lkml.kernel.org/r/1479460644-25076-8-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Ross Zwisler Acked-by: Kirill A. Shutemov Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 75fda0de64bf..39c17a2efcea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -298,8 +298,8 @@ struct vm_fault { pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ pmd_t *pmd; /* Pointer to pmd entry matching - * the 'address' - */ + * the 'address' */ + pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Handler may choose to COW */ struct page *page; /* ->fault handlers should return a -- cgit From 3917048d4572b9cabf6f8f5ad395eb693717367c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:18 -0800 Subject: mm: allow full handling of COW faults in ->fault handlers Patch series "dax: Clear dirty bits after flushing caches", v5. Patchset to clear dirty bits from radix tree of DAX inodes when caches for corresponding pfns have been flushed. In principle, these patches enable handlers to easily update PTEs and do other work necessary to finish the fault without duplicating the functionality present in the generic code. I'd like to thank Kirill and Ross for reviews of the series! This patch (of 20): To allow full handling of COW faults add memcg field to struct vm_fault and a return value of ->fault() handler meaning that COW fault is fully handled and memcg charge must not be canceled. This will allow us to remove knowledge about special DAX locking from the generic fault code. Link: http://lkml.kernel.org/r/1479460644-25076-9-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Ross Zwisler Acked-by: Kirill A. Shutemov Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 39c17a2efcea..6e25f4916d6f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -301,7 +301,8 @@ struct vm_fault { * the 'address' */ pte_t orig_pte; /* Value of PTE at the time of fault */ - struct page *cow_page; /* Handler may choose to COW */ + struct page *cow_page; /* Page handler may use for COW fault */ + struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -1103,6 +1104,7 @@ static inline void clear_page_pfmemalloc(struct page *page) #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ #define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */ +#define VM_FAULT_DONE_COW 0x2000 /* ->fault has fully handled COW */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -- cgit From 9118c0cbd44262d0015568266f314e645ed6b9ce Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:21 -0800 Subject: mm: factor out functionality to finish page faults Introduce finish_fault() as a helper function for finishing page faults. It is rather thin wrapper around alloc_set_pte() but since we'd want to call this from DAX code or filesystems, it is still useful to avoid some boilerplate code. Link: http://lkml.kernel.org/r/1479460644-25076-10-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Ross Zwisler Acked-by: Kirill A. Shutemov Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e25f4916d6f..60a230e6ece7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -620,6 +620,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); +int finish_fault(struct vm_fault *vmf); #endif /* -- cgit From b1aa812b21084285e9f6098639be9cd5bf9e05d7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:24 -0800 Subject: mm: move handling of COW faults into DAX code Move final handling of COW faults from generic code into DAX fault handler. That way generic code doesn't have to be aware of peculiarities of DAX locking so remove that knowledge and make locking functions private to fs/dax.c. Link: http://lkml.kernel.org/r/1479460644-25076-11-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Kirill A. Shutemov Reviewed-by: Ross Zwisler Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 7 ------- include/linux/mm.h | 9 +-------- 2 files changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 0afade8bd3d7..f97bcfe79472 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -46,7 +46,6 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping, #ifdef CONFIG_FS_DAX struct page *read_dax_sector(struct block_device *bdev, sector_t n); -void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index); int __dax_zero_page_range(struct block_device *bdev, sector_t sector, unsigned int offset, unsigned int length); #else @@ -55,12 +54,6 @@ static inline struct page *read_dax_sector(struct block_device *bdev, { return ERR_PTR(-ENXIO); } -/* Shouldn't ever be called when dax is disabled. */ -static inline void dax_unlock_mapping_entry(struct address_space *mapping, - pgoff_t index) -{ - BUG(); -} static inline int __dax_zero_page_range(struct block_device *bdev, sector_t sector, unsigned int offset, unsigned int length) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 60a230e6ece7..59a4da1742e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -308,12 +308,6 @@ struct vm_fault { * is set (which is also implied by * VM_FAULT_ERROR). */ - void *entry; /* ->fault handler can alternatively - * return locked DAX entry. In that - * case handler should return - * VM_FAULT_DAX_LOCKED and fill in - * entry here. - */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page @@ -1104,8 +1098,7 @@ static inline void clear_page_pfmemalloc(struct page *page) #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ -#define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */ -#define VM_FAULT_DONE_COW 0x2000 /* ->fault has fully handled COW */ +#define VM_FAULT_DONE_COW 0x1000 /* ->fault has fully handled COW */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -- cgit From 66a6197c118540d454913eef24d68d7491ab5d5f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:39 -0800 Subject: mm: provide helper for finishing mkwrite faults Provide a helper function for finishing write faults due to PTE being read-only. The helper will be used by DAX to avoid the need of complicating generic MM code with DAX locking specifics. Link: http://lkml.kernel.org/r/1479460644-25076-16-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Ross Zwisler Acked-by: Kirill A. Shutemov Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 59a4da1742e5..cec967e93f95 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -615,6 +615,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); int finish_fault(struct vm_fault *vmf); +int finish_mkwrite_fault(struct vm_fault *vmf); #endif /* -- cgit From cae1240257d9ba4b40eb240124c530de8ee349bc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:45 -0800 Subject: mm: export follow_pte() DAX will need to implement its own version of page_check_address(). To avoid duplicating page table walking code, export follow_pte() which does what we need. Link: http://lkml.kernel.org/r/1479460644-25076-18-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Ross Zwisler Cc: Kirill A. Shutemov Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cec967e93f95..63926492c06a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1210,6 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, + spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, -- cgit From 91d9c05ac6c788531136888d31ef18c6a0ec160f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:08:34 -0800 Subject: radix-tree: move rcu_head into a union with private_list I want to be able to reference node->parent after freeing node. Currently node->parent is in a union with rcu_head, so it is overwritten when the node is put on the RCU list. We know that private_list is not referenced after the node is freed, so it is safe for these two members to share space. Link: http://lkml.kernel.org/r/1480369871-5271-50-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 744486057e9e..d04073ac3a9f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -85,18 +85,12 @@ struct radix_tree_node { unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char exceptional; /* Exceptional entry count */ + struct radix_tree_node *parent; /* Used when ascending tree */ + void *private_data; /* For tree user */ union { - struct { - /* Used when ascending tree */ - struct radix_tree_node *parent; - /* For tree user */ - void *private_data; - }; - /* Used when freeing node */ - struct rcu_head rcu_head; + struct list_head private_list; /* For tree user */ + struct rcu_head rcu_head; /* Used when freeing node */ }; - /* For tree user */ - struct list_head private_list; void __rcu *slots[RADIX_TREE_MAP_SIZE]; unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -- cgit From 148deab223b23734069abcacb5c7118b0e7deadc Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:08:49 -0800 Subject: radix-tree: improve multiorder iterators This fixes several interlinked problems with the iterators in the presence of multiorder entries. 1. radix_tree_iter_next() would only advance by one slot, which would result in the iterators returning the same entry more than once if there were sibling entries. 2. radix_tree_next_slot() could return an internal pointer instead of a user pointer if a tagged multiorder entry was immediately followed by an entry of lower order. 3. radix_tree_next_slot() expanded to a lot more code than it used to when multiorder support was compiled in. And I wasn't comfortable with entry_to_node() being in a header file. Fixing radix_tree_iter_next() for the presence of sibling entries necessarily involves examining the contents of the radix tree, so we now need to pass 'slot' to radix_tree_iter_next(), and we need to change the calling convention so it is called *before* dropping the lock which protects the tree. Also rename it to radix_tree_iter_resume(), as some people thought it was necessary to call radix_tree_iter_next() each time around the loop. radix_tree_next_slot() becomes closer to how it looked before multiorder support was introduced. It only checks to see if the next entry in the chunk is a sibling entry or a pointer to a node; this should be rare enough that handling this case out of line is not a performance impact (and such impact is amortised by the fact that the entry we just processed was a multiorder entry). Also, radix_tree_next_slot() used to force a new chunk lookup for untagged entries, which is more expensive than the out of line sibling entry skipping. Link: http://lkml.kernel.org/r/1480369871-5271-55-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 71 ++++++++++++++++++++-------------------------- 1 file changed, 30 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index d04073ac3a9f..289d007d487b 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -403,20 +403,17 @@ __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) } /** - * radix_tree_iter_next - resume iterating when the chunk may be invalid - * @iter: iterator state + * radix_tree_iter_resume - resume iterating when the chunk may be invalid + * @slot: pointer to current slot + * @iter: iterator state + * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function - * to continue the iteration from the next index. + * before releasing the lock to continue the iteration from the next index. */ -static inline __must_check -void **radix_tree_iter_next(struct radix_tree_iter *iter) -{ - iter->next_index = __radix_tree_iter_add(iter, 1); - iter->tags = 0; - return NULL; -} +void **__must_check radix_tree_iter_resume(void **slot, + struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size @@ -430,10 +427,17 @@ radix_tree_chunk_size(struct radix_tree_iter *iter) return (iter->next_index - iter->index) >> iter_shift(iter); } -static inline struct radix_tree_node *entry_to_node(void *ptr) +#ifdef CONFIG_RADIX_TREE_MULTIORDER +void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, + unsigned flags); +#else +/* Can't happen without sibling entries, but the compiler can't tell that */ +static inline void ** __radix_tree_next_slot(void **slot, + struct radix_tree_iter *iter, unsigned flags) { - return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); + return slot; } +#endif /** * radix_tree_next_slot - find next slot in chunk @@ -447,7 +451,7 @@ static inline struct radix_tree_node *entry_to_node(void *ptr) * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this - * function. These cases result from the use of radix_tree_iter_next() or + * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or @@ -458,51 +462,31 @@ static __always_inline void ** radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { - void *canon = slot; - iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; - while (IS_ENABLED(CONFIG_RADIX_TREE_MULTIORDER) && - radix_tree_is_internal_node(slot[1])) { - if (entry_to_node(slot[1]) == canon) { - iter->tags >>= 1; - iter->index = __radix_tree_iter_add(iter, 1); - slot++; - continue; - } - iter->next_index = __radix_tree_iter_add(iter, 1); - return NULL; - } if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); - return slot + 1; + slot++; + goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); - iter->tags >>= offset; - iter->index = __radix_tree_iter_add(iter, offset + 1); - return slot + offset + 1; + iter->tags >>= offset++; + iter->index = __radix_tree_iter_add(iter, offset); + slot += offset; + goto found; } } else { long count = radix_tree_chunk_size(iter); - void *canon = slot; while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); - if (IS_ENABLED(CONFIG_RADIX_TREE_MULTIORDER) && - radix_tree_is_internal_node(*slot)) { - if (entry_to_node(*slot) == canon) - continue; - iter->next_index = iter->index; - break; - } - if (likely(*slot)) - return slot; + goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; @@ -511,6 +495,11 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) } } return NULL; + + found: + if (unlikely(radix_tree_is_internal_node(*slot))) + return __radix_tree_next_slot(slot, iter, flags); + return slot; } /** @@ -561,6 +550,6 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ - RADIX_TREE_ITER_TAGGED)) + RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_H */ -- cgit From 478922e2b0f41567e4a530771bfb3f693f857d45 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:08:52 -0800 Subject: radix-tree: delete radix_tree_locate_item() This rather complicated function can be better implemented as an iterator. It has only one caller, so move the functionality to the only place that needs it. Update the test suite to follow the same pattern. Link: http://lkml.kernel.org/r/1480369871-5271-56-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Acked-by: Konstantin Khlebnikov Tested-by: Kirill A. Shutemov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 289d007d487b..a13d3f7c6c65 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -296,7 +296,6 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, unsigned long nr_to_tag, unsigned int fromtag, unsigned int totag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); -unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item); static inline void radix_tree_preload_end(void) { -- cgit From 268f42de718128cd0301293177e79c08c38e39a6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:08:55 -0800 Subject: radix-tree: delete radix_tree_range_tag_if_tagged() This is an exceptionally complicated function with just one caller (tag_pages_for_writeback). We devote a large portion of the runtime of the test suite to testing this one function which has one caller. By introducing the new function radix_tree_iter_tag_set(), we can eliminate all of the complexity while keeping the performance. The caller can now use a fairly standard radix_tree_for_each() loop, and it doesn't need to worry about tricksy things like 'start' wrapping. The test suite continues to spend a large amount of time investigating this function, but now it's testing the underlying primitives such as radix_tree_iter_resume() and the radix_tree_for_each_tagged() iterator which are also used by other parts of the kernel. Link: http://lkml.kernel.org/r/1480369871-5271-57-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 74 +++++++++++++++++++++++----------------------- 1 file changed, 37 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index a13d3f7c6c65..7a8d2516c73a 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -120,6 +120,41 @@ static inline bool radix_tree_empty(struct radix_tree_root *root) return root->rnode == NULL; } +/** + * struct radix_tree_iter - radix tree iterator state + * + * @index: index of current slot + * @next_index: one beyond the last index for this chunk + * @tags: bit-mask for tag-iterating + * @node: node that contains current slot + * @shift: shift for the node that holds our slots + * + * This radix tree iterator works in terms of "chunks" of slots. A chunk is a + * subinterval of slots contained within one radix tree leaf node. It is + * described by a pointer to its first slot and a struct radix_tree_iter + * which holds the chunk's position in the tree and its size. For tagged + * iteration radix_tree_iter also holds the slots' bit-mask for one chosen + * radix tree tag. + */ +struct radix_tree_iter { + unsigned long index; + unsigned long next_index; + unsigned long tags; + struct radix_tree_node *node; +#ifdef CONFIG_RADIX_TREE_MULTIORDER + unsigned int shift; +#endif +}; + +static inline unsigned int iter_shift(const struct radix_tree_iter *iter) +{ +#ifdef CONFIG_RADIX_TREE_MULTIORDER + return iter->shift; +#else + return 0; +#endif +} + /** * Radix-tree synchronization * @@ -283,6 +318,8 @@ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag); int radix_tree_tag_get(struct radix_tree_root *root, unsigned long index, unsigned int tag); +void radix_tree_iter_tag_set(struct radix_tree_root *root, + const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, @@ -291,10 +328,6 @@ unsigned int radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); -unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, - unsigned long *first_indexp, unsigned long last_index, - unsigned long nr_to_tag, - unsigned int fromtag, unsigned int totag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); static inline void radix_tree_preload_end(void) @@ -302,39 +335,6 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } -/** - * struct radix_tree_iter - radix tree iterator state - * - * @index: index of current slot - * @next_index: one beyond the last index for this chunk - * @tags: bit-mask for tag-iterating - * @shift: shift for the node that holds our slots - * - * This radix tree iterator works in terms of "chunks" of slots. A chunk is a - * subinterval of slots contained within one radix tree leaf node. It is - * described by a pointer to its first slot and a struct radix_tree_iter - * which holds the chunk's position in the tree and its size. For tagged - * iteration radix_tree_iter also holds the slots' bit-mask for one chosen - * radix tree tag. - */ -struct radix_tree_iter { - unsigned long index; - unsigned long next_index; - unsigned long tags; -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned int shift; -#endif -}; - -static inline unsigned int iter_shift(struct radix_tree_iter *iter) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - return iter->shift; -#else - return 0; -#endif -} - #define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */ #define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */ #define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */ -- cgit From 175542f575723e43f897ddb09d0011c13f7cf0ec Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:08:58 -0800 Subject: radix-tree: add radix_tree_join This new function allows for the replacement of many smaller entries in the radix tree with one larger multiorder entry. From the point of view of an RCU walker, they may see a mixture of the smaller entries and the large entry during the same walk, but they will never see NULL for an index which was populated before the join. Link: http://lkml.kernel.org/r/1480369871-5271-58-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7a8d2516c73a..935293a24f7d 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -335,6 +335,9 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } +int radix_tree_join(struct radix_tree_root *, unsigned long index, + unsigned new_order, void *); + #define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */ #define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */ #define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */ -- cgit From e157b555945fb16ddc6cce605a1eb6b4135ea5f1 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:09:01 -0800 Subject: radix-tree: add radix_tree_split This new function splits a larger multiorder entry into smaller entries (potentially multi-order entries). These entries are initialised to RADIX_TREE_RETRY to ensure that RCU walkers who see this state aren't confused. The caller should then call radix_tree_for_each_slot() and radix_tree_replace_slot() in order to turn these retry entries into the intended new entries. Tags are replicated from the original multiorder entry into each new entry. Link: http://lkml.kernel.org/r/1480369871-5271-59-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 935293a24f7d..1f4b56120de8 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -80,6 +80,14 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) +/* + * @count is the count of every non-NULL element in the ->slots array + * whether that is an exceptional entry, a retry entry, a user pointer, + * a sibling entry or a pointer to the next level of the tree. + * @exceptional is the count of every element in ->slots which is + * either radix_tree_exceptional_entry() or is a sibling entry for an + * exceptional entry. + */ struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ @@ -293,6 +301,8 @@ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void **slot, void *item, radix_tree_update_node_t update_node, void *private); +void radix_tree_iter_replace(struct radix_tree_root *, + const struct radix_tree_iter *, void **slot, void *item); void radix_tree_replace_slot(struct radix_tree_root *root, void **slot, void *item); void __radix_tree_delete_node(struct radix_tree_root *root, @@ -335,6 +345,8 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } +int radix_tree_split(struct radix_tree_root *, unsigned long index, + unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); -- cgit From 2791653a6814d170fa893344618563a7b1da95c6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:09:04 -0800 Subject: radix-tree: add radix_tree_split_preload() Calculate how many nodes we need to allocate to split an old_order entry into multiple entries, each of size new_order. The test suite checks that we allocated exactly the right number of nodes; neither too many (checked by rtp->nr == 0), nor too few (checked by comparing nr_allocated before and after the call to radix_tree_split()). Link: http://lkml.kernel.org/r/1480369871-5271-60-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 1f4b56120de8..5dea8f6440e4 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -345,6 +345,7 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } +int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, -- cgit From 99c494077e2d4282a17120a772eecc00ec3004cc Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:09:13 -0800 Subject: idr: add ida_is_empty Two of the USB Gadgets were poking around in the internals of struct ida in order to determine if it is empty. Add the appropriate abstraction. Link: http://lkml.kernel.org/r/1480369871-5271-63-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Acked-by: Konstantin Khlebnikov Tested-by: Kirill A. Shutemov Cc: Ross Zwisler Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Michal Nazarewicz Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 083d61e92706..3639a28188c9 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -195,6 +195,11 @@ static inline int ida_get_new(struct ida *ida, int *p_id) return ida_get_new_above(ida, 0, p_id); } +static inline bool ida_is_empty(struct ida *ida) +{ + return idr_is_empty(&ida->idr); +} + void __init idr_init_cache(void); #endif /* __IDR_H__ */ -- cgit From 444306129a920015a2cc876d13fcbf52382f39bd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:09:19 -0800 Subject: rxrpc: abstract away knowledge of IDR internals Add idr_get_cursor() / idr_set_cursor() APIs, and remove the reference to IDR_SIZE. Link: http://lkml.kernel.org/r/1480369871-5271-65-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Reviewed-by: David Howells Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3639a28188c9..1eb755f77f2f 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -55,6 +55,32 @@ struct idr { } #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) +/** + * idr_get_cursor - Return the current position of the cyclic allocator + * @idr: idr handle + * + * The value returned is the value that will be next returned from + * idr_alloc_cyclic() if it is free (otherwise the search will start from + * this position). + */ +static inline unsigned int idr_get_cursor(struct idr *idr) +{ + return READ_ONCE(idr->cur); +} + +/** + * idr_set_cursor - Set the current position of the cyclic allocator + * @idr: idr handle + * @val: new position + * + * The next call to idr_alloc_cyclic() will return @val if it is free + * (otherwise the search will start from this position). + */ +static inline void idr_set_cursor(struct idr *idr, unsigned int val) +{ + WRITE_ONCE(idr->cur, val); +} + /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) -- cgit From 424251a4a929a1b6dff2056d49135e3805132e32 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 14 Dec 2016 15:09:22 -0800 Subject: idr: reduce the number of bits per level from 8 to 6 In preparation for merging the IDR and radix tree, reduce the fanout at each level from 256 to 64. If this causes a performance problem then a bisect will point to this commit, and we'll have a better idea about what we might do to fix it. Link: http://lkml.kernel.org/r/1480369871-5271-66-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox Tested-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 1eb755f77f2f..3c01b89aed67 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -18,12 +18,11 @@ #include /* - * We want shallower trees and thus more bits covered at each layer. 8 - * bits gives us large enough first layer for most use cases and maximum - * tree depth of 4. Each idr_layer is slightly larger than 2k on 64bit and - * 1k on 32bit. + * Using 6 bits at each layer allows us to allocate 7 layers out of each page. + * 8 bits only gave us 3 layers out of every pair of pages, which is less + * efficient except for trees with a largest element between 192-255 inclusive. */ -#define IDR_BITS 8 +#define IDR_BITS 6 #define IDR_SIZE (1 << IDR_BITS) #define IDR_MASK ((1 << IDR_BITS)-1) -- cgit From 427d77a32365d5f942d335248305a5c237baf63a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Dec 2016 19:32:28 +0100 Subject: x86/smpboot: Prevent false positive out of bounds cpumask access warning prefill_possible_map() reinitializes the cpu_possible_map by setting the possible cpu bits and clearing all other bits up to NR_CPUS. This is technically always correct because cpu_possible_map is statically allocated and sized NR_CPUS. With CPUMASK_OFFSTACK and DEBUG_PER_CPU_MAPS enabled the bounds check of cpu masks happens on nr_cpu_ids. nr_cpu_ids is initialized to NR_CPUS and only limited after the set/clear bit loops have been executed. But if the system was booted with "nr_cpus=N" on the command line, where N is < NR_CPUS then nr_cpu_ids is limited in the parameter parsing function before prefill_possible_map() is invoked. As a consequence the cpumask bounds check triggers when clearing the bits past nr_cpu_ids. Add a helper which allows to reset cpu_possible_map w/o the bounds check and then set only the possible bits which are well inside bounds. Reported-by: Dmitry Safonov Cc: Rusty Russell Cc: 0x7f454c46@gmail.com Cc: Jan Beulich Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1612131836050.3415@nanos Signed-off-by: Thomas Gleixner --- include/linux/cpumask.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index da7fbf1cdd56..c717f5ea88cb 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -722,6 +722,11 @@ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); +static inline void reset_cpu_possible_mask(void) +{ + bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); +} + static inline void set_cpu_possible(unsigned int cpu, bool possible) { -- cgit From 0b892c717714334890ea179a2dc1941a223e446f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 09:56:00 -0200 Subject: edac: move EDAC PCI definitions to drivers/edac/edac_pci.h The edac_core.h header contain data structures and function definitions for the 3 parts of EDAC: MC, PCI and device. Let's move the PCI ones to a separate header file, as part of a header reorganization. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index cb56dcba68c6..0fec0f26469b 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -18,6 +18,8 @@ #include #include +#define EDAC_DEVICE_NAME_LEN 31 + struct device; #define EDAC_OPSTATE_INVAL -1 -- cgit From e002075819d987dec3bf9fa3ca98ad19fa86ae0f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 28 Oct 2016 15:04:52 -0200 Subject: edac: fix kenel-doc markups at edac.h As this file was never added to the driver-api, the kernel-doc markups there were never tested. Some of them have issues. Fix them. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 0fec0f26469b..3c20d2d2686a 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -132,6 +132,8 @@ enum dev_type { * it for example, by re-trying the operation). * @HW_EVENT_ERR_FATAL: Fatal Error - Uncorrected error that could not * be recovered. + * @HW_EVENT_ERR_INFO: Informational - The CPER spec defines a forth + * type of error: informational logs. */ enum hw_event_mc_err_type { HW_EVENT_ERR_CORRECTED, @@ -162,7 +164,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * enum mem_type - memory types. For a more detailed reference, please see * http://en.wikipedia.org/wiki/DRAM * - * @MEM_EMPTY Empty csrow + * @MEM_EMPTY: Empty csrow * @MEM_RESERVED: Reserved csrow type * @MEM_UNKNOWN: Unknown csrow type * @MEM_FPM: FPM - Fast Page Mode, used on systems up to 1995. @@ -286,7 +288,7 @@ enum edac_type { /** * enum scrub_type - scrubbing capabilities - * @SCRUB_UNKNOWN Unknown if scrubber is available + * @SCRUB_UNKNOWN: Unknown if scrubber is available * @SCRUB_NONE: No scrubber * @SCRUB_SW_PROG: SW progressive (sequential) scrubbing * @SCRUB_SW_SRC: Software scrub only errors @@ -295,7 +297,7 @@ enum edac_type { * @SCRUB_HW_PROG: HW progressive (sequential) scrubbing * @SCRUB_HW_SRC: Hardware scrub only errors * @SCRUB_HW_PROG_SRC: Progressive hardware scrub from an error - * SCRUB_HW_TUNABLE: Hardware scrub frequency is tunable + * @SCRUB_HW_TUNABLE: Hardware scrub frequency is tunable */ enum scrub_type { SCRUB_UNKNOWN = 0, @@ -460,7 +462,7 @@ enum edac_mc_layer_type { /** * struct edac_mc_layer - describes the memory controller hierarchy - * @layer: layer type + * @type: layer type * @size: number of components per layer. For example, * if the channel layer has two channels, size = 2 * @is_virt_csrow: This layer is part of the "csrow" when old API @@ -483,24 +485,28 @@ struct edac_mc_layer { #define EDAC_MAX_LAYERS 3 /** - * EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer array - * for the element given by [layer0,layer1,layer2] position + * EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer + * array for the element given by [layer0,layer1,layer2] + * position * * @layers: a struct edac_mc_layer array, describing how many elements * were allocated for each layer - * @n_layers: Number of layers at the @layers array + * @nlayers: Number of layers at the @layers array * @layer0: layer0 position * @layer1: layer1 position. Unused if n_layers < 2 * @layer2: layer2 position. Unused if n_layers < 3 * - * For 1 layer, this macro returns &var[layer0] - &var + * For 1 layer, this macro returns "var[layer0] - var"; + * * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "&var[layer0][layer1] - &var" + * and to return "var[layer0][layer1] - var"; + * * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "&var[layer0][layer1][layer2] - &var" + * and to return "var[layer0][layer1][layer2] - var". * * A loop could be used here to make it more generic, but, as we only have * 3 layers, this is a little faster. + * * By design, layers can never be 0 or more than 3. If that ever happens, * a NULL is returned, causing an OOPS during the memory allocation routine, * with would point to the developer that he's doing something wrong. @@ -527,16 +533,18 @@ struct edac_mc_layer { * were allocated for each layer * @var: name of the var where we want to get the pointer * (like mci->dimms) - * @n_layers: Number of layers at the @layers array + * @nlayers: Number of layers at the @layers array * @layer0: layer0 position * @layer1: layer1 position. Unused if n_layers < 2 * @layer2: layer2 position. Unused if n_layers < 3 * - * For 1 layer, this macro returns &var[layer0] + * For 1 layer, this macro returns "var[layer0]"; + * * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "&var[layer0][layer1]" + * and to return "var[layer0][layer1]"; + * * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "&var[layer0][layer1][layer2]" + * and to return "var[layer0][layer1][layer2]"; */ #define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({ \ typeof(*var) __p; \ @@ -622,7 +630,7 @@ struct errcount_attribute_data { }; /** - * edac_raw_error_desc - Raw error report structure + * struct edac_raw_error_desc - Raw error report structure * @grain: minimum granularity for an error report, in bytes * @error_count: number of errors of the same type * @top_layer: top layer of the error (layer[0]) -- cgit From 6b1fb6f7037221981fb2cf1822c31b5fba1b9c22 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 16:13:23 -0200 Subject: edac.rst: move concepts dictionary from edac.h Instead of storing the concepts dictionary inside header file, move it to the subsystem documentation. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 108 --------------------------------------------------- 1 file changed, 108 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 3c20d2d2686a..c4433fd6c859 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -330,114 +330,6 @@ enum scrub_type { #define OP_RUNNING_POLL_INTR 0x203 #define OP_OFFLINE 0x300 -/* - * Concepts used at the EDAC subsystem - * - * There are several things to be aware of that aren't at all obvious: - * - * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc.. - * - * These are some of the many terms that are thrown about that don't always - * mean what people think they mean (Inconceivable!). In the interest of - * creating a common ground for discussion, terms and their definitions - * will be established. - * - * Memory devices: The individual DRAM chips on a memory stick. These - * devices commonly output 4 and 8 bits each (x4, x8). - * Grouping several of these in parallel provides the - * number of bits that the memory controller expects: - * typically 72 bits, in order to provide 64 bits + - * 8 bits of ECC data. - * - * Memory Stick: A printed circuit board that aggregates multiple - * memory devices in parallel. In general, this is the - * Field Replaceable Unit (FRU) which gets replaced, in - * the case of excessive errors. Most often it is also - * called DIMM (Dual Inline Memory Module). - * - * Memory Socket: A physical connector on the motherboard that accepts - * a single memory stick. Also called as "slot" on several - * datasheets. - * - * Channel: A memory controller channel, responsible to communicate - * with a group of DIMMs. Each channel has its own - * independent control (command) and data bus, and can - * be used independently or grouped with other channels. - * - * Branch: It is typically the highest hierarchy on a - * Fully-Buffered DIMM memory controller. - * Typically, it contains two channels. - * Two channels at the same branch can be used in single - * mode or in lockstep mode. - * When lockstep is enabled, the cacheline is doubled, - * but it generally brings some performance penalty. - * Also, it is generally not possible to point to just one - * memory stick when an error occurs, as the error - * correction code is calculated using two DIMMs instead - * of one. Due to that, it is capable of correcting more - * errors than on single mode. - * - * Single-channel: The data accessed by the memory controller is contained - * into one dimm only. E. g. if the data is 64 bits-wide, - * the data flows to the CPU using one 64 bits parallel - * access. - * Typically used with SDR, DDR, DDR2 and DDR3 memories. - * FB-DIMM and RAMBUS use a different concept for channel, - * so this concept doesn't apply there. - * - * Double-channel: The data size accessed by the memory controller is - * interlaced into two dimms, accessed at the same time. - * E. g. if the DIMM is 64 bits-wide (72 bits with ECC), - * the data flows to the CPU using a 128 bits parallel - * access. - * - * Chip-select row: This is the name of the DRAM signal used to select the - * DRAM ranks to be accessed. Common chip-select rows for - * single channel are 64 bits, for dual channel 128 bits. - * It may not be visible by the memory controller, as some - * DIMM types have a memory buffer that can hide direct - * access to it from the Memory Controller. - * - * Single-Ranked stick: A Single-ranked stick has 1 chip-select row of memory. - * Motherboards commonly drive two chip-select pins to - * a memory stick. A single-ranked stick, will occupy - * only one of those rows. The other will be unused. - * - * Double-Ranked stick: A double-ranked stick has two chip-select rows which - * access different sets of memory devices. The two - * rows cannot be accessed concurrently. - * - * Double-sided stick: DEPRECATED TERM, see Double-Ranked stick. - * A double-sided stick has two chip-select rows which - * access different sets of memory devices. The two - * rows cannot be accessed concurrently. "Double-sided" - * is irrespective of the memory devices being mounted - * on both sides of the memory stick. - * - * Socket set: All of the memory sticks that are required for - * a single memory access or all of the memory sticks - * spanned by a chip-select row. A single socket set - * has two chip-select rows and if double-sided sticks - * are used these will occupy those chip-select rows. - * - * Bank: This term is avoided because it is unclear when - * needing to distinguish between chip-select rows and - * socket sets. - * - * Controller pages: - * - * Physical pages: - * - * Virtual pages: - * - * - * STRUCTURE ORGANIZATION AND CHOICES - * - * - * - * PS - I enjoyed writing all that about as much as you enjoyed reading it. - */ - /** * enum edac_mc_layer - memory controller hierarchy layer * -- cgit From 4838a0def07f5611347860b1fc0129c3fe77cc02 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Thu, 1 Dec 2016 14:24:53 -0600 Subject: EDAC: Document HW_EVENT_ERR_DEFERRED type Add a description of the HW_EVENT_ERR_DEFERRED type that wasn't included with commit d12a969ebbfc ("EDAC, amd64: Add Deferred Error type"). Signed-off-by: Yazen Ghannam Acked-by: Borislav Petkov Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index c4433fd6c859..07c52c0af62d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -130,6 +130,12 @@ enum dev_type { * fatal (maybe it is on an unused memory area, * or the memory controller could recover from * it for example, by re-trying the operation). + * @HW_EVENT_ERR_DEFERRED: Deferred Error - Indicates an uncorrectable + * error whose handling is not urgent. This could + * be due to hardware data poisoning where the + * system can continue operation until the poisoned + * data is consumed. Preemptive measures may also + * be taken, e.g. offlining pages, etc. * @HW_EVENT_ERR_FATAL: Fatal Error - Uncorrected error that could not * be recovered. * @HW_EVENT_ERR_INFO: Informational - The CPER spec defines a forth -- cgit From 9bf11ecce5a2758e5a097c2f3a13d08552d0d6f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 15 Dec 2016 12:01:05 +0100 Subject: clocksource/dummy_timer: Move hotplug callback after the real timers When the dummy timer callback is invoked before the real timer callbacks, then it tries to install that timer for the starting CPU. If the platform does not have a broadcast timer installed the installation fails with a kernel crash. The crash happens due to a unconditional deference of the non available broadcast device. This needs to be fixed in the timer core code. But even when this is fixed in the core code then installing the dummy timer before the real timers is a pointless exercise. Move it to the end of the callback list. Fixes: 00c1d17aab51 ("clocksource/dummy_timer: Convert to hotplug state machine") Reported-and-tested-by: Mason Signed-off-by: Thomas Gleixner Cc: Mark Rutland Cc: Anna-Maria Gleixner Cc: Richard Cochran Cc: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Peter Zijlstra , Cc: Sebastian Frias Cc: Thibaud Cornic Cc: Robin Murphy Link: http://lkml.kernel.org/r/1147ef90-7877-e4d2-bb2b-5c4fa8d3144b@free.fr --- include/linux/cpuhotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 22acee76cf4c..2ab7bf53d529 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -101,7 +101,6 @@ enum cpuhp_state { CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, - CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_JCORE_TIMER_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, @@ -115,6 +114,8 @@ enum cpuhp_state { CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_KVM_ARM_TIMER_STARTING, + /* Must be the last timer callback */ + CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT4_STARTING, -- cgit From 9efeccacd3a486128d3add611dd4cefb5b60a58c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 11 Dec 2016 06:34:53 +0200 Subject: linux: drop __bitwise__ everywhere __bitwise__ used to mean "yes, please enable sparse checks unconditionally", but now that we dropped __CHECK_ENDIAN__ __bitwise is exactly the same. There aren't many users, replace it by __bitwise everywhere. Signed-off-by: Michael S. Tsirkin Acked-by: Greg Kroah-Hartman Acked-by: Stefan Schmidt Acked-by: Krzysztof Kozlowski Akced-by: Lee Duncan --- include/linux/mmzone.h | 2 +- include/linux/serial_core.h | 4 ++-- include/linux/types.h | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0f088f3a2fed..36d9896fbc1e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -246,7 +246,7 @@ struct lruvec { #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ -typedef unsigned __bitwise__ isolate_mode_t; +typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 5d494888a612..5def8e830fb0 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -111,8 +111,8 @@ struct uart_icount { __u32 buf_overrun; }; -typedef unsigned int __bitwise__ upf_t; -typedef unsigned int __bitwise__ upstat_t; +typedef unsigned int __bitwise upf_t; +typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ diff --git a/include/linux/types.h b/include/linux/types.h index baf718324f4a..d501ad3ba247 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -154,8 +154,8 @@ typedef u64 dma_addr_t; typedef u32 dma_addr_t; #endif -typedef unsigned __bitwise__ gfp_t; -typedef unsigned __bitwise__ fmode_t; +typedef unsigned __bitwise gfp_t; +typedef unsigned __bitwise fmode_t; #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; -- cgit From 47057abde515155a4fee53038e7772d6b387e0aa Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 12 Jan 2016 20:24:14 +0100 Subject: nfsd: add support for the umask attribute Clients can set the umask attribute when creating files to cause the server to apply it always except when inheriting permissions from the parent directory. That way, the new files will end up with the same permissions as files created locally. See https://tools.ietf.org/html/draft-ietf-nfsv4-umask-02 for more details. Signed-off-by: Andreas Gruenbacher Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 9094faf0699d..bca536341d1a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -440,6 +440,7 @@ enum lock_type4 { #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) +#define FATTR4_WORD2_MODE_UMASK (1UL << 17) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) -- cgit From 031a072a0b8ac2646def77aa310a95016c884bb0 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 23 Sep 2016 11:38:11 +0300 Subject: vfs: call vfs_clone_file_range() under freeze protection Move sb_start_write()/sb_end_write() out of the vfs helper and up into the ioctl handler. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..52663f1f3084 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1783,6 +1783,19 @@ extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); +static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len) +{ + int ret; + + sb_start_write(file_inode(file_out)->i_sb); + ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); + sb_end_write(file_inode(file_out)->i_sb); + + return ret; +} + struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); -- cgit From cb02de96ec724b84373488dd349e53897ab432f5 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 16 Dec 2016 12:40:55 +0000 Subject: x86/mpx: Move bd_addr to mm_context_t Currently bd_addr lives in mm_struct, which is otherwise architecture independent. Architecture-specific data is supposed to live within mm_context_t (itself contained in mm_struct). Other x86-specific context like the pkey accounting data lives in mm_context_t, and there's no readon the MPX data can't also live there. So as to keep the arch-specific data togather, and to set a good example for others, this patch moves bd_addr into x86's mm_context_t. Signed-off-by: Mark Rutland Acked-by: Dave Hansen Cc: Andrew Morton Link: http://lkml.kernel.org/r/1481892055-24596-1-git-send-email-mark.rutland@arm.com Signed-off-by: Thomas Gleixner --- include/linux/mm_types.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4a8acedf4b7d..ce70cebef603 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -508,10 +508,6 @@ struct mm_struct { bool tlb_flush_pending; #endif struct uprobes_state uprobes_state; -#ifdef CONFIG_X86_INTEL_MPX - /* address of the bounds directory */ - void __user *bd_addr; -#endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif -- cgit From 83a77e9ec4150ee4acc635638f7dedd9da523a26 Mon Sep 17 00:00:00 2001 From: Bartosz Folta Date: Wed, 14 Dec 2016 06:39:15 +0000 Subject: net: macb: Added PCI wrapper for Platform Driver. There are hardware PCI implementations of Cadence GEM network controller. This patch will allow to use such hardware with reuse of existing Platform Driver. Signed-off-by: Bartosz Folta Signed-off-by: David S. Miller --- include/linux/platform_data/macb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 21b15f6fee25..7815d50c26ff 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,6 +8,8 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +#include + /** * struct macb_platform_data - platform data for MACB Ethernet * @phy_mask: phy mask passed when register the MDIO bus @@ -15,12 +17,16 @@ * @phy_irq_pin: PHY IRQ * @is_rmii: using RMII interface? * @rev_eth_addr: reverse Ethernet address byte order + * @pclk: platform clock + * @hclk: AHB clock */ struct macb_platform_data { u32 phy_mask; int phy_irq_pin; u8 is_rmii; u8 rev_eth_addr; + struct clk *pclk; + struct clk *hclk; }; #endif /* __MACB_PDATA_H__ */ -- cgit From dcdc43d6642c828fa10d25130a92b712003d2ca4 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 15 Dec 2016 10:53:21 +0100 Subject: bpf: cgroup: annotate pointers in struct cgroup_bpf with __rcu The member 'effective' in 'struct cgroup_bpf' is protected by RCU. Annotate it accordingly to squelch a sparse warning. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7b6e5d168c95..92bc89ae7e20 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -20,7 +20,7 @@ struct cgroup_bpf { * when this cgroup is accessed. */ struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog *effective[MAX_BPF_ATTACH_TYPE]; + struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; }; void cgroup_bpf_put(struct cgroup *cgrp); -- cgit From 24c946cc5d35e32c5bb0c07ebdad32756e2bd20d Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:48 +0100 Subject: irnet: ppp: move IRNET_MINOR to include/linux/miscdevice.h This patch move the define for IRNET_MINOR to include/linux/miscdevice.h It is better that all minor number definitions are in the same place. Signed-off-by: Corentin Labbe Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/miscdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 722698a43d79..86d5704c9e23 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -32,6 +32,7 @@ #define STORE_QUEUE_MINOR 155 /* unused */ #define I2O_MINOR 166 #define MICROCODE_MINOR 184 +#define IRNET_MINOR 187 #define VFIO_MINOR 196 #define TUN_MINOR 200 #define CUSE_MINOR 203 -- cgit From f23bc46c30ca5ef58b8549434899fcbac41b2cfc Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:12:54 -0800 Subject: net: xdp: add invalid buffer warning This adds a warning for drivers to use when encountering an invalid buffer for XDP. For normal cases this should not happen but to catch this in virtual/qemu setups that I may not have expected from the emulation layer having a standard warning is useful. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a1658308612..af8a1804cac6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -602,6 +602,7 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_buffer(void); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; -- cgit From e8465447d2f3366069115f7453153561ac9a1220 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 16 Dec 2016 10:11:56 +0530 Subject: block: Remove unused member (busy) from struct blk_queue_tag Signed-off-by: Ritesh Harjani Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 286b2a264383..83695641bd5e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -288,7 +288,6 @@ enum blk_queue_state { struct blk_queue_tag { struct request **tag_index; /* map of busy tags */ unsigned long *tag_map; /* bit map of free/busy tags */ - int busy; /* current depth */ int max_depth; /* what we will send to device */ int real_max_depth; /* what the array can hold */ atomic_t refcnt; /* map can be shared */ -- cgit From aafe6ae9cee32df85eb5e8bb6dd1d918e6807b09 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:57 +0100 Subject: bpf: dynamically allocate digest scratch buffer Geert rightfully complained that 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") added a too large allocation of variable 'raw' from bss section, and should instead be done dynamically: # ./scripts/bloat-o-meter kernel/bpf/core.o.1 kernel/bpf/core.o.2 add/remove: 3/0 grow/shrink: 0/0 up/down: 33291/0 (33291) function old new delta raw - 32832 +32832 [...] Since this is only relevant during program creation path, which can be considered slow-path anyway, lets allocate that dynamically and be not implicitly dependent on verifier mutex. Move bpf_prog_calc_digest() at the beginning of replace_map_fd_with_map_ptr() and also error handling stays straight forward. Reported-by: Geert Uytterhoeven Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- include/linux/filter.h | 14 +++++++++++--- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8796ff03f472..201eb483c46f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,7 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); -void bpf_prog_calc_digest(struct bpf_prog *fp); +int bpf_prog_calc_digest(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index af8a1804cac6..702314253797 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -57,9 +57,6 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -/* Maximum BPF program size in bytes. */ -#define MAX_BPF_SIZE (BPF_MAXINSNS * sizeof(struct bpf_insn)) - /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -517,6 +514,17 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, return BPF_PROG_RUN(prog, xdp); } +static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) +{ + return prog->len * sizeof(struct bpf_insn); +} + +static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog) +{ + return round_up(bpf_prog_insn_size(prog) + + sizeof(__be64) + 1, SHA_MESSAGE_BYTES); +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), -- cgit From 5ccb071e97fbd9ffe623a0d3977cc6d013bee93c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:58 +0100 Subject: bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 201eb483c46f..f74ae68086dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -238,6 +238,8 @@ struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); +int __bpf_prog_charge(struct user_struct *user, u32 pages); +void __bpf_prog_uncharge(struct user_struct *user, u32 pages); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -318,6 +320,15 @@ static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } + +static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) +{ + return 0; +} + +static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) +{ +} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ -- cgit From 957ae5098185e763b5c06be6c3b4b6e98c048712 Mon Sep 17 00:00:00 2001 From: Nilesh Bacchewar Date: Mon, 7 Nov 2016 12:11:47 -0800 Subject: platform/x86: Add Whiskey Cove PMIC TMU support This adds TMU (Time Management Unit) support for Intel BXT platform. It enables the alarm wake-up functionality in the TMU unit of Whiskey Cove PMIC. Signed-off-by: Nilesh Bacchewar Reviewed-by: Mika Westerberg [andy: resolve merge conflict in Kconfig] Signed-off-by: Andy Shevchenko --- include/linux/mfd/intel_soc_pmic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index cf619dbeace2..956caa0628f5 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -26,6 +26,7 @@ struct intel_soc_pmic { struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; struct regmap_irq_chip_data *irq_chip_data_level2; + struct regmap_irq_chip_data *irq_chip_data_tmu; struct device *dev; }; -- cgit From 3f642a13359468181f29db3d8926ba36530be85e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 16 Dec 2016 18:49:38 -0500 Subject: NFS: Remove unused function nfs_revalidate_inode_rcu() Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cb631973839a..fe2e7810ae80 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -343,7 +343,6 @@ extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); -extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); -- cgit From 187e593d2779fb92ae1de06f873d6e192ba35d88 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 16 Dec 2016 18:51:15 -0500 Subject: NFS: Clean up nfs_attribute_timeout() It can be made static. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fe2e7810ae80..f1da8c8dd473 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -340,7 +340,6 @@ extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); -extern int nfs_attribute_timeout(struct inode *inode); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); -- cgit From 7b8589cc29e7c35dcfd2d5138979f17b48f90110 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 19 Dec 2016 16:22:48 -0800 Subject: ima: on soft reboot, save the measurement list The TPM PCRs are only reset on a hard reboot. In order to validate a TPM's quote after a soft reboot (eg. kexec -e), the IMA measurement list of the running kernel must be saved and restored on boot. This patch uses the kexec buffer passing mechanism to pass the serialized IMA binary_runtime_measurements to the next kernel. Link: http://lkml.kernel.org/r/1480554346-29071-7-git-send-email-zohar@linux.vnet.ibm.com Signed-off-by: Thiago Jung Bauermann Signed-off-by: Mimi Zohar Acked-by: "Eric W. Biederman" Acked-by: Dmitry Kasatkin Cc: Andreas Steffen Cc: Josh Sklar Cc: Dave Young Cc: Vivek Goyal Cc: Baoquan He Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Stewart Smith Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ima.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 0eb7c2e7f0d6..7f6952f8d6aa 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -11,6 +11,7 @@ #define _LINUX_IMA_H #include +#include struct linux_binprm; #ifdef CONFIG_IMA @@ -23,6 +24,10 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); extern void ima_post_path_mknod(struct dentry *dentry); +#ifdef CONFIG_IMA_KEXEC +extern void ima_add_kexec_buffer(struct kimage *image); +#endif + #else static inline int ima_bprm_check(struct linux_binprm *bprm) { @@ -62,6 +67,13 @@ static inline void ima_post_path_mknod(struct dentry *dentry) #endif /* CONFIG_IMA */ +#ifndef CONFIG_IMA_KEXEC +struct kimage; + +static inline void ima_add_kexec_buffer(struct kimage *image) +{} +#endif + #ifdef CONFIG_IMA_APPRAISE extern void ima_inode_post_setattr(struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, -- cgit From 1b011e2f13fcf37e1e577fed25b295808d6c83b9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 19 Dec 2016 16:23:12 -0800 Subject: ratelimit: fix WARN_ON_RATELIMIT return value The macro is to be used similarly as WARN_ON as: if (WARN_ON_RATELIMIT(condition, state)) do_something(); One would expect only 'condition' to affect the 'if', but WARN_ON_RATELIMIT does internally only: WARN_ON((condition) && __ratelimit(state)) So the 'if' is affected by the ratelimiting state too. Fix this by returning 'condition' in any case. Note that nobody uses WARN_ON_RATELIMIT yet, so there is nothing to worry about. But I was about to use it and was a bit surprised. Link: http://lkml.kernel.org/r/20161215093224.23126-1-jslaby@suse.cz Signed-off-by: Jiri Slaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ratelimit.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 57c9e0622a38..56375edf2ed2 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -77,8 +77,11 @@ extern int ___ratelimit(struct ratelimit_state *rs, const char *func); #ifdef CONFIG_PRINTK -#define WARN_ON_RATELIMIT(condition, state) \ - WARN_ON((condition) && __ratelimit(state)) +#define WARN_ON_RATELIMIT(condition, state) ({ \ + bool __rtn_cond = !!(condition); \ + WARN_ON(__rtn_cond && __ratelimit(state)); \ + __rtn_cond; \ +}) #define WARN_RATELIMIT(condition, format, ...) \ ({ \ -- cgit From c00d2c7e89880036f288a764599b2b8b87c0a364 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 20 Dec 2016 07:04:57 -0500 Subject: move aio compat to fs/aio.c ... and fix the minor buglet in compat io_submit() - native one kills ioctx as cleanup when put_user() fails. Get rid of bogus compat_... in !CONFIG_AIO case, while we are at it - they should simply fail with ENOSYS, same as for native counterparts. Signed-off-by: Al Viro --- include/linux/aio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 9eb42dbc5582..fdd0a343f455 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -14,14 +14,9 @@ typedef int (kiocb_cancel_fn)(struct kiocb *); /* prototypes */ #ifdef CONFIG_AIO extern void exit_aio(struct mm_struct *mm); -extern long do_io_submit(aio_context_t ctx_id, long nr, - struct iocb __user *__user *iocbpp, bool compat); void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline void exit_aio(struct mm_struct *mm) { } -static inline long do_io_submit(aio_context_t ctx_id, long nr, - struct iocb __user * __user *iocbpp, - bool compat) { return 0; } static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -- cgit From 5c43c52d5fb6163120ae5d9a281c3b757ca6119c Mon Sep 17 00:00:00 2001 From: Steven Wahl Date: Thu, 8 Dec 2016 17:02:28 +0000 Subject: NTB: correct ntb_peer_spad_read for case when callback is not supplied. Correct ntb_peer_spad_read for case when callback is not supplied Signed-off-by: Steve Wahl Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 6f47562d477b..816bd9835bee 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -968,6 +968,9 @@ static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, */ static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) { + if (!ntb->ops->peer_spad_read) + return 0; + return ntb->ops->peer_spad_read(ntb, idx); } -- cgit From 7c0f6ba682b9c7632072ffbedf8d328c8f3c42ba Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 24 Dec 2016 11:46:01 -0800 Subject: Replace with globally This was entirely automated, using the script by Al: PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*' sed -i -e "s!$PATT!#include !" \ $(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h) to do the replacement at the end of the merge window. Requested-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/isdnif.h | 2 +- include/linux/pagemap.h | 2 +- include/linux/poll.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/isdnif.h b/include/linux/isdnif.h index 0fc6ff276221..8d80fdc68647 100644 --- a/include/linux/isdnif.h +++ b/include/linux/isdnif.h @@ -500,6 +500,6 @@ typedef struct { * */ extern int register_isdn(isdn_if*); -#include +#include #endif /* __ISDNIF_H__ */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7dbe9148b2f8..f29f80f81dbf 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include /* for in_interrupt() */ diff --git a/include/linux/poll.h b/include/linux/poll.h index 37b057b63b46..a46d6755035e 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include extern struct ctl_table epoll_table[]; /* for sysctl */ -- cgit From c53b005dd64bdcf5acac00bd55ecf94dda22dc4f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 21 Dec 2016 20:19:50 +0100 Subject: scsi/bnx2fc: Convert to hotplug state machine Install the callbacks via the state machine. No functional change. This is the minimal fixup so we can remove the hotplug notifier mess completely. The real rework of this driver to use work queues is still stuck in review/testing on the SCSI mailing list. Signed-off-by: Sebastian Andrzej Siewior Cc: "James E.J. Bottomley" Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Peter Zijlstra Cc: Chad Dupuis Cc: QLogic-Storage-Upstream@qlogic.com Cc: Johannes Thumshirn Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20161221192111.757309869@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2ab7bf53d529..ab0e54d25647 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -41,6 +41,7 @@ enum cpuhp_state { CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, + CPUHP_SCSI_BNX2FC_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From e210faa2359f92eb2e417cd8462eb980a4dbb172 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 21 Dec 2016 20:19:51 +0100 Subject: scsi/bnx2i: Convert to hotplug state machine Install the callbacks via the state machine. No functional change. This is the minimal fixup so we can remove the hotplug notifier mess completely. The real rework of this driver to use work queues is still stuck in review/testing on the SCSI mailing list. Signed-off-by: Sebastian Andrzej Siewior Cc: "James E.J. Bottomley" Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Cc: Peter Zijlstra Cc: Chad Dupuis Cc: QLogic-Storage-Upstream@qlogic.com Cc: Johannes Thumshirn Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20161221192111.836895753@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ab0e54d25647..fc4587c05dd3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -42,6 +42,7 @@ enum cpuhp_state { CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, CPUHP_SCSI_BNX2FC_DEAD, + CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, -- cgit From 7b737965b33188bd3dbb44e938535c4006d97fbb Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Wed, 21 Dec 2016 20:19:52 +0100 Subject: staging/lustre/libcfs: Convert to hotplug state machine Install the callbacks via the state machine. No functional change. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Cc: devel@driverdev.osuosl.org Cc: Andreas Dilger Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: Oleg Drokin Cc: rt@linutronix.de Cc: lustre-devel@lists.lustre.org Link: http://lkml.kernel.org/r/20161202110027.htzzeervzkoc4muv@linutronix.de Link: http://lkml.kernel.org/r/20161221192111.922872524@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index fc4587c05dd3..175d276ac335 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -41,6 +41,7 @@ enum cpuhp_state { CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, + CPUHP_LUSTRE_CFS_DEAD, CPUHP_SCSI_BNX2FC_DEAD, CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, -- cgit From 530e9b76ae8f863dfdef4a6ad0b38613d32e8c3f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 21 Dec 2016 20:19:53 +0100 Subject: cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions hotcpu_notifier(), cpu_notifier(), __hotcpu_notifier(), __cpu_notifier(), register_hotcpu_notifier(), register_cpu_notifier(), __register_hotcpu_notifier(), __register_cpu_notifier(), unregister_hotcpu_notifier(), unregister_cpu_notifier(), __unregister_hotcpu_notifier(), __unregister_cpu_notifier() are unused now. Remove them and all related code. Remove also the now pointless cpu notifier error injection mechanism. The states can be executed step by step and error rollback is the same as cpu down, so any state transition can be tested w/o requiring the notifier error injection. Some CPU hotplug states are kept as they are (ab)used for hotplug state tracking. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20161221192112.005642358@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpu.h | 90 ---------------------------------------------- include/linux/cpuhotplug.h | 3 -- 2 files changed, 93 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 09807c2ce328..21f9c74496e7 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -57,9 +57,6 @@ struct notifier_block; #define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ #define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ -#define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ -#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ -#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ #define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ #define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug * lock is dropped */ @@ -80,80 +77,14 @@ struct notifier_block; #ifdef CONFIG_SMP extern bool cpuhp_tasks_frozen; -/* Need to know about CPUs going up/down? */ -#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) -#define cpu_notifier(fn, pri) { \ - static struct notifier_block fn##_nb = \ - { .notifier_call = fn, .priority = pri }; \ - register_cpu_notifier(&fn##_nb); \ -} - -#define __cpu_notifier(fn, pri) { \ - static struct notifier_block fn##_nb = \ - { .notifier_call = fn, .priority = pri }; \ - __register_cpu_notifier(&fn##_nb); \ -} - -extern int register_cpu_notifier(struct notifier_block *nb); -extern int __register_cpu_notifier(struct notifier_block *nb); -extern void unregister_cpu_notifier(struct notifier_block *nb); -extern void __unregister_cpu_notifier(struct notifier_block *nb); - -#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */ -#define cpu_notifier(fn, pri) do { (void)(fn); } while (0) -#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) - -static inline int register_cpu_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline int __register_cpu_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline void unregister_cpu_notifier(struct notifier_block *nb) -{ -} - -static inline void __unregister_cpu_notifier(struct notifier_block *nb) -{ -} -#endif - int cpu_up(unsigned int cpu); void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); -#define cpu_notifier_register_begin cpu_maps_update_begin -#define cpu_notifier_register_done cpu_maps_update_done - #else /* CONFIG_SMP */ #define cpuhp_tasks_frozen 0 -#define cpu_notifier(fn, pri) do { (void)(fn); } while (0) -#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) - -static inline int register_cpu_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline int __register_cpu_notifier(struct notifier_block *nb) -{ - return 0; -} - -static inline void unregister_cpu_notifier(struct notifier_block *nb) -{ -} - -static inline void __unregister_cpu_notifier(struct notifier_block *nb) -{ -} - static inline void cpu_maps_update_begin(void) { } @@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(void) { } -static inline void cpu_notifier_register_begin(void) -{ -} - -static inline void cpu_notifier_register_done(void) -{ -} - #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; @@ -182,12 +105,6 @@ extern void get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); -#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) -#define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri) -#define register_hotcpu_notifier(nb) register_cpu_notifier(nb) -#define __register_hotcpu_notifier(nb) __register_cpu_notifier(nb) -#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb) -#define __unregister_hotcpu_notifier(nb) __unregister_cpu_notifier(nb) void clear_tasks_mm_cpumask(int cpu); int cpu_down(unsigned int cpu); @@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void) {} #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) #define cpu_hotplug_enable() do { } while (0) -#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) -#define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) -/* These aren't inline functions due to a GCC bug. */ -#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) -#define __register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotcpu_notifier(nb) ({ (void)(nb); }) -#define __unregister_hotcpu_notifier(nb) ({ (void)(nb); }) #endif /* CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_PM_SLEEP_SMP diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 175d276ac335..0d5ef8563113 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -59,7 +59,6 @@ enum cpuhp_state { CPUHP_POWERPC_MMU_CTX_PREPARE, CPUHP_XEN_PREPARE, CPUHP_XEN_EVTCHN_PREPARE, - CPUHP_NOTIFY_PREPARE, CPUHP_ARM_SHMOBILE_SCU_PREPARE, CPUHP_SH_SH3X_PREPARE, CPUHP_BLK_MQ_PREPARE, @@ -74,7 +73,6 @@ enum cpuhp_state { CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_DEAD, - CPUHP_NOTF_ERR_INJ_PREPARE, CPUHP_MIPS_SOC_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -145,7 +143,6 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, - CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, -- cgit From 36e5b0e39194b09a10f19697fb9ea4ccc44eb166 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 21 Dec 2016 20:19:55 +0100 Subject: coresight/etm3/4x: Consolidate hotplug state space Even if both drivers are compiled in only one instance can run on a given system depending on the available tracer cell. So having seperate hotplug states for them is pointless. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Mathieu Poirier Link: http://lkml.kernel.org/r/20161221192112.162765484@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0d5ef8563113..4a938bee5858 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -119,7 +119,6 @@ enum cpuhp_state { CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, - CPUHP_AP_ARM_CORESIGHT4_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_X86_TBOOT_DYING, -- cgit From 6896bcd198df04777820cab4acc70142e87d5ce0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 21 Dec 2016 20:19:56 +0100 Subject: irqchip/gic: Consolidate hotplug state space Even if both drivers are compiled in only one instance can run on a given system depending on the available GIC version. So having seperate hotplug states for them is pointless. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Marc Zyngier Cc: Sebastian Siewior Link: http://lkml.kernel.org/r/20161221192112.252416267@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4a938bee5858..45c786cbb324 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -80,7 +80,6 @@ enum cpuhp_state { CPUHP_AP_SCHED_STARTING, CPUHP_AP_RCUTREE_DYING, CPUHP_AP_IRQ_GIC_STARTING, - CPUHP_AP_IRQ_GICV3_STARTING, CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_ARMADA_CASC_STARTING, -- cgit From 008b69e4d52f2cbee3ed0d0502edd78155000b1a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 21 Dec 2016 20:19:57 +0100 Subject: irqchip/armada-xp: Consolidate hotplug state space The mpic is either the main interrupt controller or is cascaded behind a GIC. The mpic is single instance and the modes are mutually exclusive, so there is no reason to have seperate cpu hotplug states. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Thomas Petazzoni Cc: Sebastian Siewior Cc: Marc Zyngier Link: http://lkml.kernel.org/r/20161221192112.333161745@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 45c786cbb324..20bfefbe7594 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -82,7 +82,6 @@ enum cpuhp_state { CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_IRQ_ARMADA_XP_STARTING, - CPUHP_AP_IRQ_ARMADA_CASC_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_UNCORE_STARTING, -- cgit From a5a1d1c2914b5316924c7893eb683a5420ebd3be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 21 Dec 2016 20:32:01 +0100 Subject: clocksource: Use a plain u64 instead of cycle_t There is no point in having an extra type for extra confusion. u64 is unambiguous. Conversion was done with the following coccinelle script: @rem@ @@ -typedef u64 cycle_t; @fix@ typedef cycle_t; @@ -cycle_t +u64 Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: John Stultz --- include/linux/clocksource.h | 22 +++++++++++----------- include/linux/dw_apb_timer.h | 2 +- include/linux/irqchip/mips-gic.h | 8 ++++---- include/linux/mlx4/device.h | 2 +- include/linux/timecounter.h | 12 ++++++------ include/linux/timekeeper_internal.h | 10 +++++----- include/linux/timekeeping.h | 4 ++-- include/linux/types.h | 3 --- 8 files changed, 30 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 65602d395a52..e315d04a2fd9 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -75,8 +75,8 @@ struct module; * structure. */ struct clocksource { - cycle_t (*read)(struct clocksource *cs); - cycle_t mask; + u64 (*read)(struct clocksource *cs); + u64 mask; u32 mult; u32 shift; u64 max_idle_ns; @@ -98,8 +98,8 @@ struct clocksource { #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; - cycle_t cs_last; - cycle_t wd_last; + u64 cs_last; + u64 wd_last; #endif struct module *owner; }; @@ -117,7 +117,7 @@ struct clocksource { #define CLOCK_SOURCE_RESELECT 0x100 /* simplify initialization of mask field */ -#define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) +#define CLOCKSOURCE_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from) { @@ -176,7 +176,7 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) * * XXX - This could use some mult_lxl_ll() asm optimization */ -static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) +static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift) { return ((u64) cycles * mult) >> shift; } @@ -236,13 +236,13 @@ static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz extern int timekeeping_notify(struct clocksource *clock); -extern cycle_t clocksource_mmio_readl_up(struct clocksource *); -extern cycle_t clocksource_mmio_readl_down(struct clocksource *); -extern cycle_t clocksource_mmio_readw_up(struct clocksource *); -extern cycle_t clocksource_mmio_readw_down(struct clocksource *); +extern u64 clocksource_mmio_readl_up(struct clocksource *); +extern u64 clocksource_mmio_readl_down(struct clocksource *); +extern u64 clocksource_mmio_readw_up(struct clocksource *); +extern u64 clocksource_mmio_readw_down(struct clocksource *); extern int clocksource_mmio_init(void __iomem *, const char *, - unsigned long, int, unsigned, cycle_t (*)(struct clocksource *)); + unsigned long, int, unsigned, u64 (*)(struct clocksource *)); extern int clocksource_i8253_init(void); diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 1f79b20918b1..4334106f44c3 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -50,6 +50,6 @@ dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base, unsigned long freq); void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs); void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs); -cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs); +u64 dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs); #endif /* __DW_APB_TIMER_H__ */ diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 81f930b0bca9..7b49c71c968b 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -259,11 +259,11 @@ extern void gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, unsigned int cpu_vec, unsigned int irqbase); extern void gic_clocksource_init(unsigned int); -extern cycle_t gic_read_count(void); +extern u64 gic_read_count(void); extern unsigned int gic_get_count_width(void); -extern cycle_t gic_read_compare(void); -extern void gic_write_compare(cycle_t cnt); -extern void gic_write_cpu_compare(cycle_t cnt, int cpu); +extern u64 gic_read_compare(void); +extern void gic_write_compare(u64 cnt); +extern void gic_write_cpu_compare(u64 cnt, int cpu); extern void gic_start_count(void); extern void gic_stop_count(void); extern int gic_get_c0_compare_int(void); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c9f379689dd0..93bdb3485192 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1460,7 +1460,7 @@ int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, u32 max_range_qpn); -cycle_t mlx4_read_clock(struct mlx4_dev *dev); +u64 mlx4_read_clock(struct mlx4_dev *dev); struct mlx4_active_ports { DECLARE_BITMAP(ports, MLX4_MAX_PORTS); diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index 4382035a75bb..2496ad4cfc99 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -20,7 +20,7 @@ #include /* simplify initialization of mask field */ -#define CYCLECOUNTER_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) +#define CYCLECOUNTER_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) /** * struct cyclecounter - hardware abstraction for a free running counter @@ -37,8 +37,8 @@ * @shift: cycle to nanosecond divisor (power of two) */ struct cyclecounter { - cycle_t (*read)(const struct cyclecounter *cc); - cycle_t mask; + u64 (*read)(const struct cyclecounter *cc); + u64 mask; u32 mult; u32 shift; }; @@ -63,7 +63,7 @@ struct cyclecounter { */ struct timecounter { const struct cyclecounter *cc; - cycle_t cycle_last; + u64 cycle_last; u64 nsec; u64 mask; u64 frac; @@ -77,7 +77,7 @@ struct timecounter { * @frac: pointer to storage for the fractional nanoseconds. */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, - cycle_t cycles, u64 mask, u64 *frac) + u64 cycles, u64 mask, u64 *frac) { u64 ns = (u64) cycles; @@ -134,6 +134,6 @@ extern u64 timecounter_read(struct timecounter *tc); * in the past. */ extern u64 timecounter_cyc2time(struct timecounter *tc, - cycle_t cycle_tstamp); + u64 cycle_tstamp); #endif diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e88005459035..110f4532188c 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,9 +29,9 @@ */ struct tk_read_base { struct clocksource *clock; - cycle_t (*read)(struct clocksource *cs); - cycle_t mask; - cycle_t cycle_last; + u64 (*read)(struct clocksource *cs); + u64 mask; + u64 cycle_last; u32 mult; u32 shift; u64 xtime_nsec; @@ -97,7 +97,7 @@ struct timekeeper { struct timespec64 raw_time; /* The following members are for timekeeping internal use */ - cycle_t cycle_interval; + u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; u32 raw_interval; @@ -136,7 +136,7 @@ extern void update_vsyscall_tz(void); extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm, struct clocksource *c, u32 mult, - cycle_t cycle_last); + u64 cycle_last); extern void update_vsyscall_tz(void); #else diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 361f8bf1429d..d2e804e15c3e 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -293,7 +293,7 @@ extern void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { - cycle_t cycles; + u64 cycles; ktime_t real; ktime_t raw; unsigned int clock_was_set_seq; @@ -321,7 +321,7 @@ struct system_device_crosststamp { * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { - cycle_t cycles; + u64 cycles; struct clocksource *cs; }; diff --git a/include/linux/types.h b/include/linux/types.h index d501ad3ba247..1e7bd24848fc 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -228,8 +228,5 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); -/* clocksource cycle base type */ -typedef u64 cycle_t; - #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ -- cgit From 2456e855354415bfaeb7badaa14e11b3e02c8466 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Dec 2016 11:38:40 +0100 Subject: ktime: Get rid of the union ktime is a union because the initial implementation stored the time in scalar nanoseconds on 64 bit machine and in a endianess optimized timespec variant for 32bit machines. The Y2038 cleanup removed the timespec variant and switched everything to scalar nanoseconds. The union remained, but become completely pointless. Get rid of the union and just keep ktime_t as simple typedef of type s64. The conversion was done with coccinelle and some manual mopping up. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra --- include/linux/futex.h | 4 +-- include/linux/hrtimer.h | 12 ++++----- include/linux/ktime.h | 68 +++++++++++++++++-------------------------------- include/linux/tick.h | 4 +-- include/linux/wait.h | 2 +- 5 files changed, 33 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 6435f46d6e13..7c5b694864cd 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -1,14 +1,14 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H +#include #include struct inode; struct mm_struct; struct task_struct; -union ktime; -long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout, +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); extern int diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 5e00f80b1535..cdab81ba29f8 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -228,8 +228,8 @@ static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t t static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { - timer->node.expires.tv64 = tv64; - timer->_softexpires.tv64 = tv64; + timer->node.expires = tv64; + timer->_softexpires = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) @@ -256,11 +256,11 @@ static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { - return timer->node.expires.tv64; + return timer->node.expires; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { - return timer->_softexpires.tv64; + return timer->_softexpires; } static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) @@ -297,7 +297,7 @@ extern void hrtimer_peek_ahead_timers(void); * this resolution values. */ # define HIGH_RES_NSEC 1 -# define KTIME_HIGH_RES (ktime_t) { .tv64 = HIGH_RES_NSEC } +# define KTIME_HIGH_RES (HIGH_RES_NSEC) # define MONOTONIC_RES_NSEC HIGH_RES_NSEC # define KTIME_MONOTONIC_RES KTIME_HIGH_RES @@ -333,7 +333,7 @@ __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) - rem.tv64 -= hrtimer_resolution; + rem -= hrtimer_resolution; return rem; } diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 0fb7ffb1775f..8e573deda55e 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -24,21 +24,8 @@ #include #include -/* - * ktime_t: - * - * A single 64-bit variable is used to store the hrtimers - * internal representation of time values in scalar nanoseconds. The - * design plays out best on 64-bit CPUs, where most conversions are - * NOPs and most arithmetic ktime_t operations are plain arithmetic - * operations. - * - */ -union ktime { - s64 tv64; -}; - -typedef union ktime ktime_t; /* Kill this */ +/* Nanosecond scalar representation for kernel time values */ +typedef s64 ktime_t; /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value @@ -50,39 +37,34 @@ typedef union ktime ktime_t; /* Kill this */ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { if (unlikely(secs >= KTIME_SEC_MAX)) - return (ktime_t){ .tv64 = KTIME_MAX }; + return KTIME_MAX; - return (ktime_t) { .tv64 = secs * NSEC_PER_SEC + (s64)nsecs }; + return secs * NSEC_PER_SEC + (s64)nsecs; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ -#define ktime_sub(lhs, rhs) \ - ({ (ktime_t){ .tv64 = (lhs).tv64 - (rhs).tv64 }; }) +#define ktime_sub(lhs, rhs) ((lhs) - (rhs)) /* Add two ktime_t variables. res = lhs + rhs: */ -#define ktime_add(lhs, rhs) \ - ({ (ktime_t){ .tv64 = (lhs).tv64 + (rhs).tv64 }; }) +#define ktime_add(lhs, rhs) ((lhs) + (rhs)) /* * Same as ktime_add(), but avoids undefined behaviour on overflow; however, * this means that you must check the result for overflow yourself. */ -#define ktime_add_unsafe(lhs, rhs) \ - ({ (ktime_t){ .tv64 = (u64) (lhs).tv64 + (rhs).tv64 }; }) +#define ktime_add_unsafe(lhs, rhs) ((u64) (lhs) + (rhs)) /* * Add a ktime_t variable and a scalar nanosecond value. * res = kt + nsval: */ -#define ktime_add_ns(kt, nsval) \ - ({ (ktime_t){ .tv64 = (kt).tv64 + (nsval) }; }) +#define ktime_add_ns(kt, nsval) ((kt) + (nsval)) /* * Subtract a scalar nanosecod from a ktime_t variable * res = kt - nsval: */ -#define ktime_sub_ns(kt, nsval) \ - ({ (ktime_t){ .tv64 = (kt).tv64 - (nsval) }; }) +#define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) /* convert a timespec to ktime_t format: */ static inline ktime_t timespec_to_ktime(struct timespec ts) @@ -103,16 +85,16 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) } /* Map the ktime_t to timespec conversion to ns_to_timespec function */ -#define ktime_to_timespec(kt) ns_to_timespec((kt).tv64) +#define ktime_to_timespec(kt) ns_to_timespec((kt)) /* Map the ktime_t to timespec conversion to ns_to_timespec function */ -#define ktime_to_timespec64(kt) ns_to_timespec64((kt).tv64) +#define ktime_to_timespec64(kt) ns_to_timespec64((kt)) /* Map the ktime_t to timeval conversion to ns_to_timeval function */ -#define ktime_to_timeval(kt) ns_to_timeval((kt).tv64) +#define ktime_to_timeval(kt) ns_to_timeval((kt)) /* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ -#define ktime_to_ns(kt) ((kt).tv64) +#define ktime_to_ns(kt) (kt) /** @@ -126,7 +108,7 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) */ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2) { - return cmp1.tv64 == cmp2.tv64; + return cmp1 == cmp2; } /** @@ -141,9 +123,9 @@ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2) */ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2) { - if (cmp1.tv64 < cmp2.tv64) + if (cmp1 < cmp2) return -1; - if (cmp1.tv64 > cmp2.tv64) + if (cmp1 > cmp2) return 1; return 0; } @@ -182,7 +164,7 @@ static inline s64 ktime_divns(const ktime_t kt, s64 div) */ BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { - s64 ns = kt.tv64; + s64 ns = kt; u64 tmp = ns < 0 ? -ns : ns; do_div(tmp, div); @@ -199,7 +181,7 @@ static inline s64 ktime_divns(const ktime_t kt, s64 div) * so catch them on 64bit as well. */ WARN_ON(div < 0); - return kt.tv64 / div; + return kt / div; } #endif @@ -256,7 +238,7 @@ extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts) { - if (kt.tv64) { + if (kt) { *ts = ktime_to_timespec(kt); return true; } else { @@ -275,7 +257,7 @@ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, struct timespec64 *ts) { - if (kt.tv64) { + if (kt) { *ts = ktime_to_timespec64(kt); return true; } else { @@ -290,20 +272,16 @@ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, * this resolution values. */ #define LOW_RES_NSEC TICK_NSEC -#define KTIME_LOW_RES (ktime_t){ .tv64 = LOW_RES_NSEC } +#define KTIME_LOW_RES (LOW_RES_NSEC) static inline ktime_t ns_to_ktime(u64 ns) { - static const ktime_t ktime_zero = { .tv64 = 0 }; - - return ktime_add_ns(ktime_zero, ns); + return ns; } static inline ktime_t ms_to_ktime(u64 ms) { - static const ktime_t ktime_zero = { .tv64 = 0 }; - - return ktime_add_ms(ktime_zero, ms); + return ms * NSEC_PER_MSEC; } # include diff --git a/include/linux/tick.h b/include/linux/tick.h index 62be0786d6d0..a04fea19676f 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -127,9 +127,7 @@ static inline void tick_nohz_idle_exit(void) { } static inline ktime_t tick_nohz_get_sleep_length(void) { - ktime_t len = { .tv64 = NSEC_PER_SEC/HZ }; - - return len; + return NSEC_PER_SEC / HZ; } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } diff --git a/include/linux/wait.h b/include/linux/wait.h index 2408e8d5c05c..1421132e9086 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -510,7 +510,7 @@ do { \ hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ hrtimer_init_sleeper(&__t, current); \ - if ((timeout).tv64 != KTIME_MAX) \ + if ((timeout) != KTIME_MAX) \ hrtimer_start_range_ns(&__t.timer, timeout, \ current->timer_slack_ns, \ HRTIMER_MODE_REL); \ -- cgit From 8b0e195314fabd58a331c4f7b6db75a1565535d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Dec 2016 12:30:41 +0100 Subject: ktime: Cleanup ktime_set() usage ktime_set(S,N) was required for the timespec storage type and is still useful for situations where a Seconds and Nanoseconds part of a time value needs to be converted. For anything where the Seconds argument is 0, this is pointless and can be replaced with a simple assignment. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ac7fa34db8a7..b53c0cfd417e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3227,7 +3227,7 @@ static inline ktime_t net_timedelta(ktime_t t) static inline ktime_t net_invalid_timestamp(void) { - return ktime_set(0, 0); + return 0; } struct sk_buff *skb_clone_sk(struct sk_buff *skb); -- cgit From 1f3a8e49d8f28f498b8694464623ac20aebfe62a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Dec 2016 12:43:07 +0100 Subject: ktime: Get rid of ktime_equal() No point in going through loops and hoops instead of just comparing the values. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra --- include/linux/ktime.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 8e573deda55e..0c8bd45c8206 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -96,21 +96,6 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ #define ktime_to_ns(kt) (kt) - -/** - * ktime_equal - Compares two ktime_t variables to see if they are equal - * @cmp1: comparable1 - * @cmp2: comparable2 - * - * Compare two ktime_t variables. - * - * Return: 1 if equal. - */ -static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2) -{ - return cmp1 == cmp2; -} - /** * ktime_compare - Compares two ktime_t variables for less, greater or equal * @cmp1: comparable1 -- cgit From 6326fec1122cde256bd2a8c63f2606e08e44ce1d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 25 Dec 2016 13:00:29 +1000 Subject: mm: Use owner_priv bit for PageSwapCache, valid when PageSwapBacked A page is not added to the swap cache without being swap backed, so PageSwapBacked mappings can use PG_owner_priv_1 for PageSwapCache. Signed-off-by: Nicholas Piggin Acked-by: Hugh Dickins Cc: Dave Hansen Cc: Bob Peterson Cc: Steven Whitehouse Cc: Andrew Lutomirski Cc: Andreas Gruenbacher Cc: Peter Zijlstra Cc: Mel Gorman Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74e4dda91238..a57c909a15e4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -87,7 +87,6 @@ enum pageflags { PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ PG_head, /* A head page */ - PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ @@ -110,6 +109,9 @@ enum pageflags { /* Filesystems */ PG_checked = PG_owner_priv_1, + /* SwapBacked */ + PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ + /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. @@ -314,7 +316,13 @@ PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP -PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) +static __always_inline int PageSwapCache(struct page *page) +{ + return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); + +} +SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) +CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(SwapCache) #endif @@ -701,12 +709,12 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. */ -#define PAGE_FLAGS_CHECK_AT_FREE \ - (1UL << PG_lru | 1UL << PG_locked | \ - 1UL << PG_private | 1UL << PG_private_2 | \ - 1UL << PG_writeback | 1UL << PG_reserved | \ - 1UL << PG_slab | 1UL << PG_swapcache | 1UL << PG_active | \ - 1UL << PG_unevictable | __PG_MLOCKED) +#define PAGE_FLAGS_CHECK_AT_FREE \ + (1UL << PG_lru | 1UL << PG_locked | \ + 1UL << PG_private | 1UL << PG_private_2 | \ + 1UL << PG_writeback | 1UL << PG_reserved | \ + 1UL << PG_slab | 1UL << PG_active | \ + 1UL << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. -- cgit From 62906027091f1d02de44041524f0769f60bb9cf3 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 25 Dec 2016 13:00:30 +1000 Subject: mm: add PageWaiters indicating tasks are waiting for a page bit Add a new page flag, PageWaiters, to indicate the page waitqueue has tasks waiting. This can be tested rather than testing waitqueue_active which requires another cacheline load. This bit is always set when the page has tasks on page_waitqueue(page), and is set and cleared under the waitqueue lock. It may be set when there are no tasks on the waitqueue, which will cause a harmless extra wakeup check that will clears the bit. The generic bit-waitqueue infrastructure is no longer used for pages. Instead, waitqueues are used directly with a custom key type. The generic code was not flexible enough to have PageWaiters manipulation under the waitqueue lock (which simplifies concurrency). This improves the performance of page lock intensive microbenchmarks by 2-3%. Putting two bits in the same word opens the opportunity to remove the memory barrier between clearing the lock bit and testing the waiters bit, after some work on the arch primitives (e.g., ensuring memory operand widths match and cover both bits). Signed-off-by: Nicholas Piggin Cc: Dave Hansen Cc: Bob Peterson Cc: Steven Whitehouse Cc: Andrew Lutomirski Cc: Andreas Gruenbacher Cc: Peter Zijlstra Cc: Mel Gorman Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/page-flags.h | 9 +++++++++ include/linux/pagemap.h | 23 +++++++++++------------ include/linux/writeback.h | 1 - 4 files changed, 22 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4424784ac374..fe6b4036664a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1758,6 +1758,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } +extern void __init pagecache_init(void); + extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a57c909a15e4..c56b39890a41 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -73,6 +73,7 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ + PG_waiters, /* Page has waiters, check its waitqueue */ PG_error, PG_referenced, PG_uptodate, @@ -169,6 +170,9 @@ static __always_inline int PageCompound(struct page *page) * for compound page all operations related to the page flag applied to * head page. * + * PF_ONLY_HEAD: + * for compound page, callers only ever operate on the head page. + * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. @@ -178,6 +182,9 @@ static __always_inline int PageCompound(struct page *page) */ #define PF_ANY(page, enforce) page #define PF_HEAD(page, enforce) compound_head(page) +#define PF_ONLY_HEAD(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(PageTail(page), page); \ + page;}) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ compound_head(page);}) @@ -255,6 +262,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) +PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) @@ -743,6 +751,7 @@ static inline int page_has_private(struct page *page) #undef PF_ANY #undef PF_HEAD +#undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #endif /* !__GENERATING_BOUNDS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index f29f80f81dbf..324c8dbad1e1 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -486,22 +486,14 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, * and for filesystems which need to wait on PG_private. */ extern void wait_on_page_bit(struct page *page, int bit_nr); - extern int wait_on_page_bit_killable(struct page *page, int bit_nr); -extern int wait_on_page_bit_killable_timeout(struct page *page, - int bit_nr, unsigned long timeout); - -static inline int wait_on_page_locked_killable(struct page *page) -{ - if (!PageLocked(page)) - return 0; - return wait_on_page_bit_killable(compound_head(page), PG_locked); -} +extern void wake_up_page_bit(struct page *page, int bit_nr); -extern wait_queue_head_t *page_waitqueue(struct page *page); static inline void wake_up_page(struct page *page, int bit) { - __wake_up_bit(page_waitqueue(page), &page->flags, bit); + if (!PageWaiters(page)) + return; + wake_up_page_bit(page, bit); } /* @@ -517,6 +509,13 @@ static inline void wait_on_page_locked(struct page *page) wait_on_page_bit(compound_head(page), PG_locked); } +static inline int wait_on_page_locked_killable(struct page *page) +{ + if (!PageLocked(page)) + return 0; + return wait_on_page_bit_killable(compound_head(page), PG_locked); +} + /* * Wait for a page to complete writeback */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c78f9f0920b5..5527d910ba3d 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -375,7 +375,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); -void page_writeback_init(void); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); -- cgit